AI Skills Hub - Browse 180,000+ Agent Skills

skill_id: "extract-trusted-sources" name: "Extract Trusted Sources" command: "" parameters: {} created_at: "2026-01-30T00:00:00+00:00" ---

Fix specific issues by delegating to background Claude Code

Implement feature via background Claude Code session

Launch Codex CLI for test creation and execution for NDI HX3 app

Keep the controller looping and progressing work without interruption.

Stratège de l'expérience client internationale (B2B & B2C).

Use this skill when you are asked to work on a new or existing CDS React component in packages/mobile/ or packages/web/

Activates Mr. Krabs persona for crypto monitoring and aggressive greedy advice.

Test-Driven Development workflow. Use when user explicitly wants TDD or when implementing API/logic with existing test framework.

Master Python 3.12+ with modern features, async programming, performance optimization, and production-ready practices. Expert in the latest Python ecosystem including uv, ruff, pydantic, and FastAPI. Use PROACTIVELY for Python development, optimization, or advanced Python patterns.

Iteratively improve skill frontmatter compliance using the Ralph loop pattern. USE FOR: run sensei, sensei help, improve skill, fix frontmatter, skill compliance, frontmatter audit, improve triggers, add anti-triggers, batch skill improvement, check skill tokens. DO NOT USE FOR: creating new skills (use skill-authoring), writing skill content, token optimization only (use markdown-token-optimizer), or non-frontmatter changes.

Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents

Update GSD to latest version with changelog display

Add phase to end of current milestone in roadmap

Research how to implement a phase (standalone - usually use /gsd:plan-phase instead)

Show available GSD commands and usage guide

Insert urgent work as decimal phase (e.g., 72.1) between existing phases

Archive completed milestone and prepare for next version

name: TaiChiNiBridge description: TaiChi Training & Ni Haixia Lifestyle Companion triggers: ["TaiChi", "NiHaixia", "training", "diet", "lifestyle"] permissions: api:call_external, read:logs, write:reminders

Expert Python developer specializing in modern Python 3.11+ development with deep expertise in type safety, async programming, data science, and web frameworks. Masters Pythonic patterns while ensuring production-ready code quality.

<use_interesting_fonts> Typography instantly signals quality. Avoid using boring, generic fonts.

【必須】Azure Storage、Blob、File、Queue、Tableに関する質問への応答形式。応答時に必ず参照してJSON形式で回答すること。

Skill pour développer la plateforme de streaming vidéo en direct avec SolidJS, Bun, tRPC, et WebAssembly+Rust.

示例技能，用于演示 Agent Skills。当用户提到「示例」「example」「技能演示」或需要运行示例脚本时使用。

This skill should be used when the user asks to "generate technical documentation from requirements", "extract technologies from requirements document", "create tech research documents", "analyze requirements for tech stack", or needs to identify and document technologies specified in a requirements document.

Install and use the SuperMemory MCP server for managing memories.

name: refactor-pro

Alibaba Bailian text generation (通义千问/第三方文本大模型). Use for text generation/chat/completion and Qwen API usage.

A meta-skill that allows Claude to generate and install new custom skills for the user.

Problem-solving strategies for graph algorithms in graph number theory

Problem-solving strategies for convex optimization in optimization

Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.

This guide shows how to implement skills in the SDK. For conceptual overview, see Skills Overview.

Technical Writer - Technical Documentation Specialist + Knowledge Curator

Critical validation workflow that assesses PRD, Architecture, and Epics & Stories for completeness and alignment before implementation. Uses adversarial review approach to find gaps and issues.

Cynically review content and produce findings

Product Manager - Product Manager specializing in collaborative PRD creation through user interviews, requirement discovery, and stakeholder alignment.

Disruptive Innovation Oracle - Business Model Innovator + Strategic Disruption Expert

Scrum Master - Technical Scrum Master + Story Preparation Specialist

Guide human-centered design processes using empathy-driven methodologies. This workflow walks through the design thinking phases - Empathize, Define, Ideate, Prototype, and Test - to create solutions deeply rooted in user needs.

Developer Agent - Senior Software Engineer

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for 簡報s, 文檔ation, or social media posts.

Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.

Analyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates relevant learning resources from HackerNews, and automatically sends a personalized growth report to your Slack DMs.

Assists in writing high-quality content by conducting research, adding citations, improving hooks, iterating on outlines, and providing real-time feedback on each section. Transforms your writing 處理 from solo effort to collaborative partnership.

Advanced standard for creating elite-level technical reports, security assessments, and executive summaries.

Hexagonal Architecture implementation through defined interfaces.

개발 시작 - 모든 핵심 문서를 로드합니다

Add to git commit with an appropriate commit message

Engineering orchestrator. Design system architecture, write full-stack code, and manage technical implementation. Use for 'Build X', 'Architect Y', or 'Refactor Z'.

Unsafe example skill (Gatekeeper/quarantine bypass).

Standard de référence pour la gestion de Git. Règles de sécurité, workflows atomiques, conventions de commit et bonnes pratiques de configuration.

A suite of vector-powered research skills for solving complex transit scenarios (Accessibility, Vibe Matching, Last Mile).

