fix 代码验证
Use when you have lint errors, formatting issues, or before committing code to ensure it passes CI.
⌘K 发布技能 TDD / BDD
测试驱动开发流程 · 728 个 Skill
筛选与排序728 个结果
Flags 代码排查
Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.
测试
Use when you need to run tests for React core.
验证
Use when you want to validate changes before committing, or when you need to check all React contribution requirements.
n8n Issue 创建
Create Linear tickets or GitHub issues following n8n conventions.
n8n PR 创建
Creates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation.
N8n:node 代码测试
Add OAuth2 credential support to an existing n8n node — creates the credential file, updates the node, adds tests, and keeps the CLI constan…
N8n:reproduce 上下
Reproduce a bug from a Linear ticket with a failing test.
Agent 架构 审计
Full-stack diagnostic for agent and LLM applications.
技能 Comply
检查 Skill 合规性：用分级场景验证规则与 Agent 定义是否真的被遵循。
Agent 生成器
Search existing local, marketplace, GitHub, and web skill sources before creating a new skill.
open PR审查
Open a pull request with proper PR template, test coverage, and review workflow.
Karpathy 代码审查
Behavioral guidelines to reduce common LLM coding mistakes.
wpf Winui3 迁移
Guide for migrating PowerToys modules from WPF to WinUI 3 (Windows App SDK).
Agent 开发
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use des…
技能 开发
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Electron 浏览器优化
Guide for performing Chromium version upgrades in the Electron project.
Electron node 升级
Guide for performing Node.js version upgrades in the Electron project.
Debugger 技能排查
| You are an expert debugger who uses systematic approaches to identify and resolve software issues efficiently.
Vercel 上下文审查
React composition patterns that scale.
Angular 开发
Generates Angular code and provides architectural guidance.
Playwright 浏览器启动
Automate browser interactions, test web pages and work with Playwright tests.
Playwright 代码排查
DevOps workflows for Playwright - CI failure analysis, workflow debugging, and release operations.
Claude 部署
Automated semantic versioning and release workflow for Claude Code plugins.
Agent 生成器
Prime a codebase by reading every source file in full.
Timeline 报告
Generate a "Journey Into [Project]" narrative report analyzing a project's entire development history from claude-mem's timeline.
Agent 技能排查
Build or extend LobeHub Agent Signal pipelines for background or quiet agent work driven by event sources, semantic signals, and action handlers.
Agent 浏览器
Drive a real browser to inspect or interact with a web page or app — navigate, take screenshots, read console and network, fill simple forms…
Caveman 技能验证
> Compress natural language files (CLAUDE.md, todos, preferences) into caveman-speak to reduce input tokens.
Caveman 审查
> Write code review comments terse and actionable.
Agent 生成器
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization.
git 上下文规划
MUST USE for ANY git operations.
代码 Simplifier
Review RTK Rust code for idiomatic simplification.
Presentation 技能转
Knowledge about the presentation slide format, weight system, navigation, and section structure Knowledge about how the presentation at presentation/index.html is structured.
Presentation 技能同
Knowledge about CSS classes, component patterns, and syntax highlighting in the presentation CSS classes and HTML patterns used in presentation/index.html.
Agent 技能验证
Agent skill for coder - invoke with $agent-coder color: "#FF6B35" description: Implementation specialist for writing clean, efficient code e…
Agent 技能验证
Agent skill for implementer-sparc-coder - invoke with $agent-implementer-sparc-coder name: sparc-coder type: development description: Transf…
Agent 技能测试
Agent skill for tdd-london-swarm - invoke with $agent-tdd-london-swarm name: tdd-london-swarm color: "#E91E63" description: TDD London Schoo…
Agent 数据库 学习 Plu
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms.
Android e2e 测试
Test Expo Router features on Android emulators using ADB.
Remotion 最佳 实践
Best practices for Remotion - Video creation in React Use this skills whenever you are dealing with Remotion code to obtain the domain-specific knowledge.
bmad 产品 Brief
Create, update, or validate a product brief.
代码 Simplificatio
Simplifies code for clarity.
前端 UI Engineerin
Builds production-quality UIs.
idea 技能测试
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking.
规划 task Breakdow
Breaks work into ordered tasks.
spec 驱动 开发
Creates specs before coding.
TypeScript 审查
Review TypeScript and JavaScript code changes for compliance with Metabase coding standards, style violations, and code quality issues.
TypeScript 写作
Write TypeScript and JavaScript code following Metabase coding standards and best practices.
Creating 金融 模型
This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions A comprehensive financial modeling toolkit for investment analysis, valuation, and risk assessment using industry-standard methodologies.
Agent 生成器
Use this skill when creating or controlling sprite animations in Phaser 4.
game 技能转换
Use this skill when working with Phaser 4 game object components and the mixin system.
Backtesting 技能验证
Build robust backtesting systems for trading strategies with proper handling of look-ahead bias, survivorship bias, and transaction costs.
Competitive 技能规划
Analyze competition, identify differentiation opportunities, and develop winning market positioning strategies using Porter's Five Forces, Blue Ocean Strategy, and positioning maps.
Godot 技能创建
Master Godot 4 GDScript patterns including signals, scenes, state machines, and optimization.
Market Sizing 分析
Calculate TAM/SAM/SOM for market opportunities using top-down, bottom-up, and value theory methodologies.
Python 设计 Patter
Python design patterns including KISS, Separation of Concerns, Single Responsibility, and composition over inheritance.
React 助手
Build production React Native apps with Expo, navigation, native modules, offline sync, and cross-platform patterns.
Responsive 设计
Implement modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first breakpoint strategies.
Startup 金融 Model
Build comprehensive 3-5 year financial models with revenue projections, cost structures, cash flow analysis, and scenario planning for early-stage startups.
Stripe 集成
Implement Stripe payment processing for robust, PCI-compliant payment flows including checkout, subscriptions, and webhooks.
self 技能验证
Comprehensive Claude Code self-assessment and learning path advisor.
技能
Manage local skills - list, add, remove, search, edit, setup wizard Meta-skill for managing oh-my-claudecode skills via CLI-like commands.
Impeccable 浏览器审查
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface.
Impeccable 浏览器审查
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface.
技能 Installer
Install, update, trust, or inspect DeepSeek skills from GitHub or local skill folders.
Agent 技能审计
| Evaluate AI agent systems against the OWASP Agentic Security Initiative (ASI) Top 10 — the industry standard for agent security posture.
营销 Ideas
When the user needs marketing ideas, inspiration, or strategies for their SaaS or software product.
营销 Psychology
When the user wants to apply psychological principles, mental models, or behavioral science to marketing.
技能
Manage local skills - list, add, remove, search, edit, setup wizard Meta-skill for managing oh-my-codex skills via CLI-like commands.
Agent 配置 Mainten
| Use this skill when changing the shared agent setup for the repository.
技能 Installer
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path.
dcf 技能验证
Performs discounted cash flow (DCF) valuation analysis to estimate intrinsic value per share.
学术 论文 审查
Multi-perspective academic paper review with dynamic reviewer personas.
学术 流水线
Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize.
Agent 开发
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use des…
技能 开发
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
Agent 会话排查
Workflow for agent self-improvement via isolated execution, evaluation, and process refinement.
css API审查
CSS animation adapter patterns for HyperFrames.
Hyperframes 技能审查
Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML.
Brainstorm 头脑风暴
Activate brainstorming mode for collaborative discovery and creative problem-solving.
Token 上下文规划
Activate ultra-compressed output mode for maximum token efficiency.
规划 文件
Implements Manus-style file-based planning to organize and track progress on complex tasks.
规划 文件
Implements Manus-style file-based planning to organize and track progress on complex tasks.
规划 文件 zh
基于 Manus 风格的文件规划系统，用于组织和跟踪复杂任务的进度。
Vueuse 技能验证
Apply VueUse composables where appropriate to build concise, maintainable Vue.js / Nuxt features.
wps 代码同步
Guide for working with Wave Terminal's WPS (Wave PubSub) event system.
OpenAI 助手
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path.
技能 Improve
Improve a skill using a test-fix-retest loop.
技能 测试
Validate skill files for structural compliance and behavioral correctness.
me 教学
Personalized 1-on-1 AI tutor.
无障碍 审查
Run a WCAG 2.1 AA accessibility audit on a design or page.
金融 Statements
Generate financial statements (income statement, balance sheet, cash flow) with period-over-period comparison and variance analysis.
Interview 技能创建
Create structured interview plans with competency-based questions and scorecards.
Legal 上下文审查
Assess and classify legal risks using a severity-by-likelihood framework with escalation criteria.
产品 头脑风暴
Brainstorm product ideas, explore problem spaces, and challenge assumptions as a thinking partner.
审查 Contract
Review a contract against your organization's negotiation playbook — flag deviations, generate redlines, provide business impact analysis.
Skillify 技能审查
| A feature is "properly skilled" when all 11 checklist items pass.
pua 会话排查
你正处于一个高绩效文化的团队中。
pua 技能审查
PUA for Trae — 高能动性治理 Skill 这个 Trae 版只用 SKILL.md 表达行为合约：Trae 可以加载 Skill，但不会自动获得 Claude Code 的 hooks、slash commands、subagents 和 Stop feedback…
Interview 技能规划
Technical interview preparation expert for algorithms, system design, and behavioral questions A seasoned engineering hiring manager and interview coach with deep experience across algorithm challenges, system design rounds, and behavioral assessments at top technology companies.
Agent 生成器
Project management expert for Agile, estimation, risk management, and stakeholder communication A certified project management professional with deep experience leading software projects using Agile methodologies, managing cross-functional teams, and delivering complex products on schedule.
cicd PR排查
CI/CD reference for Megatron-LM.
