n8n 开发规范
Quick reference for n8n patterns.
Rust、Go、Python、TS…… · 706 个 Skill
Quick reference for n8n patterns.
>- Guide for adding new ESLint rules to packages/@n8n/eslint-plugin-community-nodes/.
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。
用于审计Claude技能和命令的质量。
| You are an expert data analyst with expertise in SQL, Python (pandas), and statistical analysis.
| You are an expert full-stack web developer specializing in modern JavaScript/TypeScript stacks with React, Node.js, and databases.
| You are a senior Python developer with 10+ years of experience.
| You are an expert technical writer who creates clear, user-friendly documentation for technical products.
Creates a new Angular app using the Angular CLI.
Write clear, developer-first copy for Zed — leading with facts, grounded in craft.
Write clear, developer-first copy for Zed — leading with facts, grounded in craft.
> Compress natural language files (CLAUDE.md, todos, preferences) into caveman-speak to reduce input tokens.
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
> Use this skill to parse, convert, chunk, and analyze documents with Docling.
Review RTK Rust code for idiomatic simplification.
> You have persistent long-term memory powered by mem0.
Agent skill for adaptive-coordinator - invoke with $agent-adaptive-coordinator name: adaptive-coordinator type: coordinator color: "#9C27B0" description: Dynamic topology switching coordinator with self-organizing swarm patterns and real-time optimization priority: critical; runs on Python.
Agent skill for automation-smart-agent - invoke with $agent-automation-smart-agent name: smart-agent type: automation description: Intellige…
Agent skill for base-template-generator - invoke with $agent-base-template-generator name: base-template-generator description: Use this agent when you need to create foundational templates, boilerplate code, or starter configurations for new projects, components, or features.
Agent skill for data-ml-model - invoke with $agent-data-ml-model name: "ml-developer" description: "Specialized agent for machine learning model development, training, and deployment" version: "1.0.0" makes outbound network calls; runs on Python.
Agent skill for hierarchical-coordinator - invoke with $agent-hierarchical-coordinator name: hierarchical-coordinator type: coordinator color: "#FF6B35" description: Queen-led hierarchical swarm coordination with specialized worker delegation priority: critical; runs on Python.
Agent skill for sona-learning-optimizer - invoke with $agent-sona-learning-optimizer name: sona-learning-optimizer description: SONA-powered…
Strategic business analyst and requirements expert.
UX designer and UI specialist.
Review TypeScript and JavaScript code changes for compliance with Metabase coding standards, style violations, and code quality issues.
Write TypeScript and JavaScript code following Metabase coding standards and best practices.
Create or update component documentation in Sentry's MDX stories format.
Write comprehensive, behaviour-driven unit tests for Gradio frontend Svelte components using Vitest browser mode, Playwright, and the @self/tootils test utilities.
Profile and optimize Python code using cProfile, memory profilers, and performance best practices.
Create, edit, inspect, or convert PowerPoint decks and PPTX slide presentations with practical layout and verification steps.
Master C#/.NET backend development patterns for building robust APIs, MCP servers, and enterprise applications.
Python code style, linting, formatting, naming conventions, and documentation standards.
Python design patterns including KISS, Separation of Concerns, Single Responsibility, and composition over inheritance.
Install, update, trust, or inspect DeepSeek skills from GitHub or local skill folders.
| Patterns for adding safety, trust, and policy enforcement to AI agent systems.
| Evaluate AI agent systems against the OWASP Agentic Security Initiative (ASI) Top 10 — the industry standard for agent security posture.
| Patterns for self-improvement through iterative evaluation and refinement.
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.
GPT Researcher is an autonomous deep research agent that conducts web and local research, producing detailed reports with citations.
Convert files and office documents to Markdown.
Analyze CSV files in /mnt/data and return concise numeric summaries.
Implements Manus-style file-based planning to organize and track progress on complex tasks.
Implements Manus-style file-based planning to organize and track progress on complex tasks.
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。
| 🛑 STOP(仅一次):首次激活时输出免责声明一次——「我以Karpathy视角和你聊,基于公开言论推断,非本人观点」。
> You are an Elasticsearch solutions architect in Kibana Agent Builder.
Personalized 1-on-1 AI tutor.
Follow top traders and automatically copy their positions.
Create effective data visualizations with Python (matplotlib, seaborn, plotly).
你正处于一个高绩效文化的团队中。
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…
Data analysis expert for statistics, visualization, pandas, and exploration You are a data analysis specialist.
Web search and research specialist for finding and synthesizing information You are a research specialist.
CI/CD reference for Megatron-LM.
>- This skill is split into two layers: Do not try to apply the figure logic from memory or from this router.
This skill is split into two layers: Do not try to apply the deck-building logic from memory or from this router.
> Scan and audit AI agent skills for security risks before installation.
Validate, test, and score the quality of skills within the claude-skills ecosystem.
Complete API for Google NotebookLM - full programmatic access including features not in the web UI.
Security auditing for code, configs, and infrastructure.
> 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。
'Implement network segmentation based on the Purdue Enterprise Reference Classify all network assets and data flows according to the Purdue Model hierarchy.
| 你正在执行一次横纵分析法深度研究。
> Create, edit, and format DOCX documents via CLI tools or direct C# scripts built on OpenXML SDK (.NET).
Generate, edit, and read PowerPoint presentations.
AKShare financial data aggregator (18k+ stars).
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。
ETF分析:产品筛选、费率对比、跟踪误差、流动性评估、策略应用与中国市场ETF量化配置框架。
财报三表深度解读——三表勾稽关系、盈利质量(应计vs现金流)分析、杜邦分解、10+财务造假红旗指标 从三张报表(利润表、资产负债表、现金流量表)的勾稽关系出发,深度分析企业盈利质量,识别财务造假信号,用杜邦分析分解盈利驱动因子。
行业轮动分析——申万行业景气度评分、行业动量排名、产业链传导、估值/盈利/资金流多维比较框架 基于A股申万行业分类体系,通过景气度评分、动量排名、估值比较、资金流向四个维度进行行业轮动分析,输出行业超配/低配建议。
Creates and configures NestJS modules, controllers, services, DTOs, guards, and interceptors for enterprise-grade TypeScript backend applications.
Performs pandas DataFrame operations for data analysis, manipulation, and transformation.
Generates Spring Boot 3.x configurations, creates REST controllers, implements Spring Security 6 authentication flows, sets up Spring Data JPA repositories, and configures reactive WebFlux endpoints.
IDA Pro Python scripting for reverse engineering.
深度解读学术论文,将论文 PDF(文件或 URL)转化为通俗易懂、图文并茂的 Markdown 解读文档,保存到项目的 markdown/ 目录。
从文稿内容生成专业 PPTX 演示文稿,支持用户提供的模板/参考图风格提取、AI 配图(siliconflow-img-gen)和素材图库(pexels/pixabay)。
> SERP-overlap-driven keyword clustering for content architecture.
UI/UX design intelligence.
> Follow the workflow below exactly.
Run Rust fmt, clippy, and unit tests.