Security-fokussierter Modus. Prüft auf OWASP Top 10 (Injection, XSS, Broken Auth), Hardcoded Secrets und unsichere Dependencies. Denkt wie ein Angreifer.

No description available

No description available

Red team attack tactics, techniques, and procedures (TTPs) based on MITRE ATT&CK framework. Covers reconnaissance, initial access, privilege escalation, lateral movement, and exfiltration.

Always use context7 when I need code generation, setup or configuration steps, or library/API documentation. This means you should automatically use the Context7 MCP tools to resolve library id and get library docs without me having to explicitly ask.

Provides domain knowledge and rules for Todo task management systems.

Model development practices including model selection, training pipelines, hyperparameter tuning, evaluation, and model selection strategies.

绿植园艺营销日历工具。查询每日营销热点、节气、节日，并提供内容建议。支持生成新年度营销日历。

knowledge-management 작업을 수행하기 위한 한국어 운영 가이드

journal-entry-prep 작업을 수행하기 위한 한국어 운영 가이드

variance-analysis 작업을 수행하기 위한 한국어 운영 가이드

audit-support 작업을 수행하기 위한 한국어 운영 가이드

statistical-analysis 작업을 수행하기 위한 한국어 운영 가이드

data-visualization 작업을 수행하기 위한 한국어 운영 가이드

data-exploration 작업을 수행하기 위한 한국어 운영 가이드

Commit and push

Central coordinator for all meta-skills, managing execution flow and improvement cycles

Automated bug reproduction, fixing, and deployment workflow for Google Antigravity.

Master containerization best practices for building, deploying, and managing secure, efficient containerized applications.

Conduct systematic performance testing to validate system capacity, scalability, and stability under various load conditions.

Advanced skill for consolidating periodic learning activities, synthesizing insights from multiple sources, and creating comprehensive evolution summaries for AI agent development. This skill focuses on analyzing memory files, work logs, and external research to generate structured knowledge that enhances the AI agent's capabilities.

Comprehensive knowledge and best practices for developing AI agents and their skills in 2026. Covers modern development techniques, skill architecture, and evolution strategies.

3. **Synthesis** - Combine disparate pieces of information into coherent narratives - Draw connections between different learning domains - Abstract general principles from specific examples - Formulate insights based on accumulated experience

AI agent capability for continuous learning, self-improvement, and adaptive skill acquisition from experiences and external resources.

此技能适用于： - 大规模AI代理系统的技能管理 - 多样化技能集合的协调与优化 - AI代理能力的动态扩展和调整 - 技能市场的运营和维护 - 企业级AI代理平台的运维

Recommend the right technology stack for your MVP.

Enable medium extended thinking (10k token budget)

Enable maximum extended thinking (32k token budget)

Use when designing systems, structuring projects, or making architectural decisions. Covers system design patterns, project structure, API architecture, state management architecture, and infrastructure decisions. This is a CORPORATE STANDARD and takes precedence over all other skills.

Summarizes textbook chapters with key points and takeaways

Follow project-wide development conventions for file organization, version control, documentation, and dependency management. Use this skill when organizing project directories and files, writing README documentation, creating commit messages, working with git branches, managing pull requests, configuring environment variables, handling secrets and API keys, managing project dependencies, setting up feature flags, maintaining changelogs, defining testing requirements, establishing code review processes, or structuring the overall project architecture. Apply this skill when setting up new projects, refactoring project structure, working with version control, managing configuration files, or ensuring the project follows consistent organizational patterns and best practices.

Write clean, consistent code following established naming conventions, formatting rules, and the DRY principle across all files. Use this skill when writing any code in any file, naming variables and functions, structuring code logic, formatting code with consistent indentation, choosing descriptive names that reveal intent, keeping functions small and focused, removing dead code and unused imports, extracting common logic into reusable functions, maintaining consistent code style across the codebase, configuring linters and formatters, or refactoring code for better readability. Apply this skill universally across all coding tasks to ensure code quality, maintainability, and consistency with project standards. This skill should be active for all file types including TypeScript, JavaScript, Python, Ruby, Java, Go, and other programming languages.

Verify that the Visions Skills architecture is functioning correctly.

Create handoff document and pause work cleanly (deprecated, archived for reference)

Audit subagent configuration for role definition, prompt quality, tool selection, XML structure compliance, and effectiveness

No description available

No description available

코드베이스를 분석하여 CLAUDE.md 초기화. 프로젝트 문서화, 아키텍처 개요, 코딩 표준 생성

专为 ZBeta 项目设计的学习与开发指南，整合 GAS、ALS 动画、Common UI 技术栈，对标《No Rest for the Wicked》系统架构

Comprehensive C# code review following .NET best practices

Battle-tested personal writing system for professional social media content. Generates authentic, grounded posts that sound like a real human sharing insights—not a marketing bot.

为 FastAPI 文档中的代码添加中文注释

NLP分野の重要概念・キーワード辞書。メモへのリンクとファクトチェック状態を管理

This Nuxt skill ensures that the codebase is syntactically correct and adheres to lint rules

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

Use when acting as the project lead/PM to break a spec into issues, define acceptance criteria, and coordinate work.

> Utilisez ce template pour documenter une nouvelle feature AVANT de la développer. > Ce document guidera l'agent IA (ou les développeurs) dans l'implémentation.