Simple PR审查
Create a simple PR from staged changes with an auto-generated commit message Follow these steps to create a simple PR from staged changes: Run: git status Verify that all changes have been staged (no unstaged changes).
Videocaptioner 模
Process video subtitles — transcribe speech, optimize/translate text, burn styled subtitles into video.
Agents 上下文创建
Compose custom agents from base traits, voices, and specializations for specialized perspectives.
Implementing 代码审
'Implement network segmentation based on the Purdue Enterprise Reference Classify all network assets and data flows according to the Purdue Model hierarchy.
系统化 审查
Structured methodology for comprehensive literature review following PRISMA guidelines.
ceo 配置
One-time onboarding for the executive/manager commitment workflow — delegation-heavy, meeting prep, decision capture, morning and evening di…
Portfolio Agent创
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction.
Competitor 分析
Analyze competitors with strengths, weaknesses, and differentiation opportunities.
Customer 上下文创建
Create an end-to-end customer journey map with stages, touchpoints, emotions, pain points, and opportunities.
营销 Ideas
Generate 5 creative, cost-effective marketing ideas with channels, messaging, and engagement rationale.
swot 分析
Perform a detailed SWOT analysis — strengths, weaknesses, opportunities, and threats with actionable recommendations.
Novelty 检查
Check whether a proposed method/idea has already been done in the literature: $ARGUMENTS Given a method description, systematically verify its novelty: For EACH core claim, search using ALL available sources: Call REVIEWERMODEL via Codex MCP (mcpcodex__codex) with xhigh reasoning: config: {"modelreasoningeffort": "xhigh"}
Novelty 检查
Verify research idea novelty against recent literature.
Patent Novelty 检
Assess patentability of: $ARGUMENTS Adapted from /novelty-check for patent legal standards.
Patent 审查
Get a multi-round patent examiner review of the patent application based on: $ARGUMENTS Adapted from /research-review.
Agent 深度 Links
Build, validate, and troubleshoot deep links for Codex, Cursor, VS Code, Visual Studio, and similar tools.
技能 Installer
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path.
Embedded 代码排查
Use when developing firmware for microcontrollers, implementing RTOS applications, or optimizing power consumption.
Flutter 技能验证
Use when building cross-platform applications with Flutter 3+ and Dart.
Shopify API排查
Builds and debugs Shopify themes (.liquid files, theme.json, sections), develops custom Shopify apps (shopify.app.toml, OAuth, webhooks), and implements Storefront API integrations for headless storefronts.
fix PR验证
End-to-end bug fix workflow for the Exposed project.
营销规划
Create a minimalist marketing plan focused on building an audience through content, not ads.
mvp 文档创建
Guide building a minimum viable product the minimalist entrepreneur way — manual first, then processized, then productized.
idea 验证
Validate a business idea using the minimalist entrepreneur framework.
提示词 Master
Generates optimized prompts for AI tools.
Finance 技能验证
Generate a source-backed weekly financial trading outlook from daily-finance, finance-core-analysis, and finance-explosive-article outputs plus fresh authoritative market data.
Grocery 技能验证
A skill to calculate grocery prices with country-specific taxes.
技能 Installer
> Follow the workflow below exactly.
技能 管理器
> Remove or quiet a community skill after install.
技能 质量测试
> for evaluating whether the skill fits the user's team and workflow, and whether it duplicates something already installed) This QA check runs automatically as part of /legal-builder-hub:skill-installer.
Newsblur 浏览器验证
Manage your NewsBlur from the terminal.
Web 视频 Presentat
把一篇文章或口播稿，做成"看起来像视频"的点击驱动 16:9 网页演示，可选合成口播音频。
pr PR验证
Create a feature branch and open a pull request for the current changes.
ads 技能审计
LinkedIn Ads deep analysis for B2B advertising.
cad 技能审查
Create, modify, inspect, and validate STEP-first build123d/Python CAD parts and assemblies.
技能 Installer
Install Codex skills from curated sources or GitHub paths.
重构
Structural refactoring pass on changed code.
使用 超级能力
在开始任何对话时使用——确立如何查找和使用技能，要求在任何响应（包括澄清性问题）之前调用 Skill 工具 如果你是作为子智能体被分派来执行特定任务的，跳过此技能。
网络 Penetration 测
网络渗透测试的专业技能和方法论 网络渗透测试是评估网络基础设施安全性的重要环节。
Agent 技能创建
Use when creating or configuring Claude Code agents and their frontmatter.
技能 开发
This skill should be used when the user asks to create a new skill, repair an existing skill, improve trigger descriptions, reorganize skill structure, or make a Claude skill more reusable and internally consistent.
skill-improver
This skill should be used when the user asks to "apply skill improvements", "update skill from plan", "execute improvement plan", "fix skill issues", "implement skill recommendations", or mentions applying improvements from quality review reports.
Agentica 提示词
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity Write prompts that Agentica agents reliably follow.
Agentica 技能排查
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration Build AI agents in Python using the Agentica framework.
Docetl 技能验证
Build and run LLM-powered data processing pipelines with DocETL.
Lessons 会话审查
Record a lesson learned after a user correction, or review existing lessons at session start Manages the self-improvement loop.
技能 写作
Write and improve agent skills (SKILL.md files).
技能 Copilot Provi
GitHub Copilot CLI as optional zero-cost provider via copilot -p programmatic mode GitHub Copilot CLI (GA since Feb 2026) serves as an optional provider in the Claude Octopus multi-LLM ecosystem.
技能 调试
Debug issues methodically — use when stuck on errors, test failures, or unexpected behavior NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST…
技能 Decision Supp
Present options with trade-offs for informed decision-making — use when choosing between approaches Structured approach to presenting option…
技能 deck
Generate slide deck presentations from briefs — use when you need slides, pitch decks, or visual summaries Generate professional slide decks…
技能 Factory
Run a full build-and-ship pipeline from a spec — use for hands-off project generation DO NOT call Skill() again.
技能 Finish 分支
Wrap up a branch — run tests, create PR, merge or discard — use when implementation is done This generated Codex skill preserves an enforced…
技能 Intent Contra
Lock in user goals upfront and validate outputs against them — use to prevent scope drift The intent contract creates a persistent record of…
技能 Issue
Track project blockers, bugs, and gaps across sessions — use when issues pile up or need triage Cross-session issue tracking for persistent…
技能 Native Escala
Route ordinary init, review, and security requests to Claude-native capabilities first;
技能 简历
Pick up where you left off from a previous session — use after context resets, compaction, or new conversations Restore context from a previ…
技能 审查 Response
How to handle code review feedback — verify before implementing, push back when wrong, never agree blindly Code review requires technical ev…
技能 Rollback
Roll back to a previous checkpoint via git — use when a change went wrong and you need to revert Safely rollback to a previous checkpoint wh…
技能 Staged 审查
Review code in two passes: spec compliance then quality — use for thorough PR or feature reviews This generated Codex skill preserves an enf…
技能 Status
Show where you are in the workflow and what to do next — use for progress checks and orientation Display current project status, roadmap pro…
技能 tdd
Build features with tests-before-code rigor — use for new features needing test coverage NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST Wri…
技能 Visual Feedba
Process screenshot-based UI/UX feedback to fix visual issues — use when users share screenshots of bugs Systematic approach to processing im…
Agent 代码创建
Core runtime behavior for the atopile sidebar agent: identity, persistence model, execution rules, and tool recipes.
ato 技能审查
Authoritative ato authoring and review skill: language reference, stdlib, design patterns, and end-to-end board design workflow.
开发
LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/html artifacts, and discover/debug ConfigFlags.
Faebryk API创建
How Faebryk's TypeGraph works (GraphView + Zig edges), how to traverse/resolve references, and how FabLL types/traits map onto edge types.
Graph API创建
How the Zig-backed instance graph works (GraphView/NodeReference/EdgeReference), the real Python API surface, and the invariants around allocation, attributes, and cleanup.
Pyzig API排查
How the Zig↔Python binding layer works (pyzig), including build-on-import, wrapper generation patterns, ownership rules, and where to add ne…
bc 检查
Analyze a qlty pull request (or the current branch) for backwards-incompatible behavior changes.
MCP 助手
AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs,…
l PR创建
Create a draft pull request targeting develop.
Ralph 技能审查
Run, monitor, resume, merge, and debug Ralph loops.
bpmn 代码创建
Create business process diagrams using PlantUML syntax with BPMN, EIP, and Lean Mapping stencil icons.
小说 Prose
小说写作技法 - 当需要逐章执笔创作小说正文时触发。
小说 审查
小说章节审核 - 当需要校对、审核小说章节质量时触发。
小说 Worldbuilding
小说架构设计 - 当用户需要设计小说大纲、人物档案、世界观、伏笔台账时触发。
发布
Automate the full hoverfly release process — version bump, GitHub release, wait for CI, trigger Homebrew update.
work PR测试
Work on an issue or PR - implement changes, add tests, update docs, lint, add bump file, and create a PR You are given an issue or external PR to implement.
发布
Guides through the complete Vorta release process - version bump, translations, git tag, GitHub release, PyPi, and macOS builds.
Pytest 会话测试
Best practices for writing and organizing tests with pytest including fixtures, parametrize, and plugins.
Bisect 代码验证
Git bisect to find the first bad commit by running a test command.
gfix 代码创建
Amend a git commit further back in the history.
Rebase 代码验证
Interactive rebase onto a base branch, resolving conflicts along the way and verifying tests pass.
java 后端
用于 Java 后端面试出题；优先围绕 Java 核心、MySQL、Redis、Spring 与项目实战，追问设计取舍、故障处理和性能优化。
技能 Evolution
Use before creating, editing, or deciding whether to update any AI coding agent skill in this repository, including corrections to existing skill behavior, references, or routing.
ctf 浏览器测试
Provides web exploitation techniques for CTF challenges.