Create a feature branch and open a pull request for the current changes.
Create, modify, inspect, and validate STEP-first build123d/Python CAD parts and assemblies.
文档生成器。
当用户对已有前任 Skill 说以下内容时,进入进化模式: 当用户说 /list-exes 时列出所有已生成的前任。
Android APK analysis using GDA.exe.
产出可发布章节,完整执行上下文→起草→审查→润色→提交→备份。
Expert guide for designing and building high-quality skills from scratch through structured conversation.
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。
Build voice AI agents with ElevenLabs.
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.
Reference guide for Agentica multi-agent infrastructure APIs Complete API specification for Agentica multi-agent coordination infrastructure.
Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity Write prompts that Agentica agents reliably follow.
Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration Build AI agents in Python using the Agentica framework.
Agentica server + Claude proxy setup - architecture, startup sequence, debugging Complete reference for running Agentica SDK with a local Claude proxy.
Spawn Agentica multi-agent patterns Use this skill after user selects an Agentica pattern.
Upgrade any skill to v5 Hybrid format using decision theory + modal logic Meta-skill that upgrades any SKILL.md to Decision Theory v5 Hybrid format using 4 parallel Ragie-backed agents.
Run tasks in a loop until goals are met — use for iterative refinement, polling, or convergence Systematic iterative execution with clear go…
Craft better prompts using proven optimization techniques — use when your prompt needs refinement Generate well-structured, verifiable promp…
URL validation and content sanitization for untrusted sources — use when handling external input safely This skill defines security patterns…
How FabLL (faebryk.core.node) maps Python node/trait declarations into the TypeGraph + instance graph, including field/trait invariants and instantiation patterns.
How Faebryk's TypeGraph works (GraphView + Zig edges), how to traverse/resolve references, and how FabLL types/traits map onto edge types.
How the Zig-backed instance graph works (GraphView/NodeReference/EdgeReference), the real Python API surface, and the invariants around allocation, attributes, and cleanup.
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.
How the Zig↔Python binding layer works (pyzig), including build-on-import, wrapper generation patterns, ownership rules, and where to add ne…
How the Zig S-expression engine and typed KiCad models work, how they are exposed to Python (pyzig_sexp), and the invariants around parsing, formatting, and freeing.
How the Faebryk parameter solver works (Sets/Literals, Parameters, Expressions), the core invariants enforced during mutation, and practical workflows for debugging and extending the solver.
Excel 数据分析多步编排器。
图片理解与数据提取 skill。
Remult patterns - entities, fields, repo() usage, lifecycle hooks, permissions (allowApi + apiPrefilter), upsert, customFilter, sqlExpression, ValueList enums, relations.
AI Trading Intelligence — live prices, 30+ technical indicators, backtesting (6 strategies), walk-forward overfitting detection, trade logs,…
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
>- This companion skill is adapted from Yuan1z0825/nature-skills/tree/main/nature-figure.
花叔Design(Huashu-Design)——用HTML做高保真原型、交互Demo、幻灯片、动画、设计变体探索、设计方向顾问与专家评审。
Mass spectrometry analysis.
Guides through the complete Vorta release process - version bump, translations, git tag, GitHub release, PyPi, and macOS builds.
为剧本场景生成视频片段。
Best practices for numerical computing with NumPy including arrays, broadcasting, and vectorization.
Full pipeline: Recon -> Learn -> Hunt -> Validate -> Report.
Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai).
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。
> ├── SKILL.md # 本文件(流程指令) │ ├── setup.sh # ⭐ 环境初始化(只需运行一次) │ ├── venv/ # Python 虚拟环境(setup.sh 自动创建) │ ├── fetch_all.py # 数据采集 + 图表生成(纯数据,不写…
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.
Provides AI and machine learning techniques for CTF challenges.
Provides web exploitation techniques for CTF challenges.
Automates Apple-platform apps (iOS, tvOS, macOS) and Android devices.
Umbrella skill for document workflows (PDF/DOCX/XLSX/PPTX).
Convert files and office documents to Markdown.
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。
| 主管道是固定的 8 个 Step(下面逐节展开): [1/8] 环境 + 配置 [2/8] 选题 [3/8] 框架 + 素材 [4/8] 写作 [5/8] SEO + 验证 [6/8] 视觉 AI [7/8] 排版 + 发布 [8/8] 收尾 PY="{skill_dir}/…
| 主管道是固定的 8 个 Step(下面逐节展开): [1/8] 环境 + 配置 [2/8] 选题 [3/8] 框架 + 素材 [4/8] 写作 [5/8] SEO + 验证 [6/8] 视觉 AI [7/8] 排版 + 发布 [8/8] 收尾 PY="{baseDir}/.v…
HTML原型转Unity UGUI界面生成管线。
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…
Authors and structures professional-grade agent skills following the agentskills.io spec.
Create a new Harbor task for evaluating agents.
| Conseil fiscal pour les particuliers français.
| Copilote juridique pour le droit immobilier, les successions, les donations, le droit de la famille et le droit des sociétés en France.
当用户明确要求"生成 NSFC 技术路线图/技术路线图绘制/roadmap/flowchart"或需要把标书研究内容转成"可打印、A4 可读"的技术路线图时使用。
当用户明确要求"做系统综述/文献综述/related work/相关工作/文献调研"时使用。
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
多智能体协同通信基础设施——基于 MCP+SSE 的实时消息、任务调度、记忆共享与进化引擎。
> Upstream tools for 13+ platforms.
Improve a skill's public listing before publish.
Security vetting protocol before installing any AI agent skill.
Vet ClawHub skills for security and utility before installation.
> 你将按照以下 6 个阶段执行 YouTube 视频剪辑任务: yt-dlp --version /opt/homebrew/opt/ffmpeg-full/bin/ffmpeg -version ffmpeg -filters 2>&1 | grep subtitles py…
Internal orchestrator — users should use /paperspine to start a full workflow.
| 问用户:「你要拆哪本书?
| 你是网络小说创作教练。
小红书笔记素材创作技能。
剪映 (JianYing) AI自动化剪辑的高级封装 API (JyWrapper)。
Use when analyzing data files or transforming datasets.
Design new Claude skills from structured idea specifications.
Mine Claude Code session logs for skill idea candidates.
Validate multi-skill workflows defined in CLAUDE.md by checking skill existence, inter-skill data contracts (JSON schema compatibility), file naming conventions, and handoff integrity.
Testing framework for evaluating Databricks skills.
Create a git commit.
代码审查和质量分析技能。
文件管理技能。
Prepare a psd-tools release: update changelog, open release PR.
CTF 逆向工程技术。
| 统一入口:python3 {baseDir}/cli.py <command> [options]
This skill supports both Chinese and English reports.
AI 视频生成全流程:通过 6 个阶段(剧本→角色/场景设计→分镜→参考图→视频生成→后期剪辑)将用户想法转化为完整视频。
Spring Boot 3.x development - REST APIs, JPA, Security, Testing, and Cloud-native patterns.
Evaluate a trained checkpoint with visualization Parse the user's request from $ARGUMENTS and run evaluation.
