Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
standards-tests
Write focused tests for core user flows with clear names, behavior-focused assertions, and mocked external dependencies. Apply when creating unit tests, integration tests, or implementing TDD.
majiayu000/claude-skill-registry 163
-
co2-carbon-footprint
Calculate CO2 emissions and carbon footprint from BIM model data. Analyze embodied carbon by material, element, and building system.
majiayu000/claude-skill-registry 163
-
google-structured-data
Google Search structured data implementation - Schema.org markup for rich results, JSON-LD templates, JavaScript generation, and SEO best practices
majiayu000/claude-skill-registry 163
-
worksnaps-automation
Automate Worksnaps tasks via Rube MCP (Composio). Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
3d-games
3D game development principles. Rendering, shaders, physics, cameras.
majiayu000/claude-skill-registry 163
-
documentation
Technical documentation generation and maintenance. Creates API docs, code comments, READMEs, and changelogs. Use when documenting code, APIs, or creating project documentation.
majiayu000/claude-skill-registry 163
-
product-marketing-context
（中文）When the user wants to create or update their product marketing context document. Also use when the user mentions 'product context,' 'marketing context,' 'set up context,' 'positioning,' or wants to avoid repeating foundational information across marketing tasks. Creates `.claude/product-marketing-context.md` that other marketing skills reference.
majiayu000/claude-skill-registry 163
-
hypothesis-generation
Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.
majiayu000/claude-skill-registry 163
-
ac-tdd-runner
Run TDD cycle for feature implementation. Use when implementing features with RED-GREEN-REFACTOR, running test-driven development, automating TDD workflow, or ensuring test-first development.
majiayu000/claude-skill-registry 163
-
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
majiayu000/claude-skill-registry 163
-
humanizer_academic
学術・医療文書を AI らしい硬さから自然な英語へ人間化するスキル。Use when 論文、研究計画書、学会抄録、医療文書、カバーレターの英文を自然化したい場面。キーワード: humanize, academic writing, medical writing, manuscript polish.
majiayu000/claude-skill-registry 163
-
neverbounce-automation
Automate Neverbounce tasks via Rube MCP (Composio). Always search tools first for current schemas.
majiayu000/claude-skill-registry 163
-
python-packaging
Comprehensive guide to creating, structuring, and distributing Python packages using modern packaging tools, pyproject.toml, and publishing to PyPI.
majiayu000/claude-skill-registry 163
-
mcp-doc-scan
Scan project and report documentation coverage. Finds undocumented directories, stale manifest entries, and prioritized recommendations.
majiayu000/claude-skill-registry 163
-
aitask-reviewguide-merge
Compare two similar review guide files and merge, split, or keep separate.
majiayu000/claude-skill-registry 163
-
bmad-technical-research
Conduct technical research on technologies and architecture. Use when the user says "create a technical research report on [topic]".
majiayu000/claude-skill-registry 163
-
agent-code-goal-planner
Agent skill for code-goal-planner - invoke with $agent-code-goal-planner
majiayu000/claude-skill-registry 163
-
outreach-sequence-builder
Use when creating outreach sequences, writing cold email campaigns, building multi-channel cadences, designing follow-up flows, or crafting signal-triggered messages. Triggers: 'build an outreach sequence', 'write a cold email sequence', 'create a cadence', 'outreach for [signal]', 'email sequence', 'follow-up sequence', 'multi-channel outreach'.
majiayu000/claude-skill-registry 163
-
discord-joeyjoziah-investment-analysis-
majiayu000/claude-skill-registry 163
-
tdd-workflow
当用户要求TDD、测试驱动开发、先写测试或提到红绿重构时使用。
majiayu000/claude-skill-registry 163
-
research-refine-pipeline
Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.
majiayu000/claude-skill-registry 163
-
legal-advisor
Draft privacy policies, terms of service, disclaimers, and legal notices. Creates GDPR-compliant texts, cookie policies, and data processing agreements. Use PROACTIVELY for legal documentation, compliance texts, or regulatory requirements.
majiayu000/claude-skill-registry 163
-
architecture-patterns
Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use when architecting complex backend systems or refactoring existing applications for better maintainability.
majiayu000/claude-skill-registry 163
-
browser-use
Browser automation using Playwright MCP. Navigate websites, fill forms, click elements, take screenshots, and extract data. Use when tasks require web browsing, form submission, web scraping, UI testing, or any browser interaction.
majiayu000/claude-skill-registry 163