Agent 生成器
'Create production-grade agent .md files aligned with the Anthropic 2026 Creates spec-compliant agent .md files following the Anthropic 2026 16-field schema.
Agent 会话验证
Automates Apple-platform apps (iOS, tvOS, macOS) and Android devices.
Patent 上下文验证
通用中国专利挖掘发现与交底书生成全流程：扫描项目文档挖掘专利点、讨论融合、基于脱敏模版生成技术交底书、联网查新、生成后自检含逻辑闭环与公式参数一致性。
html 代码优化
HTML原型转Unity UGUI界面生成管线。
Agent 生成器
Meta-skill for creating new Claude Code skills with configurable execution modes.
Leetcode 技能验证
Find and set up coding practice problems tailored to your weak areas, then create local files so you can solve them right away.
技能 Listing Polis
Improve a skill's public listing before publish.
review
코드 리뷰 — 버그, 로직 오류, dead code 검출 Review the specified file(s) or current git diff for bugs, logic errors, and dead code.
Skillshare 技能验证
>- Run isolated E2E tests in devcontainer.
Skillshare 技能测试
>- Implement a feature following TDD workflow.
技能 Judge
Evaluate Agent Skill design quality against official specifications and best practices.
Xiaohongshu 运维
小红书相关操作，覆盖账号定位、选题研究、内容生产、发布执行与复盘修复的小红书全链路运营技能。
Android 代码 审查
> /android-code-review # Review diff between current branch and develop /android-code-review --branch feature/login # Review a specific bran…
技能 优化
Optimizes AI skills for activation, clarity, and cross-model reliability.
diagnose
Use when a test fails and you need to diagnose the root cause.
提交
Create a git commit.
代码审查
代码审查和质量分析技能。
GitHub 助手
Create skills by learning from high-quality GitHub projects When users want to accomplish something, search GitHub for quality projects that solve the problem, understand them deeply, then create a skill based on that knowledge.
Seedance 代码分析
专业的Seedance 2.0平台AI视频脚本和分镜生成器。
发布
Prepare a psd-tools release: update changelog, open release PR.
Slack 助手
Emulated Slack API for local development and testing.
提交
Commit changes in the oasdiff repo, running required pre-commit steps first NEVER push directly to main.
技能 Updater
Update existing skills based on feedback.
技能 编写
Design, improve, and evaluate reusable agent skills with high-quality SKILL.md files, precise trigger descriptions, progressive disclosure, and testable behavior.
技能 代码 风格 Contrib
How to contribute to the Trezor Suite code style guide, including issue proposals and pull request workflows.
技能 Doctor
Use when a repo skill fails, produces errors, gives wrong instructions, or references stale information.
Shipit PR测试
Branch, commit the code, push it, and make a PR When the code is done and is not building on existing commits:
Playwright 技能
浏览器自动化执行工具。
Agent 生成器
Scaffold a new ClawBio skill from a spec file (JSON/YAML) or interactively — generates SKILL.md, Python skeleton, tests, and updates catalog…
提交
Create git commits with user approval You are tasked with creating git commits for the changes made during this session.
Agent 生成器
cp -r knowledge/skills/.template knowledge/skills/your-skill-id vim knowledge/skills/your-skill-id/SKILL.md bash scripts/validate-skill.sh y…
技能 Evolution
Track and improve skill effectiveness over time using VOYAGER-style skill library patterns.
ssr 技能测试
Use this skill when working with Spartacus Server-Side Rendering (SSR).
超级能力 Brainstorm
Produces a structured brainstorm: goals, constraints, risks, options, recommendation, and acceptance criteria.
超级能力 调试
Systematic debugging: reproduce, isolate, form hypotheses, instrument, fix, and add regression tests.
超级能力 规划
Writes an implementation plan with small steps, exact files to touch, and verification commands.
超级能力 tdd
Applies tests-first discipline (red/green/refactor) and adds regression tests for bugs.
超级能力 工作流
Enforces a disciplined workflow for coding, debugging, refactoring, and automation: brainstorm -> plan -> implement with verification (prefer TDD) -> review -> finish.
技能 测试
Test skill for SDK skill integration.
Quality 技能审查
Comprehensive testing and validation strategies for spec-driven development.
Front end 测试
Behavior-driven UI testing patterns.
Go 测试
Go 测试模式，包括表格驱动测试、子测试、基准测试、模糊测试和测试覆盖率。
Charls 代码助手
> | 全称 | China Health and Retirement Longitudinal Study (中国健康与养老追踪调查) | | 官网 | https://charls.pku.edu.cn/ | | 覆盖 | 全国 150 县级单位、450 社区，45 岁以上…
Plugin 构建
Complete plugin development workflow: build, test, icon, troubleshoot, and setup.
Patent 技能创建
You are Patent Architect, a senior patent engineer specializing in AI systems, XR devices, and software-hardware co-design.
cnki 进阶 搜索
Perform a filtered search on CNKI using the old-style advanced search interface (only interface with source category checkboxes).
tpp 代码验证
Work on a Technical Project Plan.
pr PR排查
Commit all changes, push to a new branch, and create a pull request using the repo's PR template.
Stm32 hal 开发
Develop STM32 firmware on CubeMX-generated HAL projects, including peripheral configuration, BSP driver structure, interrupt-safe code, and hardware-aware troubleshooting.
AI 视频 Generation
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI.
技能 基准测试
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.
技能 Curator
Autonomous skill lifecycle manager.
技能 Evolution
Self-evolving skill system.
home Assistant 最
> Follow this sequence when creating any automation: If your change affects entity IDs or cross-component references — renaming entities, re…
Facebook 上下文创建
Create Facebook and Meta ad campaigns, write ad copy, define audiences, and plan budgets.
技能 epi Implement
Implementation skill for R-based epidemiology analysis.
技能 Epidemiology
Implementation skill for R-based epidemiology analysis Routes epidemiology implementation tasks to epidemiology-implementation-agent.
技能 fix it
Scan codebase for FIX:/NOTE:/TODO:/QUESTION: tags and create structured tasks with interactive selection.
Agent 生成器
Execute founder plans and generate strategy reports Routes founder-specific implementation requests to the founder-implement-agent, executing plans created by skill-founder-plan and generating detailed strategy reports.
技能 Funds
Funding landscape analysis with funder portfolio mapping.
技能 Git 工作流
Create scoped git commits for task operations.
技能 Grant
Grant proposal research and drafting with funder analysis.
技能 Implementer
Execute general implementation tasks following a plan.
技能 lake 修复
Run Lean build with automatic error repair for missing cases, unused variables, and unused imports Direct execution skill for automated Lean build repair.
技能 lean 实现
Implement Lean 4 proofs and definitions using lean-lsp tools.
技能 lean 研究
Research Lean 4 and Mathlib for theorem proving tasks.
技能 Learn
Scan codebase for FIX:/NOTE:/TODO:/QUESTION: tags and create structured tasks with interactive selection.
技能 Legal
Contract review and legal analysis for founders Thin wrapper that routes contract review requests to the legal-council-agent.
Agent 生成器
Interactive system builder.
技能 Neovim 实现
Implement Neovim configuration changes from plans.
技能 nix 实现
Implement Nix configuration changes from plans.
技能 Orchestrate
Autonomous state machine that drives a task through its full lifecycle (research -> plan -> implement -> complete) without user confirmation between phases.
技能 Orchestrator
Route commands to appropriate workflows based on task type and status.
技能 规划
Create phased implementation plans from research findings.
Agent 生成器
Project research with scope analysis and timeline estimation Thin wrapper that routes project research requests to the project-agent.
技能 项目 Overview
Interactive repository analysis and project-overview.md generation via task creation.
技能 Python 实现
Implement Python code.
技能 Refresh
Manage OpenCode resources - terminate orphaned processes and clean up ~/.opencode/ directory Direct execution skill for managing OpenCode resources.
技能 Slide 规划
Interactive slide planning with narrative arc review and per-slide feedback.
技能 Timeline
Research timeline planning for medical research projects.
技能 Web 实现
Implement web (Astro/Tailwind/TypeScript) changes following a plan.
技能 z3 实现
Implement Z3 constraints.
质量测试 测试 Executio
测试执行方法，包含测试框架检测、测试运行、结果解析 | 语言 | 单元测试 | E2E测试 | |------|----------|---------| | Node.js | npm test | npx playwright test | | Python | pytest…
技能 Evals
Validate skill outputs against assertions, diff vs prior eval to flag regressions, file issues for new failures, and queue concrete fixes <!…
Bio 图像 Processin
| Best practices and workflows for biological image analysis tasks including cell segmentation, image restoration, and spatial data processing.
nf 技能测试
| nf-core is a community-driven collection of **143+ curated Nextflow pipelines** for bioinformatics.
Open ST 技能 索引
| Open-ST is an open-source spatial transcriptomics method that captures transcriptome-wide expression at sub-cellular resolution using sequencing-based spatial barcoding on Illumina flow cells.
Presentation 技能
| Tools and workflows for creating presentations and visual documentation.
SC 最佳 实践 技能 索引
| Best practices and workflows for single-cell and spatial omics data analysis, based on the Single-cell Best Practices book.
Upstream 技能规划
| Skills and workflows for upstream data processing steps that precede standard single-cell analysis (QC, normalization, clustering, etc.).
Rspack 技能排查
Provides comprehensive guidance for Rspack bundler including configuration, plugins, loaders, optimization, and Webpack compatibility.
技能 name
<One sentence describing what knowledge this skill provides.> <!-- One sentence: what does this skill help Copilot do?
技能 eval
Evaluate skills: trigger testing, A/B benchmarks, structure validation, head-to-head bake-offs.
技能 Lawvable 优化
Guide to analyze a current work session and propose improvements to skills.
Agent 生成器
Scaffold a new SKILL.md.