Launch a training run for a robot environment using PPO Parse the user's request from $ARGUMENTS and construct a training command.
基于七角色协作的智能 PPT 生成与优化工具。
专业的爆款短视频文案创作工具。
Helps users discover and install agent skills from the open skills ecosystem (skills.sh).
PowerPoint slide deck generation and management using python-pptx with YAML-driven content and styling - Brought to you by microsoft/hve-core Generates, updates, and manages PowerPoint slide decks using python-pptx with YAML-driven content and styling definitions.
抖音无水印视频下载和文案提取工具.
> Review a Java OpenInference instrumentation package against the project's established patterns and conventions.
从微信聊天记录创建前任的数字人格 Skill 你是一个帮助用户重建前任数字人格的助手。
Search, download, and summarize academic papers from arXiv.
| 从竞品视频拆解到脚本生成的完整工作流。
Clear description of what this skill does and when to use it.
分析营养数据、识别营养模式、评估营养状况,并提供个性化营养建议。
Create distinctive, high-converting landing pages that combine proven conversion elements with exceptional design quality.
Scaffold a new ClawBio skill from a spec file (JSON/YAML) or interactively — generates SKILL.md, Python skeleton, tests, and updates catalog…
Generate editable PPTX from documents using local ppt-master pipeline.
Enforces a disciplined workflow for coding, debugging, refactoring, and automation: brainstorm -> plan -> implement with verification (prefer TDD) -> review -> finish.
专业 PPT 演示文稿全流程 AI 生成助手。
Run performance benchmarks.
uv tool install kabi-boss-cli uv tool upgrade kabi-boss-cli boss status --json 2>/dev/null | jq -r '.authenticated' | grep -q true && echo "AUTHOK" || echo "AUTHNEEDED" If AUTH_OK, skip to Command Reference.
Scan agent skills for security issues.
花叔的「md/html/docx 多向流水线」skill,四个能力 + 两种模式:(1) 用Microsoft markitdown把任意文件(PDF/DOCX/PPTX/XLSX/HTML/图片/音频/YouTube/EPub/ZIP)转成干净的md;
> Automated pipeline: session analysis -> duplicate check -> skill creation.
Meta-skill for generating new skills with proper format and structure.
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。
> | 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…
MySQL/MariaDB database inspection and queries.
Generates complete Anthropic SKILL packages with proper structure, documentation, and automated download verification.
Scan Clawdbot and MCP skills for malware, spyware, crypto-miners, and malicious code patterns before you install them.
Security scanner for AgentSkill packages.
微信自动化操作 skill,用于帮助用户快速完成微信消息群发、文件发送、群管理、聊天记录获取、多群监听、AI 自动回复等自动化任务。
This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines.
How to discover, load, and effectively use skills to solve SkillBench tasks.
| 프로젝트 컨텍스트를 분석하여 project-local 스킬을 생성하는 워크플로우.
MX Space project Zod schema patterns.
用 LAMMPS 做材料科学分子动力学模拟:晶体构建、势函数选择、形变/冲击、结构分析、可视化。
用 OpenFOAM 做 CFD:从 case 结构、网格、求解器、湍流模型到后处理和验证。
How to use the PyMAPDL command-line interface to start, stop, list, and execute commands on MAPDL instances from a terminal.
Automatic solved-to-skill compiler — detects novel task completions and autonomously drafts new SKILL.md files.
Authors deterministic and LLM rubric graders for skillgrade evaluations.
Meta-skill for creating and managing Claude Code skills Meta-skill for creating new Claude Code skills, including skills that wrap MCP pipelines.
Upgrade any skill to v5 Hybrid format using decision theory + modal logic Meta-skill that upgrades any SKILL.md to Decision Theory v5 Hybrid format using 4 parallel Ragie-backed agents.
>- Use when the user says things like "compare designs", "what changed", "diff my schematic", "show changes from main", or "diff base vs head".
A股专业分析师助手,提供每日股价分析、选股策略和投资建议。
Windows C盘清理和磁盘空间管理工具。
Implementation skill for R-based epidemiology analysis.
Presentation extraction and slide generation routing Thin wrapper that routes presentation operations to the presentation-agent.
Implement Python code.
Research Python development tasks.
Implement web (Astro/Tailwind/TypeScript) changes following a plan.
Optional sidecar skill for controlled feedback-driven skill evolution.
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…
| Tools and workflows for accessing public biological databases, retrieving sequencing data, querying gene/protein information, pulling processed functional / 3D-genome tracks, fetching cancer-cohort data, and downloading large-scale single-cell datasets.
Build and review Blazor applications across server, WebAssembly, web app, and hybrid scenarios with correct component design, state flow, rendering, and hosting choices.
Provides comprehensive guidance for Rspack bundler including configuration, plugins, loaders, optimization, and Webpack compatibility.
Audit a ClawHub skill for security risks BEFORE installation.
This skill should be used whenever users need help planning trips, creating travel itineraries, managing travel budgets, or seeking destination advice.
<One sentence describing what knowledge this skill provides.> <!-- One sentence: what does this skill help Copilot do?
Authors and structures professional-grade agent skills following the agentskills.io spec.
Fix a random FIXME in the codebase (in the given scope, use "." for the whole codebase) Your task is to make ONE improvement to the codebase by fixing a random thing about the codebase (eg, normally a FIXME).
python skills/{skill-name}/scripts/main.py --param value | パラメータ | 必須 | デフォルト | 説明 | |-----------|------|----------|------| | --param1 | はい…
Start or stop the WireMock API mock server for UI testing and E2E verification.
公文格式排版工具。
Downloads skills from a AgentKit skill space to the local machine.
Registers a local skill to the AgentKit platform by uploading it.
Google Docs の一覧を取得します。
9-language quality gate validation: linting, formatting, type checking, and test execution.
Display git changes in GitHub-style unified diff format with colored terminal output.
카카오톡 이전 메시지 보기.
Start local development environment with backend and macOS app Start the backend server and macOS app for local development.
Slack チャンネルを既読にします(一括既読化)。
Integracja KFG do istniejącego projektu bez logs/.
Discover available skills and subagents.
Safety Monitor Agent responsible for compliance and safety checks.
スレッドの参加者一覧を取得します。
A unified interface for annotating single-cell RNA-seq data using Marker Genes, Deep Learning (CellTypist), or LLMs.
Audit AI Agent skills for security vulnerabilities including malicious code, remote execution, credential leaks, and supply chain risks.
微信小程序全自动安全审计 Skill。
微信消息桥接 - 在微信中与 Claude Code 聊天。
EconML (Microsoft) — heterogeneous treatment effect estimation.
亚马逊品类自动化选品分析技能。
| 读取 06 计划/skillusagelog.jsonl,分析 Skill 使用情况,输出本周总结报告。
| 每次使用完某个 Skill 后,调用本 Skill 记录一条使用日志。
Pair Codex with Pluto.jl notebooks using MCP tools.
Implement the security design principle of secure system modification in [organization-defined].
