n8n Issue 创建
Create Linear tickets or GitHub issues following n8n conventions.
润色、改稿、合规审查 · 467 个 Skill
Create Linear tickets or GitHub issues following n8n conventions.
Applies n8n's RBAC scope decorators to REST endpoints.
Reproduce a bug from a Linear ticket with a failing test.
**WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL…
Behavioral guidelines to reduce common LLM coding mistakes.
Guide for performing Chromium version upgrades in the Electron project.
| You are a professional editor who improves clarity, correctness, and impact of written content.
| You are a senior Python developer with 10+ years of experience.
Testing strategy for Supabase Studio.
Generates Angular code and provides architectural guidance.
Review, improve, rewrite, author, or plan Storybook documentation in /docs.
Remove signs of AI-generated writing from text.
> Paperclip's UI is a professional-grade control plane — dense, keyboard-driven, dark-themed by default.
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization.
Agent skill for docs-api-openapi - invoke with $agent-docs-api-openapi name: "api-docs" description: "Expert agent for creating and maintaining OpenAPI/Swagger documentation" type: "documentation" version: "1.0.0"
Agent skill for multi-repo-swarm - invoke with $agent-multi-repo-swarm name: multi-repo-swarm description: Cross-repository swarm orchestrat…
Agent skill for payments - invoke with $agent-payments name: flow-nexus-payments description: Credit management and billing specialist.
Agent skill for pr-manager - invoke with $agent-pr-manager name: pr-manager description: Comprehensive pull request management with swarm coordination for automated reviews, testing, and merge workflows type: development color: "#4ECDC4" Comprehensive pull request management with swarm coordination for automated reviews, testing, and merge workflows.
Agent skill for project-board-sync - invoke with $agent-project-board-sync name: project-board-sync description: Synchronize AI swarms with…
Agent skill for release-manager - invoke with $agent-release-manager name: release-manager description: Automated release coordination and d…
Agent skill for release-swarm - invoke with $agent-release-swarm name: release-swarm description: Orchestrate complex software releases usin…
Agent skill for repo-architect - invoke with $agent-repo-architect name: repo-architect description: Repository structure optimization and m…
Agent skill for swarm-pr - invoke with $agent-swarm-pr description: Pull request swarm management agent that coordinates multi-agent code re…
Agent skill for sync-coordinator - invoke with $agent-sync-coordinator name: sync-coordinator description: Multi-repository synchronization…
Agent skill for workflow-automation - invoke with $agent-workflow-automation name: workflow-automation description: GitHub Actions workflow…
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization.
Create, update, or validate a product brief.
Create or update component documentation in Sentry's MDX stories format.
Create, edit, inspect, or convert PowerPoint decks and PPTX slide presentations with practical layout and verification steps.
Master Godot 4 GDScript patterns including signals, scenes, state machines, and optimization.
Python code style, linting, formatting, naming conventions, and documentation standards.
Apply typography, color theory, spacing systems, and iconography principles to create cohesive visual designs.
Manage local skills - list, add, remove, search, edit, setup wizard Meta-skill for managing oh-my-claudecode skills via CLI-like commands.
| Patterns for self-improvement through iterative evaluation and refinement.
When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid…
When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover.
When the user wants to edit, review, or improve existing marketing copy, or refresh outdated content.
When the user wants to write, rewrite, or improve marketing copy for any page — including homepage, landing pages, pricing pages, feature pa…
When the user wants to create, plan, or optimize a lead magnet for email capture or lead generation.
When the user wants to apply psychological principles, mental models, or behavioral science to marketing.
When the user wants to create sales collateral, pitch decks, one-pagers, objection handling docs, or demo scripts.
Produce a .pptx file on disk (headless) instead of driving a live PowerPoint document — for managed-agent sessions with no open Office app.
Produce a .xlsx file on disk (headless) instead of driving a live Excel workbook — for managed-agent sessions with no open Office app.
Manage local skills - list, add, remove, search, edit, setup wizard Meta-skill for managing oh-my-codex skills via CLI-like commands.
Browse the web for any task — research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test w…
| Use this skill when changing the shared agent setup for the repository.
React and Next.js performance optimization guidelines from Vercel Engineering.
A general-purpose academic paper writing tool — 12-agent pipeline covering all disciplines, with higher education domain as the default refe…
Multi-perspective academic paper review with dynamic reviewer personas.
Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize.
Universal deep research tool — a domain-agnostic 13-agent team for rigorous academic research on any topic.
| You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human.
Generate self-contained HTML architecture diagrams.
Read AI-Trader financial event snapshots and market-intel endpoints.
Review content against your brand voice, style guide, and messaging pillars, flagging deviations by severity with specific before/after fixes.
Draft marketing content across channels — blog posts, social media, email newsletters, landing pages, press releases, and case studies.
| This skill is the inverse of gbrain skillpack scaffold.
Video editing using Volcengine Track structure.
Converts live-action videos into artistic styles like comic, anime, manga, 3D cartoon.