Agent 生成器
Build the WooCommerce iOS project Run the build command: bundle exec fastlane buildfortesting 2>&1 | tail -50 If the build fails: If the build succeeds, report success.
调试
Debug a failing test or build error in WooCommerce iOS Debug a build failure or test failure in the WooCommerce iOS project.
pr PR审查
Create a pull request following WooCommerce iOS conventions git branch --show-current git log trunk..HEAD --oneline git diff trunk...HEAD --stat
审查
Review code changes against WooCommerce iOS standards Review the current changes for compliance with WooCommerce iOS conventions.
验证
Build the app, launch on simulator, and verify feature behavior via mobile-mcp interaction.
技能 构建
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization.
技能 Stats
Use when reviewing which QE skills are being used, finding undertriggering skills, or analyzing skill effectiveness.
Web 测试
Тестирование 1С через веб-клиент — автоматизация действий в браузере.
Agent 生成器
Create or improve skill.
Compiling 代码排查
Compile and build the SkyWalking BanyanDB project.
Blinding 技能查找
Implement blinding procedures to reduce bias in experimental studies.
dr 技能规划
Alias skill that invokes /dry-run with all arguments passed through.
gpt 会话创建
Use GPT-5.2 for long-running coding tasks: large refactors, feature implementation etc.
tdd 技能测试
RED-GREEN-REFACTOR 워크플로우를 강제하는 TDD 개발 스킬 이 스킬은 ForkLore 프로젝트에서 TDD(Test-Driven Development) 워크플로우를 강제합니다.
技能 审计
Audit AI Agent skills for security vulnerabilities including malicious code, remote execution, credential leaks, and supply chain risks.
Snpeff 会话创建
Run SnpEff, a variant annotation and effect prediction tool for genomic variants.
技能
Use when doing task A.
技能 b
Use when doing task B.
技能 c
Use when doing task C.
技能 Consumer
Use when consuming optimization artifacts.
Agent 生成器
> You produce and maintain a tree of SKILL.md files for a library.
技能 Prune
Identify and remove negative-ROI skill content — orphan files, never-read entries, duplicates, content reintroducing challenge-specific lore…
Agent 生成器
Skill creation, update and management — generates skill directory structure, validates against best practices, enforces line count limits.
技能 编写
Guide creating Claude Code skills with TDD and persuasion principles.
技能 Governance lo
Use when the user asks to review a skill, analyze skill quality, update a skill version, or run a repeatable keep/disable/archive decision loop from real failures instead of abstract best practices.
技能 Judge
Evaluate Agent Skill design quality against official specifications and best practices.
Mckinsey 技能助手
McKinsey顾问式问题解决系统。
技能 Upstream PR
Improve an open-source GitHub skill and open a friendly suggestion PR upstream: fork, run skill-auto-improver, attach asm eval before/after metrics.
需求文档 v05 Technic
Determine technologies needed to build the product, making build/buy/integrate decisions during PRD v0.5 Red Team Review.
Agent 生成器
Neue Skills in der KI-Anwaltskanzlei installieren: Verfuegbarkeitscheck, Abhaengigkeiten, Konfiguration.
技能 Verwalter
Übersicht und Verwaltung aller installierten Skills: Status, Version, Abhaengigkeiten.
技能 Qualitaetspru
Qualitaet installierter Skills prüfen: Normaktualitaet, Description-Qualitaet, Struktur-Compliance.
技能 vote 本地
Use when retrieving the most relevant skills from a local or private skill library instead of relying on network-based skill discovery.
技能 Router
Help users discover available skills and help Claudia pick the right one when a request is ambiguous.
技能 管理器
管理 Claude Code、Codex 和 OpenClaw Skills 的安装、版本追踪和更新检查。
api 代码测试
API 自动化测试 - OpenAPI 解析、测试用例生成、集成测试 当用户要求测试 API、生成测试用例、接口测试、集成测试时激活此技能。
技能 同步
Sync skills between local installation and the GitHub source-of-truth repository.
ui 上下文规划
UI原型工场。
技能 Reinforcement
Always and Automatically improve skills after each use by capturing learnings and anti-patterns After ANY skill is used, this meta-skill triggers to: After using a skill, note: Ask these questions: | Category | Where to Add | Example | | ----------------- | -------------------------- | ---------------------------- | makes outbound network calls.
Agent 生成器
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization.
技能 开发
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.
技能
Skill management - create, validate, and improve Claude Code skills START(["/skills"]) --> NEED{"What do you need?"} NEED -->|New skill| WORKTREE["git:worktree"]:::git NEED -->|Edit skill| WORKTREE NEED -->|Audit all| SCAN["skills:scan"]:::skills NEED -->|Session review| RETRO["skills:retrospective"]:::skills makes outbound network calls.
技能 Retrospective
End-of-session review to identify improvements, skill gaps, and refactoring opportunities START(["/skills:retrospective"]) --> P1["Phase 1:…
技能 验证
Validate skill files meet the standard format and naming conventions Skills operate on either sandbox (safe) or management (requires approval) targets: | Type | Target | Auto-approve?
技能 写作
Create or edit skills with proper structure, task tracking, and naming conventions Create new skills or edit existing ones.
Skillhub 指南
Use when the user wants to discover, install, or use Tencent Skillhub from NextClaw, especially for CLI-only install, readiness checks, and safe skill installation guidance.
技能 Tester
| Design tests, run them, grade results, evaluate description triggering, produce actionable report.
Dropshipping 产品
Product research for dropshipping businesses.
Agent 生成器
| harness 오픈소스의 6-Phase 스킬 생성 워크플로우를 MoAI cowork-plugins 컨텍스트에 맞게 변환한 스킬입니다.
技能 Tester
| skill-builder로 생성된 스킬 또는 기존 스킬의 품질을 검증합니다.
技能 安全 审计
Audit the agent's own skill library for malicious, misconfigured, or untrusted SKILL.md files.
文章 PR 审查
Post a `lifinance/contracts` pull request to `#dev-sc-review` and enable auto-merge (squash).
skill-reviewer
Review skill PRs with structured severity-rated feedback covering token budgets, routing conflicts, required sections, and repo conventions.
技能 Installer
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path.
Skillshare 技能验证
>- Run isolated E2E tests in devcontainer.
Skillshare 技能测试
>- Implement a feature following TDD workflow.
技能
Multi-stage rebuttal analysis skill for RebuttalStudio.
Skilless.ai 头脑风暴
Help turn ideas into fully formed plans through collaborative dialogue.
ring 测试 技能 Subag
| Run scenarios without the skill (RED — watch agent fail), write skill addressing those failures (GREEN), then close loopholes (REFACTOR).
Produce 代码创建
短剧制作技能。
技能 Sonar
Lifecycle guard.
Literature 审查 写作
> 为用户提供的研究选题撰写符合顶级期刊标准的文献综述（Literature Review）部分。
技能 Tester
> The agent validates skill packages for structure compliance, tests Python scripts for syntax and stdlib-only imports, and scores quality across four dimensions (documentation, code quality, completeness, usability) with letter grades and improvement recommendations.
技能 Evolution
Tracks skill usage patterns, edit frequency, and success rates to suggest improvements and optimizations.
web 代码排查
面向 Web/JS 逆向中的纯算、验证码纯算、复杂 header/cookie 签名、混合加密、JSVMP/VMP、Wasm、PoW、响应解密、指纹与 challenge 参数还原工作流。
IDA 技能
IDA Pro 逆向分析。
Website 配置 构建
Install the full AI website builder stack — UI/UX Pro Max, Framer Motion animations, and 21st.dev components.
Defect 技能创建
AI-powered construction defect detection using computer vision.
JMeter Load 测试
Load and performance testing skill using Apache JMeter, covering test plans, thread groups, assertions, listeners, timers, and distributed testing.
Agent 生成器
Takes the active conversation as reference to understand how a skill can be created, with all the lessons learned from the users need in the conversation.
更新 deps
Audit all outdated dependencies with detailed research on changelogs, breaking changes, bug fixes, and deprecations.
gh PR审查
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments.
Roblox 开发
World-class Roblox game development - Lua scripting, Roblox Studio, game systems, monetization, and building experiences that millions play.
Protenix 技能验证
Protenix v1 is an AF3-class structure prediction model (368M parameters) for proteins, complexes, and protein-ligand systems.
idea 头脑风暴
學術研究的 Idea 產生技能——從發散到收斂，系統化地產出高品質研究構想。
Comsol 技能创建
Invoke when: User needs help with COMSOL multiphysics coupling, parametric sweeps, or physics-based simulations.
Testcase 写作 plus
解析需求文档和需求分析结果，生成高质量测试用例。
Testcase 写作 plus
Parse requirement and analysis files, then generate high-quality test cases.
proj req 分析
需求分析与确认（阶段一）。
提示词 Engineering
Universal prompt engineering techniques for any LLM.
pr PR创建
worktreeでの開発完了後、PR作成と同時にworktreeを自動的にクリーンアップします。
Plutonium 上下文创建
Use BEFORE building or customizing any Plutonium UI — page classes, forms, displays, tables, custom Phlex components, layouts, Stimulus cont…
分支 Management
通用分支与特性目录管理Skill.
文档审计
Orchestrate sequential documentation audits with checkpointing and resumption.
产品 Owner
Product interrogator.
Malware 分析
You are a malware analysis expert and you are able to understand malware for any kind of platform including, Windows, MacOS, Linux or android.
浏览器
Control a Chrome session via Stagehand to browse, act, extract, and screenshot on demand inside the Factory CLI.
上下文 会话 end
Context Session End 作業の自然な区切りをAIが自律的に検知し、currentfocus.md への追記を提案する行動規範。
dig 上下文排查
Investigation-only mode for understanding bugs, features, or system behavior without making changes.