> 本 skill 帮助你完成 Xilinx(AMD)完整设计流程,生成可直接运行的脚本和文件。
McKinsey顾问式问题解决系统。
当用户提供一段梦境文字素材、日记片段、或口述梦境内容,并希望生成视频时触发。
Improve a SKILL.md to pass the skill-creator standard (quick_validate, frontmatter audit, ≤500 lines) AND the asm-eval 85/8 floor.
ALWAYS use when writing code importing \"sqlite-vec\".
OpenClaw Skills 全方位安全审计工具,检测供应链投毒、Prompt注入、恶意代码模式、权限越权和依赖风险 基于《OpenClaw 极简安全实践指南》和《安全验证与攻防演练手册》的 Skill 安全审计工具。
| Turn every hard-earned lesson into a reusable improvement.
> from rclpy.node import Node from rclpy.qos import QoSProfile, ReliabilityPolicy, HistoryPolicy from std_msgs.msg import String class PerceptionNode(Node): def init(self):; runs on Node.js.
技能架构师向导与审查工具,整合官方 skill-creator 流程与内置合规检查。
管理 Claude Code、Codex 和 OpenClaw Skills 的安装、版本追踪和更新检查。
SolidWorks CAD 自动化技能,可通过 Python COM 接口与 OpenClaw / Codex / Claude 协作控制 Windows 上运行的 SolidWorks,用于零件建模、装配体、工程图、钣金、焊件、仿真、文件导出、自定义属性、设计表与配置管理;
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。
专业的 Dify 工作流 DSL/YML 文件生成器,根据用户业务需求自动生成完整的 Dify 工作流配置文件,支持各种节点类型和复杂工作流逻辑 专业的 Dify 工作流 DSL/YML 文件自动生成工具,基于对 86+ 实际工作流案例的深度学习,能够根据用户的业务需求自动生成符…
微信公众号文章聚合器。
本技能应在用户要求"数学建模"、"建模比赛"、"数模论文"、"数学建模竞赛"、"建模分析"、"建模求解"或提及数学建模相关任务时使用。
Design and conduct qualitative research using grounded theory and case studies A skill for designing and conducting rigorous qualitative research.
A skill that creates new Claude skills and automatically shares them on Slack using Rube for seamless team collaboration and skill discovery.
Brief description of what this skill enables.
Luamake 构建系统指南——用于当前项目的 `luamake` / `make.lua` / Ninja 生成流程。
Audit the agent's own skill library for malicious, misconfigured, or untrusted SKILL.md files.
A meta-skill that silently watches your workflows and automatically generates reusable Hermes skills from them.
ECharts数据可视化专家,能够根据数据和分析需求生成专业的ECharts图表配置。
Lifecycle guard.
> 使用Chrome DevTools MCP工具从知网采集数据。
Validates all interactive skills in this repo against the Agent Skills spec, project conventions, and structural requirements.
Validates all CI skills in this repo.
efinance 中国金融市场数据获取工具,封装 A 股行情、资金流向、龙虎榜、十大股东、业绩报表、基金净值持仓、可转债、期货等数据接口。
> 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.
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。
> 本 Skill 实现从「商品原始图片 + 卖点信息」到「完整电商套图」的一键生成流程: ① 上传商品图片(必须)+ 输入卖点信息(可选) ② AI 视觉分析:提取商品主体,智能生成卖点文案(可编辑) ③ 选择平台规范 + 套图类型(7种标准图) ④ AI 生成每张图的详细 P…
IDA Pro 逆向分析。
Convert CAD/BIM files to structured data.
AI-powered construction defect detection using computer vision.
Convert AutoCAD DWG files (1983-2026) to Excel databases using DwgExporter CLI.
跨学科AI论文写作助手,专为本科生/研究生论文写作提供全方位支持。
| 约束 | 规范 | |---|---| | 字体大小 | 正文字体小四(12pt)= \normalsize (TikZ) = font.size=13 (matplotlib);禁止 \small、\footnotesize | | 留白 | 不过大;
STM32 + FreeRTOS 嵌入式开发专家。
TAPD 敏捷研发管理平台集成。
微信聊天记录分析助手,用于查询、分析和导出本地微信数据库中的聊天数据。
阅读、分析并总结学术文献(PDF论文),生成结构化的文献概要笔记。
Senior Front-End Developer expertise in ReactJS, NextJS, JavaScript, TypeScript, HTML, CSS, and modern UI/UX frameworks You are a Senior Front-End Developer with expertise in ReactJS, NextJS, JavaScript, TypeScript, HTML, CSS, and modern UI/UX frameworks (TailwindCSS, Shadcn, Radix).
Automate HappyCapy skill creation by finding and adapting existing skills from anthropics/skills repository.
智能简历助手,通过五个AI代理提供全流程求职支持:(1)故事挖掘-发现经历亮点;(2)职位推荐-匹配合适岗位;(3)简历优化-针对JD定制内容;(4)模拟面试-实战演练与反馈;(5)能力提升-差距分析与计划。
> 按内容的结构形态归类——同一拓扑可能映射到多个图表类型: | 拓扑形态 | 识别信号 | 可表达的图表类型 | |---------|---------|----------------| | 线性序列 | A → B → C,单路径,步骤、阶段、流程 | 流程图(线性)、时…
钉钉 AI 表格(多维表)操作技能。
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.
Manage contacts, companies, deals, and pipeline with crm.cli — a headless CLI-first CRM backed by SQLite with a virtual filesystem interface…
| 你是一名具备中国法律全领域知识、擅长系统性检索与规范性文件整理的资深法律AI助手。
数学建模竞赛端到端工作流, 用于 CUMCM 国赛 / MCM·ICM 美赛 / 电工杯的选题、建模、求解、论文写作和终稿审核.
Generate complete academic survey papers using multi-LLM parallel outline generation, RAG-based subsection writing, citation validation, and local coherence enhancement.
Picking the wrong design strategy on a novel target wastes a GPU day.
Thorough target research before design prevents wasted compute and failed campaigns.
Protenix v1 is an AF3-class structure prediction model (368M parameters) for proteins, complexes, and protein-ligand systems.
You are an expert at designing de novo protein binders using PXDesign.
基于认知科学的源代码深度理解助手(中文改进版)。
Documenta projeto Power BI (PBIP) inteiro em markdown estruturado + HTML navegável (mini-site de doc).
论文格式自动化处理工具。
Use this skill whenever the user wants to create a tailored resume for a specific job posting.
Step-by-step guide for adding new pages to the Yew frontend This skill guides you through adding a new page to the Lightfriend Yew WebAssembly frontend.
| 根据用户提供的数据表信息(表名、字段定义),按照若依框架规范自动生成完整的 CRUD 代码,包括: 用户需要提供以下信息(可以通过对话澄清获取):
UI/UX design intelligence.
UI/UX design intelligence.
>- This skill helps AI agents create and manipulate Word documents programmatically.
Discover, browse, filter, and pay for x402-compatible API endpoints and MCP tools from the x402 Bazaar — the autonomous discovery layer for…
Main entry point for hierarchical task execution.