Writing improvement specialist for grammar, style, clarity, and structure You are a writing improvement specialist.
Web search via 9Router /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Linkup / SearchAPI / You.com / Perplexity.
This skill is split into two layers: Do not try to apply the polishing logic from memory or from this router.
>- This skill is split into two layers: Do not try to apply the response logic from memory or from this router.
This skill is split into two layers: Do not try to apply the drafting logic from memory or from this router.
> 根据用户输入自动判断发布方式和发布模式,简化发布流程。
Systematic literature review methodology including search strategy, screening, and synthesis.
根据自然语言生成 SQL 查询语句(支持 MySQL/Doris/ClickHouse/PostgreSQL) 你是一个 SQL 专家,根据用户的自然语言描述生成正确的 SQL 查询语句。
> Create, edit, and format DOCX documents via CLI tools or direct C# scripts built on OpenXML SDK (.NET).
Open, create, read, analyze, edit, or validate Excel/spreadsheet files (.xlsx, .xlsm, .csv, .tsv).
Generate, edit, and read PowerPoint presentations.
Implement single-slide PowerPoint pages with PptxGenJS.
Orchestrate a complete paper writing workflow for: $ARGUMENTS This skill chains five sub-skills into a single automated pipeline: /paper-pla…
Orchestrate Unity Editor via MCP (Model Context Protocol) tools and resources.
**WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL…
商品文案写作助手。
固收与信用分析:信用债评级、利差分析、违约风险评估、城投债研究、可转债定价与策略。
Use when optimizing PostgreSQL queries, configuring replication, or implementing advanced database features.
Generates publication-quality figures for ML papers from research context.
IDA Pro Python scripting for reverse engineering.
Generates optimized prompts for AI tools.
You generate a high-quality daily financial news report based on reliable sources, including macro trends, market movements, and key events.
Use when multiple plausible dates exist and "latest" is not implied.
Generate a source-backed weekly financial trading outlook from daily-finance, finance-core-analysis, and finance-explosive-article outputs plus fresh authoritative market data.
从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读,并保存到当前项目的 markdown 目录。
Download WeChat official account articles in multiple formats (HTML, PDF, Word, Markdown, TXT, MHTML), including single article download, collection (appmsgalbum) download, local bulk workflows, and metadata export.
Remove AI writing patterns from prose.
Agent management expert.
面向 GPT Image 2 的图像生成 / 编辑技能。
Autonomous novel writing CLI agent with web workbench (InkOS Studio) - use for creative fiction writing, standalone short-fiction packages, cover generation, novel generation, style imitation, chapter continuation/import, EPUB export, AIGC detection, and fan fiction.
TikTok Ads deep analysis covering creative quality, tracking, bidding, campaign structure, and TikTok Shop under the TikTok USDS Joint Venture (post Jan 2026 divestiture).
GitHub issue and project-board management for the dotnet/msbuild repo.
Use kordoc for agent-native HWP/HWPX document parsing, JSON extraction, diffing, form-field extraction, and Markdown→HWPX reverse conversion…
Use when the user asks for any kind of slide-based output or wants to turn.
Always use when user asks to create, generate, draw, or design a diagram, flowchart, architecture diagram, ER diagram, sequence diagram, class diagram, network diagram, mockup, wireframe, or UI sketch, or mentions draw.io, drawio, drawoi, .drawio files, or diagram export to PNG/SVG/PDF.
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.
This skill should be used when the user asks to "analyze skill quality", "evaluate this skill", "review skill quality", "check my skill", or "generate quality report".
Agent Orchestration Rules When the user asks to implement something, use implementation agents to preserve main context.
Guide for integrating Agentica SDK with Claude Code CLI proxy Use this skill when developing or debugging the Agentica-Claude proxy integration.
>-
Write and improve agent skills (SKILL.md files).
Persist design documents with branch tracking, revision chains, and cross-session discovery Persist design documents from brainstorming and planning sessions with branch tracking, revision chains, and cross-session discoverability.
Post-ship doc sync across project markdown.
Switch to Knowledge Work mode for research and writing — use when task is non-code focused All subsequent workflows will use Knowledge Conte…
Create zero-context implementation plans with bite-sized tasks — use for multi-step feature planning Write comprehensive implementation plan…
Create Excalidraw diagram JSON files that make visual arguments.
Core runtime behavior for the atopile sidebar agent: identity, persistence model, execution rules, and tool recipes.
How the Faebryk component library is structured, how `_F.py` is generated, and the conventions/invariants for adding new library modules.
How the atopile Language Server works (pygls), how it builds per-document graphs for completion/hover/defs, and the invariants for keeping it fast and crash-proof.
Improve academic paper writing quality for ML/CV/NLP-style papers with clear section structure, paragraph flow, and reviewer-facing presentation.
一句话生成大师级海报、书籍封面、专辑封面和各类设计作品。
>- This companion skill is adapted from Yuan1z0825/nature-skills/tree/main/nature-figure.