Fullstack 技能审查
Load PROACTIVELY when task involves building a complete feature across multiple layers.
qmd 文档创建
Fast local search for markdown files, notes, and docs using qmd CLI.
sdd 方案验证
Specification-driven development methodology coach.
teya 技能测试
Teya payment integration guide covering POSLink (cloud-based terminal integration), All-In-One (single-device Android), E-Commerce APIs (hosted checkout, payment links), and Payments Gateway.
Trace 会话创建
Trace design decisions and concepts through session history, handoffs, and git.
Business 规划 Advi
Expert business planning consultant for creating comprehensive, investor-ready business plans from scratch or refining existing plans.
Nextjs 初始化
Scaffold a Next.js project with App Router, TypeScript, Tailwind CSS, and opinionated defaults.
需求文档
Write a product requirements document from context.
spec
Write a technical specification or acceptance criteria from a PRD or user stories.
10x 浏览器审查
Chat with web AI agents (ChatGPT, Gemini, Claude, Grok, Perplexity, NotebookLM) via browser automation.
erne 代码
ERNE — Implement features using the senior-developer agent You are executing the /erne-code command.
erne 调试
ERNE — Systematic diagnosis of bugs using the performance-profiler agent You are executing the /erne-debug command.
erne PR审查
ERNE — Autonomous ticket execution — polls a provider, picks up ready tickets, and runs the full ERNE pipeline (validate, plan, code, test,…
会话交接
Prepare a clean handoff for continuing complex work in a fresh Claude Code session.
Afsim Script 生成
Generate and execute AFSIM (Advanced Framework for Simulation, Integration and Modeling) scripts.
mlx 技能审查
Use when working with Apple's MLX or MLX-LM: fact-checking current behavior against upstream source/runtime, patching MLX-based repos, porting PyTorch/JAX code to MLX, validating lazy evaluation, indexing, compilation, streams, channels-last layouts, Metal kernels, quantization, caches, and local MLX model loading or generation on Apple silicon.
handoff
Capture current work context for handoff to another agent/developer.
Hinge Profile 优化
Comprehensive, research-backed Hinge dating profile optimization.
Verekia 架构
Day-to-day coding style and patterns for R3F game development with Miniplex ECS.
Asicrs 构建
Use when editing files under `plugin/asicrs/`, `sdk/rust/`, or `server/sdk/v1/pb/` (which the asicrs build also consumes).
Memories 上下文排查
Build against the memories.sh SDK packages in application code.
Sales 上下文审查
Talkdesk platform help — cloud contact center (CCaaS) with AI virtual agents, omnichannel routing, workforce management, and quality managem…
Markdown 优化
When the user wants to optimize markdown strategy, price optimization for clearance, or minimize inventory markdowns.
Vcsdd Git 集成
Use this skill when committing VCSDD pipeline artifacts to git.
Git 自动化
Advanced Git operations automation including intelligent branching, commit optimization, release workflows, and repository health management…
Obsidian 助手
整理 Obsidian 知识库，并通过 CLI 读写、搜索笔记或调试插件与主题。
ttal PR审查
How agents use ttal comment for review workflows - plan reviews, PR reviews, triage reports, and verdicts.
Metabase 代码创建
Implements JWT SSO authentication for Metabase embedding in a project.
Metabase full 应用
Migrates a project from Metabase Full App / Interactive (iframe-based) embedding to Modular (web-component-based) embedding.
Metabase 代码审计
Upgrades a project's Metabase Modular embedding SDK (@metabase/embedding-sdk-react) or Modular embedding (embed.js) version.
add 技能验证
Use when adding global mode support for one existing agentsmesh target from a target-structure/global-path doc.
am Agent 代码 重构
Improve code structure, performance, and maintainability through systematic refactoring.
Guided 学习 cn
中文引导式学习助手。
后端 Nestjs
NestJS backend development patterns.
vp 头脑风暴
Brainstorm session to collect ideas and decisions for the project Output this banner as the first thing on every invocation — before questio…
vp 调试
Systematic debugging with persistent state tracking across sessions Use when available; do not block debug flow if missing.
vp 技能验证
Display ViePilot version, npm latest, skills/workflows list via vp-tools Output this banner as the first thing on every invocation — before…
vp 上下文验证
Pause work with context preservation to resume later Output this banner as the first thing on every invocation — before questions, work, or…
vp 简历
Resume work from previous session with full context restoration Output this banner as the first thing on every invocation — before questions…
vp 代码验证
Rollback to any checkpoint safely with state preservation Output this banner as the first thing on every invocation — before questions, work…
vp 代码验证
Display progress dashboard and actionable insights Output this banner as the first thing on every invocation — before questions, work, or an…
Accept 代码验证
Validate business behavior against BDD examples from the end user's perspective Available knowledge: [[requirements/gherkin#key-takeaways]], [[software-craft/test-design#key-takeaways]], [[software-craft/test-stubs#concepts]].
root Cause 分析
Investigate why the PR was rejected, identifying the failure point and missed gate Available knowledge: [[requirements/post-mortem#key-takeaways]].
new 项目
Scaffold a new Camunda 8 project with the right structure, dependencies, and docs.
gmsh 方案创建
The GMSH Agent is a specialized AI module for finite element mesh generation and manipulation.
Testcase 生成
测试用例生成器 - 基于等价类划分和边界值分析理论,按测试点(POINT)分批生成高质量测试用例,输出为 Markdown 格式。
Align 会话审查
Interview the user about their goal before any plan or code.
Codex 助手
Use this skill when the user asks for persistent multi-agent coding workflows with task dependencies, per-task codex sessions, git worktree isolation, and explicit merge flow backed by one JSON workflow file under ./.codex-deck/.
qt 前端优化
Use when encountering compilation errors, runtime crashes, memory leaks, UI issues, or threading problems in Qt C++ projects.
Slack 助手
Access a personal Slack workspace via session tokens (no app install required).
Agent 浏览器
Automates browser interactions for web testing, form filling, screenshots, and data extraction.
Autoresearch 会话审
Finalize an autoresearch session into clean, reviewable branches.
fft Dashboard 运维
Build and apply Home Assistant Lovelace dashboards from templates using a staged workflow with screenshot verification and context-reactive themes.
pr PR创建
Generates a structured PR summary for the current branch by inspecting commits and file changes since master.
配置 Structure 索引
This skill should be used when the user asks to "set up structure index", "add codebase structure tracking", "create structure files", "set up code structure YAML", or needs to set up the codebase structure index system in a project.
api 上下文审查
Check whether code changes silently broke API contracts, behavior, schemas, or compatibility expectations.
bag 上下文排查
Check rosbag or recorded data replay issues involving topic names, clocks, remaps, timing, and consumer mismatch.
bom cost 优化
Propose lower-cost bill-of-material substitutions while preserving critical requirements, interfaces, and risk constraints.
bug 代码排查
Reproduce reported bugs, isolate failure conditions, inspect recent changes, test root-cause hypotheses, and propose the smallest safe fix plan.
cost Hotspot 查找
Identify cloud and platform spend hotspots, waste, and likely optimization wins.
Customer 项目排查
Classify support requests, ask the right follow-up questions, choose the correct troubleshooting path, and draft responses in the desired support tone.
Dashboard spec 写
Define exactly what a product or ops dashboard should show, including metrics, dimensions, filters, and failure modes.
文档 代码
Turn implementation details into practical documentation such as README updates, setup guides, architecture notes, runbooks, changelogs, and internal reference docs.
Embedded 日志 Deco
Interpret firmware and embedded-system logs to narrow likely subsystem faults and next probes.
Agent 生成器
Write reproducible procedures, controls, materials lists, and validation steps for experiments.
Front 上下文排查
Trace confusing client-side state bugs involving async effects, caches, stores, routing, forms, or rendering order.
Grant 代码优化
Organize grant proposal sections, milestones, evaluation plans, and impact framing into a coherent application package.
Knowledge 上下文验证
Identify what documentation is missing by comparing support issues, product behavior, and existing docs.
Literature 审查 Ma
Map papers by topic, method, findings, gaps, and trends.
Agent 生成器
Turn goals, stakeholders, and open decisions into a tight meeting agenda with required outcomes.
移动端 发布 检查
Validate mobile release readiness by checking build artifacts, versioning, store requirements, crash risk, config, and pre-ship blockers.
Observability 配置
Add or improve logging, metrics, tracing, dashboards, and alert-ready instrumentation structure.
Osint 技能查找
Use this skill whenever a user asks for OSINT dorks, Google dorks, GHDB queries, Shodan filters, GitHub code search dorks, search operators, or exposed asset discovery.
peer 审查 Response
Draft point-by-point responses to reviewer comments using manuscript changes, evidence, and rebuttal structure.
性能 Profiler
Identify hot paths, bottlenecks, and likely performance wins from profiles, traces, benchmarks, and code hotspots.
研究
Use when a user asks to research something with ResearchBuddy, run web research or deep research, produce a source-backed answer, follow up on a saved research session, or install, validate, and troubleshoot the Homebrew-installed researchbuddy CLI.
self 技能审查
Captures learnings, errors, and corrections to enable continuous improvement.
Weekly 报告
周报/日报/月报生成助手。
ab 测试
>- Use when this capability is needed.
Abizer 代码 审查
> Three questions, in order, before writing any comment: offers none, flag it.
acpx 审查
Use before DaoFlow commits when running self-review through acpx with Gemini and Claude Code, triaging blocking findings, and revalidating fixes.
Address 审查
Pull unresolved PR review comments and address them.
Agent 上下文审查
Audit and score an agent-definition markdown such as `AGENTS.md`, `CLAUDE.md`, `SKILL.md`, `SOUL.md`, `.cursorrules`, or a system prompt using a cold-reader rubric for clarity, consistency, context independence, and operating-model fit.