论文写作专家。
Build and maintain a git-based markdown wiki for software teams.
Fetch HarmonyOS docs through API first, then fallback to generic fetch.
中文学术论文去AI化检测与改写。
Pipeline for downloading academic paper full-text at scale.
Generate structured PR review comments using Claude Code agents and post them to GitHub.
Local-first AI agent with personality.
Essential tools for using JAX in machine learning and mathematical analysis, covering core concepts, transformations, ML specifics, control flow, and parallelism.
Control and interact with Kitty terminal windows - list windows, read output, send commands, and launch new terminals Control your Kitty terminal windows directly from the agent.
Implements Manifold-Constrained Hyper-Connections (mHC) to solve residual connection issues using Doubly Stochastic Matrices.
Search Israeli restaurants, check table availability, view menus, and get booking links on Ontopo.
Modern RDKit workflows for cheminformatics, including molecular fingerprints, drawing, and property calculations.
Path-conditional verification checklist (basic/standard/strict) with retry loop | 工具 | 类型 | 用法 | 调用方式 | |:---|:---|:---|:---| | Superpowers…
Lightweight voice MCP server with local Moonshine STT + Kokoro TTS Vox is a lightweight voice MCP server (~1,500 lines of Rust) providing local text-to-speech (Kokoro) and speech-to-text (Moonshine Base) via the MCP protocol.
Fast, semantic, and hybrid code search tool.
Scaffold a Next.js project with App Router, TypeScript, Tailwind CSS, and opinionated defaults.
Ollama API Documentation Comprehensive assistance with Ollama development - the local AI model runtime for running and interacting with large language models programmatically.
Defensive exploratory data analysis for scientific data (CSV, FASTA, etc.).
Comprehensive Cocos Creator 3.x development guide covering TypeScript scripting, component system, node hierarchy, scene management, resource loading, and event handling.
ACTIVATE THIS SKILL FOR ANY SHELL COMMAND OR FILE READ.
Use when editing files under `plugin/asicrs/`, `sdk/rust/`, or `server/sdk/v1/pb/` (which the asicrs build also consumes).
| 处理、生成、发送、转换、编辑 Word、Excel、PDF、Markdown 等文档的统一中心。
Build against the memories.sh SDK packages in application code.
Package map and reading order for Better Translate product skills.
Vben Admin 5.0 前端框架开发技能。
Entry point for documentation skills covering Upstash Search quick starts, core concepts, and TypeScript SDK usage.
Runbook for working in the AGILab repo (uv, Streamlit, run configs, packaging, troubleshooting).
Build type-safe applications with advanced TypeScript features, generics, and strict type checking.
公文写作助手。
NestJS backend development patterns.
Package text and images into valid ePub 3 e-books — chapters, TOC, cover images, and metadata for Kindle and Apple Books.
| 一站式学术研究工作流,覆盖从论文检索到最终演示的完整链路。
Universal validation and knowledge capture.
专利交底书撰写与专利检索助手。
Use when modern C++ features from C++11/14/17/20 including auto, lambdas, range-based loops, structured bindings, and concepts.
Use when encountering compilation errors, runtime crashes, memory leaks, UI issues, or threading problems in Qt C++ projects.
投标服务方案文档生成器。
| This skill covers modern ML-based causal inference methods: Causal Forests (GRF) for heterogeneous treatment effects, Double/Debiased Machine Learning (DML) for partially linear models, and LASSO-based variable selection.
Access a personal Slack workspace via session tokens (no app install required).
> Windows: C:\Users\<用户名>\Zotero\zotero.sqlite macOS: ~/Zotero/zotero.sqlite Linux: ~/Zotero/zotero.sqlite 配置文件: %APPDATA%\Zotero\Zotero\Pro…
> One install, one entry point, one query interface to all project state.
Guide frontend component design and code review using functional cohesion.
Fast, free web search using DuckDuckGo.
Extract transcripts, captions, or subtitles from YouTube videos.
Expose a workload for access.
MiniMax AI 音乐生成 Skill。
> 适用于 兼职/ 下所有需要交付 Word 报告、论文式分析说明、正式统计表或客户可见结果文档的任务。
Master creative specialized skill 38 with comprehensive coverage of concepts, implementation, optimization, and production best practices.
Docker 多服务部署最佳实践 - 遵循生产级 Dockerfile 和 Docker Compose 架构原则。
Access A-share (中国A股) market data via East Money's public HTTP APIs.
| 本技能提供同花顺 iFinD HTTP API 的完整函数参考,用于编写通过 HTTP 请求获取金融数据的 Python 代码。
| 创建符合学术出版标准的高质量图表。
获取7×24 新闻资讯,聚焦中国国内信息和国际热点。
微信公众号文章检索工具。
>- Use when this capability is needed.
> Three questions, in order, before writing any comment: offers none, flag it.
| Use when this capability is needed.
Add a chunking hook for a new or existing language in the ingest pipeline.
Add Telegram as a channel.
Principal AI Architect.
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 this capability is needed.
| Passthrough proxy for direct access to third-party APIs using managed auth connections.
>- 从多个公开中文财经/政策/社交来源抓取 A 股相关情报,输出结构化条目。
> Atheris is a coverage-guided Python fuzzer built on libFuzzer.
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.
Use when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app.
> Use when this capability is needed.
>- Use when this capability is needed.
Operate Azure SQL Database, Cosmos DB, and managed database services.
Comprehensive backend development guide for Node.js/Express/TypeScript microservices.
Auto-invoke when reviewing API routes, server logic, Express/Node.js code, or backend architecture.
Design banners for social media, ads, website heroes, creative assets, and print.
Design banners for social media, ads, website heroes, creative assets, and print.
Create native unit tests for Swift (iOS) and Kotlin (Android) code in the bcsc-core package.
> Take a benchmark the user envies — a founder, KOL, company, or product whose success looks suspiciously shiny — and produce a teardown tha…
>- Get the structured substrate the Bigdata.com MCP server doesn't hand over.
用于下载哔哩哔哩视频并支持截图功能的技能。
| Use when this capability is needed.
Refresh bQuery AI guidance and release metadata.
Brian API — natural language to executable Web3 transactions.
| Use when this capability is needed.
Direct GraphQL API integration with Bunny — the subscription billing and management platform.
Free OSINT reconnaissance to discover, validate, and build outreach-ready contact lists for businesses by region/industry.
Performs comprehensive C/C++ security review for memory corruption, integer overflows, race conditions, and platform-specific vulnerabilities.
Generate parametric 3D CAD models using OpenSCAD scripting language.
Scans Cairo/StarkNet smart contracts for 6 critical vulnerabilities including felt252 arithmetic overflow, L1-L2 messaging issues, address conversion problems, and signature replay.
> cargo-fuzz is the de facto choice for fuzzing Rust projects when using Cargo.
> Use when this capability is needed.
Python or Docker Use the upstream install or setup path that matches your environment: Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Python.
> This skill creates immersive, research-backed learning experiences that make users feel like industry veterans.