【WORKFLOW SKILL】通用剪辑流程。
Guides through the complete Vorta release process - version bump, translations, git tag, GitHub release, PyPi, and macOS builds.
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.
Use when writing literature review sections - guides searching, organizing, and synthesizing academic sources 本技能指导文献搜索、整理和综述写作。
Use when writing academic papers, theses, or research articles - supports brainstorming, chapter writing, literature review, and LaTeX outpu…
Use when the user requests diagrams, flowcharts, architecture diagrams, ER diagrams, UML / sequence / class diagrams, network topology, ML/DL model figures (Transformer/CNN/LSTM), mind maps, or any visualization.
| 你是小说封面设计师。
>- Execute CLI commands and tests inside the devcontainer.
Evaluate Agent Skill design quality against official specifications and best practices.
Optimizes AI skills for activation, clarity, and cross-model reliability.
剪映 (JianYing) AI自动化剪辑的高级封装 API (JyWrapper)。
微信公众号文章写作 - 文章结构、排版规范、阅读转化优化、封面建议 帮助运营者写出高阅读、高转发的微信公众号文章,覆盖从选题到排版的全流程。
> When this skill triggers, go straight to Step 1.
专业的爆款短视频文案创作工具。
How to contribute to the Trezor Suite code style guide, including issue proposals and pull request workflows.
Academic writing expert specializing in scholarly papers, literature reviews, research methodology, and thesis writing with strict academic standards.
Generate editable PPTX from documents using local ppt-master pipeline.
Generate AI images using Gemini or GPT APIs directly.
Writes an implementation plan with small steps, exact files to touch, and verification commands.
Create distinctive, production-grade frontend interfaces with high design quality.
Behavior-driven UI testing patterns.
写作助手 - 当用户说"我想写XX"、"帮我梳理选题"、"怎么形成框架"、"给我组织思路"时触发。
Design, inspect, create, and update Hone skills using the Claude Code-style runtime contract.
Debug dbt errors — compilation failures, runtime database errors, test failures, wrong data, and performance issues.
When the user wants to define, audit, or apply brand strategy—purpose, values, positioning, storytelling, voice, narrative (not only visuals…
When the user wants to create Pinterest Pins, optimize Pin descriptions, or grow Pinterest presence.
中文写作技能指南,用于生成高质量的周刊、博客及科技资讯类文章。
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI.
How to use the PyMAPDL command-line interface to start, stop, list, and execute commands on MAPDL instances from a terminal.
Authors deterministic and LLM rubric graders for skillgrade evaluations.
Sets up and runs skillgrade evaluation pipelines for Agent Skills.
Create Facebook and Meta ad campaigns, write ad copy, define audiences, and plan budgets.
In-place DOCX editing routing to docx-edit-agent Thin wrapper that routes in-place DOCX editing requests to the docx-edit-agent, which edits documents using SuperDoc MCP with optional Word AppleScript integration for zero-friction workflow.
Implement Neovim configuration changes from plans.
Implement Nix configuration changes from plans.
Thin wrapper that delegates plan revision to reviser-agent subagent.
XLSX creation, editing, and analysis routing to sheet-agent Thin wrapper that routes XLSX creation, editing, and analysis requests to the sheet-agent, which manipulates spreadsheets using openpyxl and pandas via Bash.
产品需求文档(PRD)的标准编写格式和内容要求,确保输出完整、清晰、可执行的产品文档 完成需求穿透和调研分析后,需要输出一份完整的产品需求文档(PRD),供设计师、开发者、测试人员使用。
Discord messaging via `message_send` (channel=discord).
| Two modes control which files and gates are loaded.
Build and review Blazor applications across server, WebAssembly, web app, and hybrid scenarios with correct component design, state flow, rendering, and hosting choices.
Build, maintain, or modernize Windows Forms applications with practical guidance on designer-driven UI, event handling, data binding, MVP separation, and migration to modern .NET.
Build and modernize WPF applications on .NET with correct XAML, data binding, commands, threading, styling, and Windows desktop migration decisions.
Assist writers with story planning, character development, plot structuring, chapter writing, timeline tracking, and consistency checking.
中文写作、改写、润色、翻译和审阅的去 AI 味技能。
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization.
Mark expedition as blocked with reason and optional unblock agent Mark an expedition as blocked with a clear reason so other agents know why and who can help.
Use GPT-5.2 for long-running coding tasks: large refactors, feature implementation etc.
gh pr checks <PR番号> ブランチ feature/4-ethernet-frame で実行:
Dump a Claude Code session transcript as navigable Markdown.
Manage Contextium tasks - create, update, complete, and list tasks Manage tasks in .contextium/tasks.json.
Find and start the next highest-priority expedition from the kanban board Find and start work on an expedition.
公众号文章自动化写作流程。
Evaluate Agent Skill design quality against official specifications and best practices.
Improve an open-source GitHub skill and open a friendly suggestion PR upstream: fork, run skill-auto-improver, attach asm eval before/after metrics.