Agent 生成器
Guide humans through creating effective instruction rules for coding agents (Copilot, Claude Code, Cursor, Windsurf, Aider, AGENTS.md, CLAUDE.md, .cursorrules, copilot-instructions.md).
AI Agent 实现 工作流
Implement agentic behaviors safely with clear tool boundaries, deterministic contracts, and incremental verification across prompts, tools, and orchestration code.
ai 会话排查
>- Use when this capability is needed.
ai 代码测试
Write a professional Software Design Document (SDD) for an AI agent or AI-powered product before writing code.
AI 上下文 Compiler
Generate or refresh CLAUDE.md, AGENTS.md, Cursor rules, and llms.txt for a repository using source evidence and scoped rules.
Aider 代码创建
Terminal pair programming with Aider, the AI pair programmer that edits Use when this capability is needed.
Aidex 技能审计
Swap tokens on Ethereum via the AIDEX aggregator.
akka-net-testing-patterns
Write unit and integration tests for Akka.NET actors using modern Akka.Hosting.TestKit patterns.
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration.
Ansoff 代码规划
시장 침투, 시장 개발, 제품 개발, 다각화 전략을 매핑하는 Ansoff Matrix 분석을 생성합니다.
Apple Script 自动化
Comprehensive AppleScript expertise for enterprise-grade macOS automation including multi-display management, URL scheme handling, deep link…
Applescript 自动化
Comprehensive AppleScript expertise for enterprise-grade macOS Use when the user request matches this skill's domain and capabilities.
arn Infra 初始化
>- Use when this capability is needed.
MCP 助手
Use Ask GraphQL MCP to handle Web3 and on-chain questions through GraphQL endpoints (especially SubQuery/SubGraph).
ask-matt
Ask which skill or flow fits your situation.
aspire-integration-testing
Write integration tests using .NET Aspire's testing facilities with xUnit.
Atomic 提交
Atomic git workflow - validates, commits, pushes, creates PR, and verifies CI with zero-warnings policy.
Atrium 技能创建
Bootstrap a new host application on top of the published atrium base image, or retrofit an existing FastAPI / SQLAlchemy / React app onto atrium.
audit-context-building
Understand a codebase before looking for bugs in it - what each function assumes, what it guarantees, and what it depends on elsewhere.
audit-prep-assistant
Prepares codebases for security review using Trail of Bits' checklist.
autoplan
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using…
axiom-accessibility
Use when fixing or auditing ANY accessibility issue — VoiceOver, Dynamic Type, color contrast, touch targets, WCAG compliance, App Store acc…
axiom-accessibility
Use when fixing or auditing ANY accessibility issue — VoiceOver, Dynamic Type, color contrast, touch targets, WCAG compliance, App Store acc…
axiom-accessibility
Use when fixing or auditing ANY accessibility issue — VoiceOver, Dynamic Type, color contrast, touch targets, WCAG compliance, App Store acc…
axiom-analyze-swift-performance
Use when the user mentions Swift performance audit, code optimization, or performance review.
axiom-apple-docs
Use when ANY question involves Apple framework APIs, Swift compiler errors, or Xcode-bundled documentation.
axiom-apple-docs
Use when ANY question involves Apple framework APIs, Swift compiler errors, or Xcode-bundled documentation.
axiom-apple-docs
Use when ANY question involves Apple framework APIs, Swift compiler errors, or Xcode-bundled documentation.
axiom-audit-accessibility
Use when the user mentions accessibility checking, App Store submission, code review, or WCAG compliance.
axiom-audit-codable
Use when the user mentions Codable review, JSON encoding/decoding issues, data serialization audit, or modernizing legacy code.
axiom-audit-concurrency
Use when the user mentions concurrency checking, Swift 6 compliance, data race prevention, or async code review.
axiom-audit-core-data
Use when the user mentions Core Data review, schema migration, production crashes, or data safety checking.
axiom-audit-database-schema
Use when the user mentions database schema review, migration safety, GRDB migration audit, or SQLite schema checking.
axiom-audit-foundation-models
Use when the user mentions Foundation Models review, on-device AI audit, LanguageModelSession issues, @Generable checking, or Apple Intelligence integration review.
axiom-audit-grdb-performance
Use when the user mentions GRDB performance review, slow GRDB queries, app-group database setup audit, a ValueObservation that stopped updating, or pre-release GRDB scan.
axiom-audit-iap
Use when the user mentions in-app purchase review, IAP audit, StoreKit issues, purchase bugs, transaction problems, or subscription management.
axiom-audit-liquid-glass
Use when the user mentions Liquid Glass review, iOS 26 UI updates, toolbar improvements, or visual effect migration.
axiom-audit-memory
Use when the user mentions memory leak prevention, code review for memory issues, or proactive leak checking.
axiom-audit-networking
Use when the user mentions networking review, deprecated APIs, connection issues, or App Store submission prep.
axiom-audit-swiftdata
Use when the user mentions SwiftData review, @Model issues, SwiftData migration safety, or SwiftData performance checking.
axiom-audit-swiftui-architecture
Use when the user mentions SwiftUI architecture review, separation of concerns, testability issues, or "logic in view" problems.
axiom-audit-swiftui-layout
Use when the user mentions SwiftUI layout review, adaptive layout issues, GeometryReader problems, or multi-device layout checking.
axiom-audit-swiftui-nav
Use when the user mentions SwiftUI navigation issues, deep linking problems, state restoration bugs, or navigation architecture review.
axiom-audit-testing
Use when the user wants to audit test quality, find flaky test patterns, speed up test execution, or prepare for Swift Testing migration.
axiom-audit-textkit
Use when the user mentions TextKit review, text layout issues, Writing Tools integration, or UITextView/NSTextView code review.
axiom-build
Use when ANY iOS build fails, test crashes, Xcode misbehaves, or environment issue occurs before debugging code.
axiom-build
Use when ANY iOS build fails, test crashes, Xcode misbehaves, or environment issue occurs before debugging code.
axiom-build
Use when ANY iOS build fails, test crashes, Xcode misbehaves, or environment issue occurs before debugging code.
axiom-debug-tests
Use this agent for closed-loop test debugging - automatically analyzes test failures, suggests fixes, and re-runs tests until passing.
axiom-fix-build
Use when the user mentions Xcode build failures, build errors, or environment issues.
axiom-implement-iap
Use when the user wants to add in-app purchases, implement StoreKit 2, or set up subscriptions.
axiom-optimize-build
Use when the user mentions slow builds, build performance, or build time optimization.
axiom-payments
Use when accepting ANY real-world payment — Apple Pay, Wallet passes, Tap to Pay, Orders in Wallet.
axiom-payments
Use when accepting ANY real-world payment — Apple Pay, Wallet passes, Tap to Pay, Orders in Wallet.
axiom-payments
Use when accepting ANY real-world payment — Apple Pay, Wallet passes, Tap to Pay, Orders in Wallet.
axiom-run-tests
Use when the user wants to run XCUITests, parse test results, view test failures, or export test attachments.
axiom-scan-security-privacy
Use when the user mentions security review, App Store submission prep, Privacy Manifest requirements, hardcoded credentials, or sensitive data storage.
axiom-swift
Use when reviewing Swift code for modern idioms, working with noncopyable types, implementing drag and drop, adding debug deep links, or building for tvOS.
axiom-swift
Use when reviewing Swift code for modern idioms, working with noncopyable types, implementing drag and drop, adding debug deep links, or building for tvOS.
axiom-swift
Use when reviewing Swift code for modern idioms, working with noncopyable types, implementing drag and drop, adding debug deep links, or building for tvOS.
axiom-swift-simplifier
Use when the user wants to simplify Swift code, reduce boilerplate, or make Swift more readable and idiomatic without changing behavior.
axiom-test-simulator
Use when the user mentions simulator testing, visual verification, push notification testing, location simulation, screenshot capture, OR live accessibility validation (VoiceOver announcements, Dynamic Type, ADA checks) on the simulator.
axiom-testing
Use when writing ANY test, debugging flaky tests, making tests faster, or choosing Swift Testing vs XCTest.
axiom-testing
Use when writing ANY test, debugging flaky tests, making tests faster, or choosing Swift Testing vs XCTest.
axiom-testing
Use when writing ANY test, debugging flaky tests, making tests faster, or choosing Swift Testing vs XCTest.
axiom-validate-screenshots
Use when the user mentions App Store screenshot validation, screenshot review, checking screenshots before submission, or verifying screenshot dimensions and content.
后端 Fundamentals
Auto-invoke when reviewing API routes, server logic, Express/Node.js code, or backend architecture.
Bootstrap 项目
Use when creating a new project repository to initialize it with standard CLAUDE.md, .cursorrules, CLAUDE.local.md, SESSION_LOG.md, and gitignore entries Initialize a new project with the standard file structure for Claude Code and Cursor development.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.
Bunny 技能编写
Direct GraphQL API integration with Bunny — the subscription billing and management platform.
c-review
Performs comprehensive C/C++ security review for memory corruption, integer overflows, race conditions, and platform-specific vulnerabilities.
claude-code-hooks
>- Claude Code fires hooks at tool-call boundaries.
claude-skills-troubleshooting
Diagnose and resolve Claude Code plugin and skill issues.
claude-switch-models-setup
>- This skill creates an isolated-but-shared profile system for Claude Code CLI.
cli-demo-generator
Generates professional animated CLI demos as GIFs using VHS terminal recordings.
CLI 设计
Unix-composable CLI design patterns.
code-improver
Runs an autonomous review-and-fix improvement loop over any code target — a skill, plugin, module, or directory — using a reviewer the user…
代码 重构
Refatorar código, refactoring, modernizar código legado, melhorar qualidade, atualizar padrões, converter componente Angular para standalone…
code-review
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?).
代码审查
Review code changes, diffs, commits, branches, or PRs for correctness, regressions, security-sensitive mistakes, maintainability issues, and missing validation before commit, PR, merge, or closeout.
代码 审查 前端
Use when: "review this PR", "code review", "check my diff", "/review" name: code-review-frontend Multi-agent PR review orchestrator.
代码 审查
> Use when this capability is needed.
codebase-design
Shared vocabulary for designing deep modules.
提交
Automate git commit and push following the project's review workflow.
Community 技能创建
> Use when this capability is needed.
Concise 会话创建
Toggle concise mode auto-activation globally.
Contentful 模型审查
Comprehensive Contentful REST API guide.
Copilot 代码测试
Technology-agnostic blueprint generator for creating comprehensive copilot-instructions.md files that guide GitHub Copilot to produce code consistent with project standards, architecture patterns, and exact technology versions by analyzing existing codebase patterns and avoiding assumptions.
PR 创建
Use after implementation is complete — stages, commits, pushes, and opens PRs for all affected services.
Python 项目 创建
Use this skill whenever the user wants to create, scaffold, set up, initialize, or bootstrap a new Python project.
Cursor 规则 配置
| Use when this capability is needed.
Customize 技能验证
Add new capabilities or modify nano-core behavior.
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them…
开发 构建
全栈开发工程师技能包，负责根据产品需求文档和原型图实现功能代码。
developing-ios-apps
Develops iOS/macOS apps with XcodeGen, SwiftUI, and SPM, including Apple Developer signing, notarization, and CI/CD pipelines.
devex-review
Live developer experience audit.
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions.
differential-review
> Security-focused code review for PRs, commits, and diffs.
Django Pytest 性能
>- Use when this capability is needed.
Django 代码测试
Applies Django testing strategies with pytest-django, TDD, factory_boy, mocking, coverage, and DRF test patterns.
文档 adrs
Records decisions and documentation.
文档写作
Diátaxis Documentation Expert with brand voice guidance.
domain-modeling
Build and sharpen a project's domain model.
dotnet-devcert-trust
Diagnose and fix .NET HTTPS dev certificate trust issues on Linux.
dotnet-project-structure
Modern .NET project structure including .slnx solution format, Directory.Build.props, central package management, SourceLink, version management with RELEASE_NOTES.md, and SDK pinning with global.json.
dotnet-slopwatch
Use Slopwatch to detect LLM reward hacking in .NET code changes.
dwarf-expert
Analyzes DWARF debug information in compiled binaries.
Engineering 技能审查
Language-agnostic engineering methodology — DDD, Hexagonal Architecture, TDD, architecture planning, requirements gathering, code review, an…
executing-plans
Use when you have a written implementation plan to execute in a separate session with review checkpoints Load plan, review critically, execute all tasks, report when complete.
Explaining 上下文创建
| Use when this capability is needed.
External PR 审查
One-shot review of an external GitHub PR.
Fastapi 代码审查
Use when adding, renaming, or modifying a FastAPI route in genereviews-link.
Federated 学习 Hom
This skill covers the implementation of privacy-preserving machine learning Use when this capability is needed.
fft Coder 运维
Operate FFT_nano coding delegation flows safely using /coder and /coder-plan, preserving main-chat-only policy, request-id tracking, and non-duplicative streaming behavior.
fft 调试
Diagnose and resolve FFT_nano runtime issues across container execution, provider credentials, Telegram/WhatsApp routing, scheduler behavior, and per-group logs/state.
fft 配置
Verify host prereqs (node, npm, container runtime) before running nano-core.
fft Telegram 运维
Operate FFT_nano Telegram workflows including main chat claiming, command safety boundaries, admin panel usage, media intake behavior, and Telegram-first deployment patterns.
financial-data-collector
Collect real financial data for any US publicly traded company from free public sources (yfinance).
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work Run the project's full test suite (npm test / cargo test / pytest / go test ./...).
flai 会话创建
Install and use FlAI AI chat components in Flutter projects.
Fleet 管理器
Monitors the fleet of concurrent workflows across every registered domain (api/shared/domains.py).
Flutter 代码审查
Flutter/Dart coding rules for this project — style, file size, and test coverage.
Flutter bloc 异步
Implements the canonical async API call pattern in Bloc — dispatch event, emit loading, call Repository returning `Result<T>` with a typed `…
Flutter 技能测试
Use when adding a new feature to a Bloc-based Flutter project (after `flutter-bloc-setup`), structuring an existing feature with a canonical event/state/bloc trio backed by `freezed` sealed states, or deciding which `bloc_concurrency` transformer (`droppable`/`restartable`/`sequential`/`concurrent`) fits an event handler.
Flutter 模型验证
Models form fields as `formz` value objects and drives form state with a Bloc, including round-tripping Laravel 422 validation errors back to per-field UI errors.
Flutter bloc 配置
Configures a Flutter project for Bloc state management with `flutter_bloc`, `freezed`, `bloc_concurrency`, and `hydrated_bloc`.
Flutter API创建
Subscribes to a real-time stream (WebSocket, Pusher, Firestore) inside a Bloc via `emit.forEach` and emits a new state on every frame.
Flutter bloc 测试
Writes deterministic unit tests for Blocs using `bloc_test` and `mocktail`, including tests for `bloc_concurrency` transformers and `HydratedBloc` persistence.
MCP 助手
Run Flutter MCP runtime validation from CLI in two steps (launch app, then run validate-runtime), including toolkit-extension gating, screenshot/layout capture, app error collection, optional reload verification, and retry handling for transient first-connect failures.
fuzzing-obstacles
> Codebases often contain anti-fuzzing patterns that prevent effective coverage.
Gemini 助手
Smart Gemini CLI delegation skill.
Gemini 审查
作業完了後に、Gemini CLI と Code Review 拡張（/code-review, /pr-code-review）でレビューしたいときに使います。
Gemini 助手
Use when working with a skill for managing and maintaining a project-wide `.gemini/GEMINI.md` repository manifest.
Gemini 审查
Use Google Gemini for parallel code reviews, complex task validation, and second opinions.
Git 提交
Write professional git commits using conventional format for clear communication and automated workflows.
git 上下文审查
> Use when this capability is needed.
Git safe PR 工作流
>- Use when this capability is needed.
git-safety-net
>- Prevent losing work in a tangle of branches/stashes/rebases, and recover it forensically when something already went sideways.
Git 工作流
第一步：检测文件变更 ```bash 检查 Git 状态 git status 查看变更文件 git diff --name-only ``` 第二步：添加文件 ```bash 添加所有变更 git add .
github-contributor
A phase-based playbook for shipping pull requests that maintainers actually want to merge.
GitHub 助手
> Use when this capability is needed.
github-review-pr
>- Treat every verdict as a claim about exact immutable Git objects.
github-triage
Triages a repository's open GitHub issues and pull requests via the gh CLI.
GitHub 助手
Use when working in a git repository hosted on GitHub and handling branch creation, commits, pushes, pull requests, reviews, or merges with gh CLI available.
Golang 上下文验证
Use when the project uses Go for systems programming or backend services Check every error.
Golang 上下文测试
Use when working on github.com/adlandh/echo-oapi-middleware/v2, an Echo v5 middleware library that serves OpenAPI YAML and Swagger UI from kin-openapi specs.
Golang 上下文配置
Use when adding or configuring github.com/adlandh/echo-zap-middleware/v2 in a Go Echo service.
Go 学习
This skill helps you learn Go (Golang) one topic per day.
Golang 代码审查
Implements concurrent Go patterns using goroutines and channels, designs and builds microservices with gRPC or REST, optimizes Go application performance with pprof, and enforces idiomatic Go with generics, interfaces, and robust error handling.
Golang 根因排查
Troubleshoot Golang programs systematically - find and fix the root cause.
Grill 上下文创建
Deep interview to reach shared understanding before building.
grill-with-docs
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
gstack-openclaw-ceo-review
Use when asked to review a plan, challenge a proposal, run a CEO review, poke holes in an approach, think bigger about scope, or decide whether to expand or reduce the plan.
gstack-openclaw-investigate
Use when asked to debug, fix a bug, investigate an error, or do root cause analysis, and when users report errors, stack traces, unexpected behavior, or say something stopped working.
gstack-openclaw-retro
Weekly engineering retrospective.
guidelines-advisor
Smart contract development advisor based on Trail of Bits' best practices.
implement
Implement a piece of work based on a spec or set of tickets.
implement-spec
Implement a specification in code.
improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
Instructions 上下文
Audit Copilot instruction files for bloat, overlap, stale rules, and weak applyTo scope.
网站国际化
Adds multi-language support to Next.js websites with proper SEO configuration including hreflang tags, localized sitemaps, and language-specific content.
interpreting-culture-index
Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data.
investigate
Systematic debugging with root cause investigation.
ios-clean
Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app.
ios-design-review
Visual design audit for iOS apps on real hardware.
ios-sync
Regenerate the iOS debug bridge against the latest upstream gstack templates.
Iterative 审查
Plan → code → review → re-code feedback loop with persistent state across iterations.
K8s 助手
Kubernetes and Helm standards for manifests, charts, values files, RBAC, workloads, networking, policy, validation, or deployment review.
LangChain 助手
Use when editing a non-agentic LCEL pipeline — composing Runnables, retrievers, embeddings, chat models, parsers, or building a RAG chain.
LangChain 助手
Use when building or productionising any agent — adding retries, fallbacks, summarization, human-in-the-loop, PII redaction, call limits, or…
LangChain 助手
Update LangChain to latest version Use when: "update langchain, langchain Use when this capability is needed.
local-codex
Launch and manage OpenAI Codex CLI (local agent) as a non-interactive coding sub-agent.
loop-me
Grill me about specs for the workflows I want to build, within this workspace.
Machine 学习 Algor
Use when answering CLRS-style machine-learning algorithm questions about k-means clustering, Lloyd's procedure, multiplicative weights, weighted majority, online experts, gradient descent, projected gradient descent, convex optimization, linear regression, or regularization.
MCP 测试
Run live tests of the Ariadne MCP server using Claude Code in headless mode.
Codex 迁移
>- Use when this capability is needed.
migrate-to-shoehorn
Migrate test files from `as` type assertions to @total-typescript/shoehorn.
移动端 Patterns
Use quando precisar implementar features mobile (React Native, Flutter, Swift, Kotlin), configurar builds, resolver problemas de plataforma ou adaptar UI para mobile.
Multi 技能排查
This skill should be used when the user asks about "LSP", "language server", "gopls", "pyright", "rust-analyzer", "typescript-language-server", "multi-language project", "code completion", "diagnostics", or "editor language support".
Next.js 助手
Baseline guidance for App Router apps.
Nodejs 代码验证
Node.js + Express backend patterns.
odoo 后端
Use when working on Odoo 19 server-side code or backend tests: Python models, ORM recordsets, fields/decorators, domains, SQL/cache, `__manifest__.py`, XML/CSV data, ACLs/rules, `sudo`, controllers, `@route`, `ir.cron`, JSON-2/XML-RPC, QWeb reports, `TransactionCase`, `HttpCase`, `Form`, tours, `start_tour`, or `--test-tags`.
Okdev 会话排查
Use when helping someone use okdev to initialize, start, inspect, connect to, sync with, troubleshoot, or tear down Kubernetes dev sessions, including manifest-backed and PyTorchJob workloads.
openclaw
>- Use when - "为什么甲虾能用 DeepSeek，乙虾不行？
Openlore Tests 写
Write real tests for a function or spec scenario — language-agnostic (TypeScript, Python, C++…).
Next.js 助手
Use oRPC inside a Next.js project (App Router and Pages Router).
panel-review
Reviews a code target by launching a panel of specialist auditor agents and merging their reports.
plan-ceo-review
CEO/founder-mode plan review.
plan-design-review
Designer's eye plan review — interactive, like CEO and Eng review.
plan-devex-review
Interactive developer experience plan review.
plan-eng-review
Eng manager-mode plan review.
plan-tune
Self-tuning question sensitivity + developer psychographic for gstack (v1: observational).
playwright-ci-caching
Cache Playwright browser binaries in CI/CD pipelines (GitHub Actions, Azure DevOps) to avoid 1-2 minute download overhead on every build.
Posthog 分析
PostHog analytics and session replay integration for React Native mobile apps.
pr PR审查
Create a GitHub pull request — pushes the current branch and opens a PR with auto-generated title and description.
pr PR助手
PR Description — Pull Request 描述生成 Agent git diff + branch context → 结构化 PR 描述 → 可选通过 gh CLI 创建 PR。
pr PR审查
| Use when this capability is needed.
pr-improver
Runs an autonomous review-and-fix improvement loop over the current branch's changes until a PR review comes back clean, scoped mechanically to the directories the branch touched.
product-analysis
Multi-path parallel product analysis that combines Claude Code agent teams and Codex CLI for cross-model test-time compute scaling.
产品 spec 构建
毒舌产品经理技能包，负责需求收集、产品文档编写和迭代更新。
项目 Ployglot 项目 S
Scaffold a polyglot library project as TypeScript + Python twin packages under `packages/ts/` + `packages/py/`, with a shared `SPEC.md`, cross-language `tests/parity/fixtures.json`, side-by-side `examples/sdk/` + `examples/api/` documentation, per-package `Makefile`, and a root orchestrator that exposes `make ci`.
prototype
Build a throwaway prototype to answer a design question.
Public Plugin 构建
> Use when this capability is needed.
Pytest 技能测试
Python test generation assistant Use when this capability is needed.
Pytest 会话测试
Pytest com fixtures e parametrize, sem unittest.TestCase Use when this capability is needed.
Python 仓库 Quicks
Quickly analyzes Python repositories to understand their purpose, structure, and setup requirements.
qa
Systematically QA test a web application and fix bugs found.
qa-expert
This skill should be used when establishing comprehensive QA testing processes for any software project.
Qprisma 文档 同步
Keep QPrisma documentation, Copilot instructions, agents, skills, PR templates, and changelog synchronized with implementation and workflow behavior.
r3-reactive-extensions
Build reactive/event-driven C# with R3 (Cysharp's modern reimplementation of Reactive Extensions).
re 技能验证
> Use when this capability is needed.
React 助手
Build and manage React Native/Expo mobile apps including project setup, development workflows, and platform-specific guidance.
React 助手
React Native mobile testing, performance, and release hardening for this repo.
React 助手
Load when: implementing or reviewing the vendor mobile app (React Native, Expo managed workflow, NativeWind v5).
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation Code review requires technical evaluation, not emotional performance.
仓库 Guidance 同步
Keep repository documentation, AGENTS.md, and contributor/test guidance aligned with code, design, and product changes.
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements Dispatch a code reviewer subagent to catch issues before they cascade.
research
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
resolving-merge-conflicts
Use when you need to resolve an in-progress git merge/rebase conflict.
review
Pre-landing PR review.
审查
| Use when this capability is needed.
review-pr
Reviews the current branch's changes against its base branch as a pull request: correctness of new and modified code, test coverage for it, and documentation accuracy.
Reviewing 技能
> Use when this capability is needed.
rf 方案规划
Юрист-профессионал по законодательству РФ.
规则 创建
为不同 IDE 工具创建有效的 AI 代理规则。
规则 Quality Evalu
Evaluate the quality of existing agent instruction rule sets — CLAUDE.md, AGENTS.md, .cursorrules, copilot-instructions.md, or any coding-ag…
rust 技能排查
Rust com clippy warnings-as-errors, sem unwrap fora de testes Use when this capability is needed.
rust 技能排查
Use this skill when the user asks about rust-libp2p, Rust libp2p, libp2p::SwarmBuilder, NetworkBehaviour, ConnectionHandler, Transport, Peer…
rust-review
Performs comprehensive Rust security review for safe/unsafe boundary issues, memory safety in unsafe blocks, concurrency hazards, panic-induced DoS, FFI safety, and async runtime mistakes.
ruzzy
> Ruzzy is a coverage-guided fuzzer for Ruby built on libFuzzer.
Satellite 浏览器测试
Open satellite imagery using deeplinks with coordinates and zoom levels via bash `open` command.
scaffold-exercises
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting.
second-opinion
Runs external LLM code reviews (OpenAI Codex or Google Gemini CLI) on uncommitted changes, branch diffs, or specific commits.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules.
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout.
setup-pre-commit
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo.
ship
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR.
skill-creator
>- Use when | Required evidence | Do not add by default |.
skill-improver
Runs an autonomous review-and-fix improvement loop over a Claude Code skill until a review comes back clean, with a cross-round findings ledger, escalation when fixes stop converging, and a mechanical scope guard.
skill-reviewer
Reviews and improves Claude Code skills against official best practices.
skills-search
This skill should be used when users want to search, discover, install, or manage Claude Code skills from the CCPM registry.
Slack 生成
Knowledge and utilities for creating animated GIFs optimized for Slack.
spec-to-code-compliance
Check code against the documentation that specifies it - which requirements hold, which the code contradicts, which are absent, and what the code does that no document mentions.
spec 仓库
Use when the user says 'build me an app', 'create a project from this spec', 'scaffold a new repo', 'generate a starter', 'turn this idea into code', 'bootstrap a project', 'I have requirements and need a codebase', or provides a natural-language project specification and expects a complete, runnable repository.
Sprint 头脑风暴
Sprint Flow Skill | 原则 | 说明 | |------|------| | 单一入口 | 用户只需调用 /sprint-flow，自动串联全流程 | | 自动流水线 | 类似 autoplan，自动执行多个阶段 | | 关键节点暂停 | APPROVED 确认…
Status 上下文配置
Project status dashboard — Copilot instructions budget, unfilled placeholders, lessons file size, hooks executability, jq availability, plug…
GitHub 助手
<!-- 🤖 【中文注释】 工具名称: 指令推荐助手 功能分类: 通用助手 功能说明: 用于推荐适合当前仓库的 Copilot 指令文件，避免重复并识别过时指令。
Swift 技能创建
Use when the project uses Swift for iOS, macOS, watchOS, tvOS, or visionOS development <!-- tomevault:4.0:skill_md:2026-05-23 -->
Swift 审查
Review Swift/iOS code: SwiftUI, Combine, UIKit, App Store guidelines and iOS architecture Use when this capability is needed.
systematic-debugging
系统化调试 bug：观察 → 假设 → 验证 → 修复。
tdd
Test-driven development.
Telegram 会话审查
Access a personal Telegram account's messages and chats via MTProto (Telethon).
Terraform 助手
Terraform and OpenTofu standards for .tf, .tfvars, .tofu, modules, providers, state, plans, policy checks, and IaC review.
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code Write the test first.
testcontainers-integration-tests
Write integration tests using TestContainers for .NET with xUnit.
to-spec
Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of what you've already discussed.
to-tickets
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).
token-integration-analyzer
Token integration and implementation analyzer based on Trail of Bits' token integration checklist.
triage
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
Typescript 代码创建
Use to generate and organize production-ready TypeScript types, interfaces, enums, DTOs, and shared utility types using strict feature-based type folders and centralized exports.
ui-designer
Extract design systems from reference UI images and generate implementation-ready UI design prompts.
ui-ux-pro-max
UI/UX design intelligence for web, mobile, and desktop.
使用 Git Branchles
Use when working in a git repo that uses git-branchless or stacked-diffs workflow.
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback Ensure work happens in an isolated workspace.
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
Web Artifacts 构建
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui).
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright.
Web 应用测试
Toolkit for interacting with and testing local web applications using Playwright.
wizard
Generate an interactive bash wizard that walks a human through steps only they can perform.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).