Scaffold/audit GitHub Actions CI/CD — Go/Rust/TS.
Analytical circuit design and simulation — voltage dividers, RC/RL/RLC filters, power calculations, impedance analysis, transfer functions.
|- This skill helps you build LLM-powered applications with Claude.
Delegate complex, multi-file coding tasks to an autonomous coding agent that can iterate and self-correct.
>- Search and recover content from Claude Code session history stored in active homes and explicitly registered long-term archives.
>- Claude Code fires hooks at tool-call boundaries.
| 这些词触发的本能是「砍行数」。
Diagnose and resolve Claude Code plugin and skill issues.
Analyze Claude Code and Claude Desktop Code token usage, cost, quota burn, model mix, cache read/write, and 5-hour block consumption using ccusage evidence.
> Quantitative portfolio toolkit for professional investors.
Generates professional animated CLI demos as GIFs using VHS terminal recordings.
Unix-composable CLI design patterns.
Refatorar código, refactoring, modernizar código legado, melhorar qualidade, atualizar padrões, converter componente Angular para standalone…
| Use when this capability is needed.
>- Supported languages: Python, JavaScript/TypeScript, Go, Java/Kotlin, C/C++, C#, Ruby, Swift.
Bridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both tools Use when this capability is needed.
Build Codex-native workflows for open-source maintenance.
name: coding-standards Use when this capability is needed.
Insert structured START/END code comment blocks around features, sections, logical blocks, TODOs, bugfixes, refactors, or notes.
> Use when this capability is needed.
Detects timing side-channel vulnerabilities in cryptographic code.
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.
Keeps examples/integrations/* demos aligned to the north-star (langgraph-python).
Scaffold a new Trinity-compatible Claude Code agent from scratch on any topic.
Create a new domain-specific instruction file when current coverage gaps require file-scoped guidance Use when this capability is needed.
Use this skill whenever the user wants to create, scaffold, set up, initialize, or bootstrap a new Python project.
| Use when this capability is needed.
Guidelines for introducing and using nullable reference types (NRT) and System.Diagnostics.CodeAnalysis nullable attributes in C# / .NET codebases.
| Use when this capability is needed.
Add new capabilities or modify nano-core behavior.
当用户要求下载地球科学数据(ERA5 再分析、OSI SAF 海冰产品等)时使用。
|- 对某个申万行业/东财板块做一次完整投研交付:Top N 涨幅标的 → 公告窗口检索 → 市场情绪判断 → Agent Team 对抗验证 → 综合报告。
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。
> Use when this capability is needed.
Initialize and configure local development tooling for TypeScript, Rust, and Python projects including monorepos.
Use the upstream install or setup path that matches your environment: Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Node.js.
Creates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes.
Your intelligent developer command center -- start here for any Python, wxPython, desktop app, NVDA addon, accessibility tool building, desktop accessibility, or general software engineering task.
Difftastic is a structural diff tool that compares files based on their syntax rather than line-by-line text.
Dioxus is a fullstack app framework for Rust that enables building cross-platform applications for web, desktop, and mobile from a single codebase.
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.
Django + FastAPI development.
Django + Celery async task patterns — configuration, task design, beat scheduling, retries, canvas workflows, monitoring, and testing.
> Use when this capability is needed.
>- Use when this capability is needed.
Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations.
Applies Django testing strategies with pytest-django, TDD, factory_boy, mocking, coverage, and DRF test patterns.
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
Convert documents to high-quality markdown with intelligent multi-tool orchestration and automatic DOCX post-processing.
>- Documentation goes wrong in two different ways, and they need different work.
Generate language-specific docstrings for C#, Java, Python, and TypeScript following industry standards (PEP 257, Javadoc, JSDoc, XML documentation) Use when this capability is needed.
Effective technical documentation strategies, API docs, README patterns, and doc generation workflows Use when this capability is needed.
>- Use when this capability is needed.
Domain-Driven Design patterns for TypeScript.
Diagnose and fix .NET HTTPS dev certificate trust issues on Linux.
| Use when this capability is needed.
Use Slopwatch to detect LLM reward hacking in .NET code changes.
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.
| Use when this capability is needed.
| Use when this capability is needed.
Analyzes smart contract codebases to identify state-changing entry points for security auditing.
TEMPLATE - Mobile development patterns.
> Use when this capability is needed.
Build, test, inspect, install, and deploy MCP servers with FastMCP in Python.
| Use when this capability is needed.
> Reconstruct broken line wrapping in Claude Code exported .txt files.
Design and simulate control systems — transfer functions, PID controllers, Bode plots, root locus, stability analysis, state-space modeling.
Run a complete engineering project through Forge's 8-phase autonomous pipeline.
Free local AI image and video processing toolkit with cloud AI generation.
One-command installer, credential configurator, and diagnostic layer for the full Gangtise (岗底斯投研) OpenAPI skill suite.
>- Prevent losing work in a tangle of branches/stashes/rebases, and recover it forensically when something already went sideways.
Compute PR statistics (total, merged, closed, avg merge time, top contributor) from GitHub API data using Python or jq.
> Use when this capability is needed.
抓取指定 GitHub 用户 Stars 下的所有项目,并生成标准化中文 Markdown 报告。
Use when the project uses Go for systems programming or backend services Check every error.
Write and review Go code with idiomatic project structure, errors, concurrency, testing, and performance guidance.
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.
Use when adding or configuring github.com/adlandh/echo-otel-middleware/v2 in a Go Echo application, or when writing examples for this middleware.
Use when adding or configuring github.com/adlandh/echo-zap-middleware/v2 in a Go Echo service.
This skill helps you learn Go (Golang) one topic per day.
>- Use when this capability is needed.
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.
Implement structured logging in Go with log/slog, including logger setup, common attributes, context propagation, redaction, and performance-minded patterns.
Write Go integration tests with testcontainers-go Use when this capability is needed.
Write idiomatic Go tests.
Troubleshoot Golang programs systematically - find and fix the root cause.
> Use when this capability is needed.
| Use when this capability is needed.
Start and troubleshoot the Hermes Agent Web UI (Vite + React frontend with Python backend) Use when this capability is needed.
Fetch and organize Hugging Face Daily Papers for a specified date.
Adapted from Hugging Face's dataset creator skill for FF-Terminal, Use when another skill is a better direct match for the task.
This skill enables you to create, manage, and publish datasets on the Hugging Face Hub with a focus on agricultural and farm-related data.
This skill enables you to manage, track, and analyze evaluation results for machine learning models used in agricultural applications.
This skill helps you publish and manage research papers on the Hugging Face Hub, enabling seamless integration with models, datasets, and reproducible research.
This skill enables publishing and managing research papers on the Use when the user request matches this skill's domain and capabilities.
> このスキルは AgentVillage プロジェクトの開発フローをガイドする。
> Ika is a parallel MPC signing network built on Sui.
Kubernetes NetworkPolicies provide pod-level network segmentation by defining ingress and egress rules that control Use when this capability is needed.
OpenD 安装助手。
>- Use when this capability is needed.