创建或改写 akashic-bot 技能(SKILL.md)。
ALWAYS use when writing code importing \"sqlite-vec\".
微信公众号文章聚合器。
Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization.
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.
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?
Create or edit skills with proper structure, task tracking, and naming conventions Create new skills or edit existing ones.
| 本 Skill 提供 30 个论文写作场景的 Prompt 模板,覆盖文献调研→大纲撰写→初稿写作→润色修改→图表制作→投稿回复→基金申请全流程。
Evaluates and optimizes skill file quality using 8 content patterns and 9 editing principles.
Guidelines for writing Agent Skills that comply with the agentskills.io specification.
>- Execute CLI commands and tests inside the devcontainer.
Help produce written content by researching topics and gathering references.
| Run scenarios without the skill (RED — watch agent fail), write skill addressing those failures (GREEN), then close loopholes (REFACTOR).
Apply consistent Material Design UI theming in Egroo using MudBlazor.
Tracks skill usage patterns, edit frequency, and success rates to suggest improvements and optimizations.
|- <powerpointprofessionalsuite> <highfidelitycreation> The preferred method for precise layout positioning: </highfidelitycreation> <template_structure>
When the AI leads vs.
Generate complete academic survey papers using multi-LLM parallel outline generation, RAG-based subsection writing, citation validation, and local coherence enhancement.
| Use when MCP returns no images, or when page-region cropping is needed:.
Minimal, goal-driven, surgical coding workflow adapted from forrestchang/andrej-karpathy-skills for OMK.
专业的党政机关公文写作指南。
You are a senior digital imaging professional with 10+ years of Adobe Photoshop expertise.
论文撰写全流程指导 skill,覆盖六种类型:专项研究、综述、系统/基准、短论文/Workshop、立场论文、科研汇报。
论文写作专家。
Query the Dimensions Analytics API using the dimcli CLI tool.
IT Manager Pro (Elite Leadership Advisor) workflow skill.
PostgreSQL Table Design workflow skill.
\u5eb7\u590d\u8bad\u7ec3\u5206\u6790\u6280\u80fd workflow skill.
Generates OpenAPI 3.0/3.1 specifications from Express, Next.js, Fastify, Hono, or NestJS routes.
Generate structured PR review comments using Claude Code agents and post them to GitHub.
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing This skill enables the use of Codex CLI for code analysis, refactoring, and automated editing tasks.
Creates or adds Cursor agent lifecycle hooks.
Investigation-only mode for understanding bugs, features, or system behavior without making changes.
Etalon memory architecture with Knowledge Graph (PARA), session isolation, memory decay, and QMD hybrid search Three-layer memory architecture for OpenClaw agents: curated long-term memory (MEMORY.md), structured knowledge graph (life/), and session-isolated daily notes (memory/).
Manages financial risks through quantitative analysis, modeling, and mitigation strategies.
Create distinctive, production-grade frontend interfaces with high design quality.
Comprehensive Cocos Creator 3.x development guide covering TypeScript scripting, component system, node hierarchy, scene management, resource loading, and event handling.
Use when editing files under `plugin/asicrs/`, `sdk/rust/`, or `server/sdk/v1/pb/` (which the asicrs build also consumes).
Build against the memories.sh SDK packages in application code.
> Use when ** Showing adoption rates, market growth, performance over time.
Navigate codebases efficiently using structural indexes.
Integration with the Pest PHP testing framework for writing and running tests Pest is an elegant PHP testing framework with a focus on simplicity.
Automate parametric pump impeller design in SolidWorks via API This skill provides guidance for automating parametric pump impeller design and other mechanical component modeling using the SolidWorks API.
小说创作工作台。
Comprehensive word document processing with full format support.
Use when adding global mode support for one existing agentsmesh target from a target-structure/global-path doc.
Streamlit page authoring patterns for AGILAB (session_state safety, keys, rerun, UX).
Enforce coding standards, style guides, and architectural patterns across projects.
Working with Microsoft Access databases exported via VCS (Version Control System for Access).
公文写作助手。
Apply text substitutions, rename package directory, and write templates Available knowledge: [[software-craft/versioning]].
| This skill enables Claude Code to work effectively with Lovable.dev projects while respecting Lovable's deployment requirements.
Merge new upstream releases of nushell and reedline into Shannon Shannon tracks nushell and reedline as git subtrees under nushell/ and features and fixes.
Writes Google Ads copy including RSA headlines, descriptions, extensions, DKI, CTAs, and intent-matched campaigns.
Photoshop advanced techniques and reference: wind direction master table (drips down, flames up, streaks left/right with canvas rotation), f…
Build and apply Home Assistant Lovelace dashboards from templates using a staged workflow with screenshot verification and context-reactive themes.
Guide frontend component design and code review using functional cohesion.
Anton ADR lifecycle — author new architectural decision records, list existing ones by status or affects-category, and mark old decisions su…
Triage ntfy.sh-routed alerts in Anton — identify which alert fired, why it fired (or why it didn't deliver), and propose a fix.
Anton planner skill — author, update, and close multi-session initiatives (migrations, rollouts, long-running refactors) in `context/plans/`…
Audit interfaces for accessibility issues across semantics, keyboard use, focus management, color contrast, labels, and announcements.
Check whether code changes silently broke API contracts, behavior, schemas, or compatibility expectations.
Draft app titles, descriptions, changelogs, and keyword sets for app-store releases.
Check whether backup and restore plans are actually restorable, verifiable, and operationally safe.
Propose lower-cost bill-of-material substitutions while preserving critical requirements, interfaces, and risk constraints.
Organize raw commits, merged changes, and unreleased notes into structured versioned changelog entries.
Check whether claims are adequately supported by cited sources and flag weak or mismatched citations.
Draft community replies, announcements, and moderation actions in an on-brand tone.
Generate useful Storybook stories, states, controls, and edge-case examples for UI components.
Transform one source asset into channel-specific content such as LinkedIn posts, X threads, captions, reel scripts, carousel copy, blog outlines, or newsletters while preserving the core message and voice.
Identify cloud and platform spend hotspots, waste, and likely optimization wins.
Define exactly what a product or ops dashboard should show, including metrics, dimensions, filters, and failure modes.
Review UI changes against spacing, typography, tokens, component usage, and design-system constraints.
Improve Dockerfiles for image size, caching, security, reproducibility, and multi-stage build hygiene.
Design realistic end-to-end test scenarios from product flows, state transitions, and critical user journeys.
Write reproducible procedures, controls, materials lists, and validation steps for experiments.
Structure post-failure analysis from field symptoms, logs, operator notes, and hardware context.
飞牛 fnOS FPK 应用包开发指南。
Draft concise investor, advisor, or team updates from raw notes, metrics, and milestones.
Organize grant proposal sections, milestones, evaluation plans, and impact framing into a coherent application package.
Review Kubernetes manifests, deployment defaults, probes, resources, security context, and rollout safety.
Identify what documentation is missing by comparing support issues, product behavior, and existing docs.
Design factory, bench, or end-of-line validation procedures for hardware products.
Turn goals, stakeholders, and open decisions into a tight meeting agenda with required outcomes.
Plan and carry out technical migrations such as dependency upgrades, framework changes, runtime version bumps, routing changes, schema moves, or package reorganizations.
Build a full internal or external newsletter from source notes, launches, events, and updates.
Add or improve logging, metrics, tracing, dashboards, and alert-ready instrumentation structure.
Draft point-by-point responses to reviewer comments using manuscript changes, evidence, and rebuttal structure.
Convert transcripts into polished show notes, summaries, timestamps, and links.
Review diffs like a senior engineer by checking correctness, architectural fit, style, missing tests, security smells, and migration or operational risk.
Draft polished client or stakeholder responses to proposals, questions, or requests using source notes and requirements.
Review SQL queries, execution plans, schema usage, and indexes to propose safer faster alternatives.
> | Use ralph-small | Use ralph-medium (this) | Use ralph-huge | |---------------------|----------------------------|-------------------| |…
> I receive a task.
> | Use ralph-small (this) | Use ralph-medium | Use ralph-huge | |---------------------------|---------------------|-------------------| | 1…
微信公众号文章检索工具。
Orchestrate the full add-a-program workflow on the crazy4points project (works for airlines, hotels, alliances, and credit cards — generic b…
Sync constitution to CLAUDE.md, AGENTS.md, and other agent files declared in manifest.yaml.
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.
Aider is an open-source AI pair programming tool that runs in your terminal, letting you collaborate with LLMs to edit code across your entire codebase.
Terminal pair programming with Aider, the AI pair programmer that edits Use when this capability is needed.
Use when building, extracting, reviewing, rendering, validating, or looking up ArchiMate® or UML® dediren packages, SVG/OEF/XMI evidence, dr…
Bootstrap a new host application on top of the published atrium base image, or retrofit an existing FastAPI / SQLAlchemy / React app onto atrium.
>- Make the repository usable without changing the user's normal way of working.
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using…
Use when fixing or auditing ANY accessibility issue — VoiceOver, Dynamic Type, color contrast, touch targets, WCAG compliance, App Store acc…
Use when fixing or auditing ANY accessibility issue — VoiceOver, Dynamic Type, color contrast, touch targets, WCAG compliance, App Store acc…
Use when implementing, testing, or evaluating ANY Apple Intelligence, on-device AI, or speech-to-text feature.
Use when implementing, testing, or evaluating ANY Apple Intelligence, on-device AI, or speech-to-text feature.
Use when ANY iOS build fails, test crashes, Xcode misbehaves, or environment issue occurs before debugging code.
Use when ANY iOS build fails, test crashes, Xcode misbehaves, or environment issue occurs before debugging code.
Use when writing ANY async code, actors, threads, or seeing ANY concurrency error.
Use when writing ANY async code, actors, threads, or seeing ANY concurrency error.
Use when working with ANY data persistence, database, storage, CloudKit, migration, or serialization.
Use when working with ANY data persistence, database, storage, CloudKit, migration, or serialization.
Use when making design decisions, implementing HIG patterns, Liquid Glass, SF Symbols, typography, or structuring app entry points and authentication flows.
Use when making design decisions, implementing HIG patterns, Liquid Glass, SF Symbols, typography, or structuring app entry points and authentication flows.
Use when building ANY 2D or 3D game with SpriteKit, SceneKit, or RealityKit, or adding touch controls or game controller support.
Use when building ANY 2D or 3D game with SpriteKit, SceneKit, or RealityKit, or adding touch controls or game controller support.
Use when integrating ANY iOS system feature - Siri, Shortcuts, widgets, IAP, localization, privacy, alarms, calendar, reminders, contacts, background tasks, push notifications, timers.
Use when integrating ANY iOS system feature - Siri, Shortcuts, widgets, IAP, localization, privacy, alarms, calendar, reminders, contacts, background tasks, push notifications, timers.
Use when working with camera, photos, audio, haptics, ShazamKit, or Now Playing.
Use when working with camera, photos, audio, haptics, ShazamKit, or Now Playing.
Use when implementing or debugging ANY network connection, API call, or socket.
Use when implementing or debugging ANY network connection, API call, or socket.
Use when app feels slow, memory grows, battery drains, or diagnosing ANY performance issue.
Use when app feels slow, memory grows, battery drains, or diagnosing ANY performance issue.
Use when storing credentials securely, encrypting data, implementing passkeys, securing AI/agentic features against prompt injection, code signing, or managing certificates and provisioning profiles.
Use when storing credentials securely, encrypting data, implementing passkeys, securing AI/agentic features against prompt injection, code signing, or managing certificates and provisioning profiles.
Use when preparing ANY app for submission, handling App Store rejections, writing appeals, or managing App Store Connect.
Use when preparing ANY app for submission, handling App Store rejections, writing appeals, or managing App Store Connect.
Use when reviewing Swift code for modern idioms, working with noncopyable types, implementing drag and drop, adding debug deep links, or building for tvOS.
Use when reviewing Swift code for modern idioms, working with noncopyable types, implementing drag and drop, adding debug deep links, or building for tvOS.
Use when the user wants to simplify Swift code, reduce boilerplate, or make Swift more readable and idiomatic without changing behavior.
Use when building, fixing, or improving ANY SwiftUI UI — views, navigation, layout, animations, performance, architecture, gestures, debuggi…
Use when building, fixing, or improving ANY SwiftUI UI — views, navigation, layout, animations, performance, architecture, gestures, debuggi…
Use when writing ANY test, debugging flaky tests, making tests faster, or choosing Swift Testing vs XCTest.
Use when writing ANY test, debugging flaky tests, making tests faster, or choosing Swift Testing vs XCTest.
Use when asking how to use Axiom or what skills exist, capturing console with xclog, symbolicating .ips/MetricKit/.crash crashes with xcsym, driving/validating simulator UI & accessibility with xcui, or analyzing xctrace/CPU profiles with xcprof.
Use when asking how to use Axiom or what skills exist, capturing console with xclog, symbolicating .ips/MetricKit/.crash crashes with xcsym, driving/validating simulator UI & accessibility with xcui, or analyzing xctrace/CPU profiles with xcprof.
Use when bridging UIKit and SwiftUI, modernizing UIKit apps (scene lifecycle, resizability), debugging Auto Layout, Combine, TextKit, PencilKit, or UIKit animations.
Use when bridging UIKit and SwiftUI, modernizing UIKit apps (scene lifecycle, resizability), debugging Auto Layout, Combine, TextKit, PencilKit, or UIKit animations.
Use when building ANY watchOS app — app structure, independent apps, Watch Connectivity, Smart Stack widgets, complications, controls, Relev…
Use when building ANY watchOS app — app structure, independent apps, Watch Connectivity, Smart Stack widgets, complications, controls, Relev…
Design banners for social media, ads, website heroes, creative assets, and print.
Design banners for social media, ads, website heroes, creative assets, and print.
群聊精华提取专家。
Create native unit tests for Swift (iOS) and Kotlin (Android) code in the bcsc-core package.
Performance regression detection using the browse daemon.
Cross-model benchmark for gstack skills.
用于下载哔哩哔哩视频并支持截图功能的技能。
Brand voice, visual identity, messaging frameworks, asset management, brand consistency.
Brand voice, visual identity, messaging frameworks, asset management, brand consistency.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel.
Fast headless browser for QA testing and site dogfooding.
Post-deploy canary monitoring.
Safety guardrails for destructive commands.
> Use when this capability is needed.
CI/CD review for workflows, artifact safety, caching, deployment gates, secrets, permissions, and reproducibility.
|- This skill helps you build LLM-powered applications with Claude.
'Guides the agent through a short, repeatable debug loop: capture the Refer to templates/fix_checklist.md and ensure every box is addressed:
"Guides the agent through a short, repeatable debug loop: capture Use when the user request matches this skill's domain and capabilities.
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.
OpenAI Codex CLI wrapper — three modes.
Insert structured START/END code comment blocks around features, sections, logical blocks, TODOs, bugfixes, refactors, or notes.
>- Use when this capability is needed.
Use whenever the user is authoring or modifying Kubernetes configuration stored in ConfigHub, or is about to reach for Helm, Kustomize, Jsonnet, cdk8s, or a values file.
> Use when this capability is needed.
Restore working context saved earlier by /context-save.
Save working context.
Recover actionable context from local `.claude` session artifacts and continue interrupted work without running `claude --resume`.
>- Recover actionable context from a prior Codex CLI session and continue execution in the current conversation.
Keeps examples/integrations/* demos aligned to the north-star (langgraph-python).
Maintains and extends the AI Assistant Crafter Studio plugin per in-repo Cursor rules and docs without regressing locked UX.
Create a new domain-specific instruction file when current coverage gaps require file-scoped guidance Use when this capability is needed.
Export OpenClaw cron job configurations as restorable JSON snapshots and import them back.
Chief Security Officer mode.
SQL database migrations with zero-downtime strategies for PostgreSQL, MySQL, and SQL Server.
understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview...
Design finalization: generates production-quality Pretext-native HTML/CSS.
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them…
generate multiple AI design variants, open a comparison board, collect structured feedback, and iterate.
Generates the full visual language (color palette, typography, spacing grid, elevation, interactive states) for a website based on a chosen mood.
Live developer experience audit.
Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can open on excalidraw.com, and rendered SVG + PNG.
Complete Discord server interaction via Discord bot API for posting messages, uploading/downloading images and files, editing/deleting messages, reading channel content, responding to mentions, and full server integration.
Apply fixes from a review.
Generate missing documentation from scratch for a feature, module, or entire project.
Post-ship documentation update.
Diátaxis Documentation Expert with brand voice guidance.
读取、新建或精细编辑 DOCX,并检查版式、修订与评论结构。
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction.
Build and sharpen a project's domain model.
Complete DreamHost website management via SFTP/SSH for React JS deployments, multi-site routing, file operations, and content management.
"Complete DreamHost website management via SFTP/SSH for React JS Use when the user request matches this skill's domain and capabilities.
Drizzle ORM is a lightweight TypeScript ORM that provides type-safe SQL schema declarations, relational and SQL-like query builders, and automatic migration generation.
Entity Framework Core best practices including NoTracking by default, query splitting for navigation collections, migration management, dedicated migration services, and common pitfalls to avoid.
Language-agnostic engineering methodology — DDD, Hexagonal Architecture, TDD, architecture planning, requirements gathering, code review, an…
One-shot review of an external GitHub PR.
Compose and edit dynamic multi-card Agent Canvas specs and staged dashboard patches through allowlisted farm actions.
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.
Use this skill whenever inspecting, interacting with, or live-editing a running Flutter app via the Flutter MCP toolkit server (`mcpServers` key **`flutter-mcp-toolkit`**, or legacy **`flutter-inspector`**).
Free local AI image and video processing toolkit with cloud AI generation.
Restrict file edits to a specific directory for the session.
You are an expert frontend/UI/UX designer with deep knowledge of modern design principles, accessibility standards, and responsive design patterns.
Builds distinctive, production-grade UIs that avoid generic AI aesthetics.
>- Audit the interface the user can actually see.
Smart Gemini CLI delegation skill.
Use when the user asks to run Gemini CLI, Google Gemini for code tasks, or references Gemini for analysis, code generation, or automated editing | Model | When to Use | |-------|-------------| | gemini-3-flash-preview | DEFAULT - Use for most tasks.
Discovers, retrieves, ranks, and summarizes real existing research papers on any topic.
A phase-based playbook for shipping pull requests that maintainers actually want to merge.
Provides comprehensive GitHub operations using gh CLI and GitHub API.
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.
Use when adding or configuring github.com/adlandh/echo-otel-middleware/v2 in a Go Echo application, or when writing examples for this middleware.
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.
Router for the gstack skill suite.
Upgrade gstack to the latest version.
Full safety mode: destructive command warnings + directory-scoped edits.
Code quality dashboard.
Systematic debugging with root cause investigation.
Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app.
Visual design audit for iOS apps on real hardware.
Autonomous iOS bug fixer.
Live-device iOS QA for SwiftUI apps.
Regenerate the iOS debug bridge against the latest upstream gstack templates.
Kimi-K2.5 Writing Skill.
Use when: organizing a markdown knowledge repository, importing sources into 原始资料, compiling 来源笔记/概念/主题, maintaining 索引, generating 派生内容, ru…
Land and deploy workflow.
Read-only queue dashboard for workspace-aware ship.
Use when editing a DeepAgents project — adding tools, sub-agents, modifying the system prompt, choosing a filesystem backend, or composing e…
Use when editing a non-agentic LCEL pipeline — composing Runnables, retrievers, embeddings, chat models, parsers, or building a RAG chain.
Use when building a custom-graph LangGraph agent — when `create_agent(...)` + middleware isn't enough and you need explicit StateGraph contr…
Use when authoring eval datasets, writing evaluators, running evals against a LangChain / LangGraph / DeepAgents project, comparing eval results between runs, or writing unit/integration tests for an agent.
Manage project learnings.
Use when the user wants to learn a new programming language, framework, or platform via a hands-on, one-lesson-at-a-time curriculum — phrasi…
Grill me about specs for the workflows I want to build, within this workspace.
Turn any markdown file into a publication-quality PDF.
Write and review Markdown (.md) files with consistent structure, correct links, and repo-friendly conventions.
>- Use when the skill should install, update, and roll back.
Authoritative reference for building MCP (Model Context Protocol) servers in Go using the official Anthropic+Google SDK.
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".
Edit PDFs with natural-language instructions using the nano-pdf CLI.
使用 newsbox CLI 与 Python SDK 采集 AI 内容信源、读取 raw.db、二次加工成日报/摘要/筛选结果。
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling Use when this capability is needed.
NocoDB turns any SQL database into a smart spreadsheet with a full REST API.
YC Office Hours — two modes.
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.
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in.
>- Switch or repair an OpenClaw instance's model configuration by safely editing openclaw.json.
Manage NuGet packages using Central Package Management (CPM) and dotnet CLI commands.
Pair a remote AI agent with your browser.
Propose a code patch for a finding.
CEO/founder-mode plan review.
Designer's eye plan review — interactive, like CEO and Eng review.
Interactive developer experience plan review.
Eng manager-mode plan review.
Self-tuning question sensitivity + developer psychographic for gstack (v1: observational).
PostHog analytics and session replay integration for React Native mobile apps.
PPT Master - AI 视觉内容生成系统 基于 AI 多角色协作的 SVG 内容生成系统,支持演示文稿、社交媒体、营销海报等多种格式。
Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both.
Presentation creation, editing, and analysis.
How to use the PyMAPDL command-line interface to start, stop, list, and execute commands on MAPDL instances from a terminal.
Systematically QA test a web application and fix bugs found.
Report-only QA testing.
| Use when this capability is needed.
Keep repository documentation, AGENTS.md, and contributor/test guidance aligned with code, design, and product changes.
Enterprise-grade autonomous research paper generation skill for AI coding agents — full papers, literature reviews, theses, whitepapers, sur…
Use when a pull request has received code review comments from gemini-code-assist and you need to read the feedback, fix or decline each item, reply in comment threads, and post a summary Read code review feedback on a pull request, resolve each item, reply in comment threads, and post a summary comment.
Weekly engineering retrospective.
Conduct a retrospective on a coding session.
Pre-landing PR review.
Pull data from a web page.
2026 SEO content writing for marketing sites — search intent, on-page structure, keyword research, E-E-A-T, internal linking, and AI Overvie…
Set up or update repository agent instruction files after installing skills.
Import cookies from your real Chromium browser into the headless browse session.
Configure deployment settings for /land-and-deploy.
Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy.
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR.
This skill provides comprehensive Shopify store management capabilities through the Shopify Admin GraphQL API.
把一套反复使用的 Agent 工作流打磨成可复用的 SKILL.md。
>- Use when | Required evidence | Do not add by default |.
Codify the most recent successful /scrape flow into a permanent browser-skill on disk.
Selects bounded, graph-informed source slices with Trailmark and delegates focused code analysis or patch-proposal work to a smaller subagent.
Turn vague intent into a precise, executable spec in five phases.
Load a flat dataset (CSV / Parquet / JSON / Excel) into a SQL database.
Keep gbrain current with this repo's code and refresh agent search guidance in CLAUDE.md.
State management, modules, workspaces, remote backends, and multi-environment strategies Use when this capability is needed.
>- 「Tibo reset」= OpenAI Codex/ChatGPT Work 负责人 Thibault Sottiaux(X: @thsottiaux) 个人在 X 上宣布的全员额度重置传统。
Clear the freeze boundary set by /freeze, allowing edits to all directories again.
Implement features and fix bugs for the vfs-s3 project.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui).
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui).
Uses the W&B Python SDK and Public API to stream live training metrics, system stats, and gradients from active runs.
Wiki.js is a powerful open-source wiki app built on Node.js with support for Markdown, visual editing, Git-backed storage, and a GraphQL API.
Windsurf editor - use when working on related tasks Use when this capability is needed.
Writing documents for agents.
Writing, exploit: shape raw material into an article, paragraph by paragraph.
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).
X (Twitter) integration for FFT_nano.
Search X posts and get Grok-grounded summaries via the local x-search CLI.
Use this skill any time a spreadsheet file is the primary input or output.