Add Opik tracing to an existing codebase.
| Use when this capability is needed.
Jujutsu (jj) is a powerful Git-compatible version control system that reimagines VCS workflows with automatic rebasing, first-class conflict tracking, and operation-log undo.
Kimi-K2.5 Writing Skill.
Kubernetes cluster management skill.
Kubernetes NetworkPolicies provide pod-level network segmentation by defining ingress and egress rules that control traffic flow between pods, namespaces, and external endpoints.
Implement Kubernetes network segmentation using Calico NetworkPolicy and GlobalNetworkPolicy for zero-trust pod-to-pod communication.
Use when building a Kubernetes Operator — custom controllers that reconcile CRD state.
Use when editing a DeepAgents project — adding tools, sub-agents, modifying the system prompt, choosing a filesystem backend, or composing e…
Use when productionising or deploying a LangChain / LangGraph / DeepAgents agent.
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.
Use when building or productionising any agent — adding retries, fallbacks, summarization, human-in-the-loop, PII redaction, call limits, or…
Use when creating a new LangChain / LangGraph / DeepAgents project from scratch.
Audit LangChain configuration and security Use when: "audit langchain, Use when this capability is needed.
Backup LangChain data and configuration Use when: "backup langchain, Use when this capability is needed.
Build LangChain chains, agents, and tool integrations with scaffolding, validation, and template generation.
Configure LangChain settings Use when: "configure langchain, langchain Use when this capability is needed.
Configure LangChain settings Use when: "configure langchain, langchain Use when this capability is needed.
Configure LangChain settings Use when: "configure langchain, langchain Use when this capability is needed.
Configure LangChain settings Use when: "configure langchain, langchain Use when this capability is needed.
Configure LangChain settings Use when: "configure langchain, langchain Use when this capability is needed.
Configure LangChain settings Use when: "configure langchain, langchain Use when this capability is needed.
Export data from LangChain Use when: "export langchain, langchain export, Use when this capability is needed.
Check LangChain service health Use when: "health langchain, langchain Use when this capability is needed.
Import data into LangChain Use when: "import langchain, langchain import, Use when this capability is needed.
Install LangChain service Use when: "install langchain, langchain install, Use when this capability is needed.
Install LangChain service Use when: "install langchain, langchain install, Use when this capability is needed.
Install LangChain service Use when: "install langchain, langchain install, Use when this capability is needed.
Install LangChain service Use when: "install langchain, langchain install, Use when this capability is needed.
Install LangChain service Use when: "install langchain, langchain install, Use when this capability is needed.
Install LangChain service Use when: "install langchain, langchain install, Use when this capability is needed.
View LangChain service logs Use when: "logs langchain, langchain logs, Use when this capability is needed.
Migrate data to/from LangChain Use when: "migrate langchain, langchain Use when this capability is needed.
Monitor LangChain status and health Use when: "monitor langchain, langchain Use when this capability is needed.
Monitor LangChain status and health Use when: "monitor langchain, langchain Use when this capability is needed.
Monitor LangChain status and health Use when: "monitor langchain, langchain Use when this capability is needed.
Monitor LangChain status and health Use when: "monitor langchain, langchain Use when this capability is needed.
Monitor LangChain status and health Use when: "monitor langchain, langchain Use when this capability is needed.
Monitor LangChain status and health Use when: "monitor langchain, langchain Use when this capability is needed.
Generate reports from LangChain Use when: "report langchain, langchain Use when this capability is needed.
Restart LangChain service Use when: "restart langchain, langchain restart, Use when this capability is needed.
Restore LangChain from backup Use when: "restore langchain, langchain Use when this capability is needed.
Set up and configure LangChain Use when: "setup langchain, langchain Use when this capability is needed.
Set up and configure LangChain Use when: "setup langchain, langchain Use when this capability is needed.
Set up and configure LangChain Use when: "setup langchain, langchain Use when this capability is needed.
Set up and configure LangChain Use when: "setup langchain, langchain Use when this capability is needed.
Set up and configure LangChain Use when: "setup langchain, langchain Use when this capability is needed.
Set up and configure LangChain Use when: "setup langchain, langchain Use when this capability is needed.
Sync data between LangChain and other services Use when: "sync langchain, Use when this capability is needed.
Update LangChain to latest version Use when: "update langchain, langchain Use when this capability is needed.
LangExtract by Google is a Python library for extracting structured information from unstructured text using LLMs with precise source grounding.
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…
> LibAFL is a modular fuzzing library that implements features from AFL-based fuzzers like AFL++.
> libFuzzer is an in-process, coverage-guided fuzzer that is part of the LLVM project.
| Use when this capability is needed.
>- Give this skill an endpoint (base_url + model + an API key in an env var) and it measures whether the endpoint actually works and whether…
帮用户搭一个金融投研专用 LLM Wiki(Karpathy 模式):纯 markdown 文件 + [[wikilink]] 互联 + LLM 维护,知识随用复利。
Private LLM and vision via LM Studio.
Multi-language code navigation via persistent LSP daemons.
Microsoft 365 Agents SDK for Python.
Design and implement a complete ML pipeline for: $ARGUMENTS Use when this capability is needed.
Workflow for publishing skills and agents to the dotnet-skills Claude Code marketplace.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools.
> Use when this capability is needed.
> Use when this capability is needed.
>- Use when this capability is needed.
Migrate test files from `as` type assertions to @total-typescript/shoehorn.
React Native mobile app development patterns with Expo 54, Tamagui, and expo-router.
>- Use when this capability is needed.
Use at session start and before running shell commands involving Python, Node.js, file search, or HTTP requests.
Guides C++ code toward modern idioms (C++20/23/26).
Write modern, high-performance C# code using records, pattern matching, value objects, async/await, Span<T>/Memory<T>, and best-practice API design patterns.
Configures Python projects with modern tooling (uv, ruff, ty).
Modern Python toolchain substrate.
> Use when this capability is needed.
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".
Configures mewt or muton mutation testing campaigns — scopes targets, tunes timeouts, and optimizes long-running runs.
hwpx 공문/기안문 양식을 첨부하면 주제에 맞춰 공문 내용을 자동 작성 mkdir -p hwpxwork && cd hwpxwork cp 원본.hwpx 원본.zip unzip -o 원본.zip -d original Contents/section0.xm…
Scaffold a new project with the full AI-assisted development workflow — Makefile targets, linter/formatter configs, pre-commit hooks, CLAUDE…
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。
Node.js + Express backend patterns.
>- Use when this capability is needed.
Use this skill when the user wants to start, stop, check, or list generated NoUI MCP servers, or connect a server to Claude Code.
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`.
Ollama runs large language models locally with a simple CLI and REST API.
Agent-driven cold-start onboarding.
onefetch is a Rust CLI tool that displays project information and code statistics for Git repositories directly in the terminal.
Run and audit OperatorOne Stage1 marketing SEO shadow experiments across input sync, context index, keyword graph, experiment synthesis, and Ready/Hold/Drop queueing.
>- Use when - "为什么甲虾能用 DeepSeek,乙虾不行?
Write real tests for a function or spec scenario — language-agnostic (TypeScript, Python, C++…).
Pair a remote AI agent with your browser.
处理 PDF 文件:读取、修改、合并、抽内容都行。
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms.
Convert markdown files to professional PDF documents with proper Chinese font support, theme system, and visual self-check.
Turn a PDF into a single, self-contained, readable HTML file — images, tables, charts and reading order preserved — and optionally translate…
> 从新浪财经免费公开接口抓取 A 股医药板块实时行情,分析后通过飞书发送日报。
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.
Initialize a brand-new project from scratch with a default full-stack scaffold (Rust core + React Router 7 portal + Docker + Kubernetes).
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`.
Configures and runs LLM evaluation using Promptfoo framework.
> Use when this capability is needed.
How to use the PyMAPDL command-line interface to start, stop, list, and execute commands on MAPDL instances from a terminal.
Python test generation assistant Use when this capability is needed.
Requirements and caveats from upstream: Basic usage or getting-started notes: <!-- tomevault:4.0:skill_md:2026-05-22 -->; runs on Python >=3.10.
When the user wants to design, implement, debug, or scale Python API tests using pytest + requests/httpx.
Deploy a Python project to the target environment.
> Use when this capability is needed.
Prepare Python projects with professional structure, documentation, and tooling.
Quickly analyzes Python repositories to understand their purpose, structure, and setup requirements.
This skill should be used when establishing comprehensive QA testing processes for any software project.
Generate strongly-typed models and serializers from JSON, JSON Schema, TypeScript, and GraphQL queries in 20+ programming languages.
Build reactive/event-driven C# with R3 (Cysharp's modern reimplementation of Reactive Extensions).
> Use when this capability is needed.
Build and manage React Native/Expo mobile apps including project setup, development workflows, and platform-specific guidance.
>- Pull a Claude.ai web conversation into a full, structured transcript — every message and every tool call, not just what is currently on s…
| Use when this capability is needed.
Universal release workflow supporting any project type with multi-language changelog.
Safely package codebases with repomix by automatically detecting and removing hardcoded credentials before packing.
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo.
| Use when this capability is needed.
| +-- .pdf --> python parse.py --input resume.pdf --output resume.md | +-- .docx/.doc --> python parse.py --input resume.docx --output resum…
Pre-landing PR review.
Execute and orchestrate external CLI-based agents to delegate subtasks, obtain specialized outputs, or compose multi-agent workflows.
Rust com clippy warnings-as-errors, sem unwrap fora de testes Use when this capability is needed.
>- Use when this capability is needed.
Use this skill when the user asks about rust-libp2p, Rust libp2p, libp2p::SwarmBuilder, NetworkBehaviour, ConnectionHandler, Transport, Peer…
Set up Rust quality gates (cargo check/build, clippy, rustfmt, dead code, unused deps via cargo-machete, doc build, tests) in any Rust repo, wired through `prek` (pre-commit reimagined) with a `check.sh` orchestrator underneath.
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.
| Use when this capability is needed.
One-file-at-a-time Rust quality pass for Citum, using jcodemunch to target the highest-value cleanup.
Static Application Security Testing (SAST) for multi-language codebases.
>- Use when this capability is needed.
>- Use when this capability is needed.
Perform language and framework specific security best-practice reviews and suggest improvements.
>- Run a Semgrep scan with automatic language detection, parallel execution, and merged SARIF output.
>- Use when this capability is needed.
Comprehensive software architecture skill for designing scalable, maintainable systems across web, mobile, and backend stacks (React, Next.js, Node/Express, React Native, Swift, Kotlin, Flutter, Postgres, GraphQL, Go, Python).
This skill should be used when the user asks to "design REST APIs", "optimize database queries", "implement authentication", "build microservices", "review backend code", "set up GraphQL", "handle database migrations", or "load test APIs".
| Use when this capability is needed.
Test, analyze, or start Docker for the server project Use when this capability is needed.
| Use when this capability is needed.
| Use when this capability is needed.
Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy.
Wire dependency-cruiser into a TypeScript repo so each package is a deep module, with implementation hidden in subfolders and reachable only through its entry-point files.
This skill provides comprehensive Shopify store management capabilities through the Shopify Admin GraphQL API.
Audits a Claude Code / Agent SDK skill (or folder of skills) against 10 QA Use when this capability is needed.
Reviews and improves Claude Code skills against official best practices.
Knowledge and utilities for creating animated GIFs optimized for Slack.
Knowledge and utilities for creating animated GIFs optimized for Slack.
Scans Solana programs for 6 critical vulnerabilities including arbitrary CPI, improper PDA validation, missing signer/ownership checks, and sysvar spoofing.
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 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…
Use this skill when the agent is designing schemas, reviewing migrations, tuning queries, modeling NoSQL access patterns, configuring replic…
Load a flat dataset (CSV / Parquet / JSON / Excel) into a SQL database.
Build SQL database integrations with SQLModel for FastAPI projects.
Perform real structural engineering calculations — beam deflection, stress analysis, buckling, safety factors.
Scans Substrate/Polkadot pallets for 7 critical vulnerabilities including arithmetic overflow, panic DoS, incorrect weights, and bad origin checks.
| Use when this capability is needed.
Complete Telegram bot creation for AI agents and pipelines.
Terraform CLI 安装与初始化技能。
Terraform IaC management skill.
>- 「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。
Remote-control tmux sessions for interactive CLIs by sending Use when the user request matches this skill's domain and capabilities.
>- 适用于 TokenKey fork of sub2api。
When no existing engineering tool fits the problem, the fabricator creates a new one from scratch.
Activate when user asks to sync, push, or publish local Tracecat MCP server code or Claude Code skills to their GitHub repositories Use when this capability is needed.
>- Use when | Required reading |.
Fetch Twitter/X post content including long-form Articles with full images and metadata.
TypeScript type safety, async correctness, error handling, and immutability patterns.
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.
Mobile UI patterns - React Native, iOS/Android, touch targets Use when this capability is needed.
World-class UI для Veda на Untitled UI React v8.
Language-specific verification for Python, TypeScript/JavaScript, and Go.
Implement features and fix bugs for the vfs-s3 project.
This skill should be used when comparing two videos to analyze compression results or quality differences.
|- Use when this capability is needed.
> Use when this capability is needed.
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).
Toolkit for interacting with and testing local web applications using Playwright.
Toolkit for interacting with and testing local web applications using Playwright.
提供企业微信智能表格添加记录的正确操作方法,包括不同数据类型的处理格式。
Uses the W&B Python SDK and Public API to stream live training metrics, system stats, and gradients from active runs.
When Whisper (CLI or Python) gets stuck on video files during transcription — output dir stays empty, process runs at low CPU/memory with no…
> Wycheproof is an extensive collection of test vectors designed to verify the correctness of cryptographic implementations and test against known attacks.
Use this skill any time a spreadsheet file is the primary input or output.
> Write detection rules that catch malware without drowning in false positives.
Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification.