Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
roster-party
Parallel team composition analysis using G-1 PERSONNEL. Deploy 6 probes for comprehensive roster assessment before complex task assembly.
majiayu000/claude-skill-registry 163
-
api-documenter
Master API documentation with OpenAPI 3.1, AI-powered tools, and modern developer experience practices. Create interactive docs, generate SDKs, and build comprehensive developer portals. Use PROACTIVELY for API documentation or developer portal creation.
majiayu000/claude-skill-registry 163
-
value-messaging
Use to map pricing/packaging tiers to tailored value pillars, proof, and objection handling.
majiayu000/claude-skill-registry 163
-
migrate
Migration workflow - research → analyze → plan → implement → review
majiayu000/claude-skill-registry 163
-
subagent-testing
TDD-style testing methodology for skills using fresh subagent instances
to prevent priming bias and validate skill effectiveness.
Triggers: test skill, validate skill, skill testing, subagent testing,
fresh instance testing, TDD for skills, skill validation
Use when: validating skill improvements, testing skill effectiveness,
preventing priming bias, measuring skill impact on behavior
DO NOT use when: implementing skills (use skill-authoring instead),
creating hooks (use hook-authoring instead)
majiayu000/claude-skill-registry 163
-
gtasks-todo-manager
Manages to-do items across multiple Google accounts using the Google Tasks API. Use when the user needs to create, update, complete, or organize tasks in Google Tasks, manage task lists, or view tasks across multiple Google accounts. Supports personal Gmail, Google Workspace, and organization-provisioned accounts with secure OAuth authentication.
majiayu000/claude-skill-registry 163
-
requirements-reviewer
Copilot agent that assists with systematic requirements review using Fagan Inspection and Perspective-Based Reading (PBR) techniques
Trigger terms: requirements review, specification review, SRS review, Fagan inspection, perspective-based review, requirements validation, requirements verification, quality gate review, formal inspection, requirements checklist
Use when: User requests involve requirements review, validation, or inspection tasks.
majiayu000/claude-skill-registry 163
-
coding-style
Coding style, testing, and PR guidelines for the Kubb ecosystem. Use when writing or reviewing code for the Kubb ecosystem.
majiayu000/claude-skill-registry 163
-
boundary-value-problems
Problem-solving strategies for boundary value problems in odes pdes
majiayu000/claude-skill-registry 163
-
naming
命名规范 / Naming conventions。在创建类、函数、变量，或重命名、检查命名时使用。核心原则：简洁优先，上下文消歧义，类型提示已提供足够信息。Use when naming classes/functions/variables, renaming code, or reviewing names. Prioritizes brevity over self-documentation.
majiayu000/claude-skill-registry 163
-
executive-ebr-kit
Template pack for executive business reviews with outcomes, risks, and asks.
majiayu000/claude-skill-registry 163
-
create-mongodb-repository
Create MongoDB repository implementation for production database. Use when implementing repository interface with MongoDB, setting up document mapping, creating indexes, or connecting to real database. Triggers on "mongodb repository", "mongo repository", "production repository", "database repository".
majiayu000/claude-skill-registry 163
-
clarify-skill
澄清用户意图的 Skill。当用户给出模糊想法、需要脑暴、需要讨论设计时触发。触发词：帮我想想、我想做、讨论一下、澄清、clarify。
majiayu000/claude-skill-registry 163
-
meeting-notes
Generate structured meeting notes with action items, decisions, and summaries from transcripts. Use when documenting meetings or creating meeting summaries.
majiayu000/claude-skill-registry 163
-
agent-tool
Define tools for the support agent. Use when adding new capabilities like refund processing, license transfer, knowledge lookup, or any agent action.
majiayu000/claude-skill-registry 163
-
ia-presenter-themes
This skill should be used when creating, modifying, or troubleshooting custom themes for iA Presenter.
majiayu000/claude-skill-registry 163
-
Brand Partnership Negotiator
Negotiate and structure brand partnerships and co-marketing deals
majiayu000/claude-skill-registry 163
-
python-uv-project-setup
Use when initializing a Python project or script, adding dependencies, or running commands with uv, especially to avoid pip install and direct python/pytest usage.
majiayu000/claude-skill-registry 163
-
literature-search
Search and retrieve academic literature from multiple databases.
LOAD THIS SKILL WHEN: User says "搜尋文獻", "search literature", "find papers", "PubMed", "學術搜尋" | needs to find research articles | starting literature review.
CAPABILITIES: PubMed search, MeSH term expansion, citation metrics, batch retrieval.
majiayu000/claude-skill-registry 163
-
Upgrades
Track PAI upgrade opportunities. USE WHEN upgrades, improvement tracking. SkillSearch('upgrades') for docs.
majiayu000/claude-skill-registry 163
-
debug
Systematic bug investigation and resolution workflow with root cause analysis.
majiayu000/claude-skill-registry 163
-
agent-board-cli
Command-line task management tool for AI coding agents and humans. Provides local SQLite-based task boards for tracking work items, checklists, and comments without requiring an external API.
Use this skill when:
- Managing multi-step coding tasks
- Tracking progress on complex implementations
- Breaking down work into checkable subtasks
- Documenting decisions and progress via comments
- Coordinating work across agent sessions
majiayu000/claude-skill-registry 163
-
heap-dump-analyzer
Analyze heap dump analyzer operations. Auto-activating skill for Performance Testing.
Triggers on: heap dump analyzer, heap dump analyzer
Part of the Performance Testing skill category. Use when analyzing or auditing heap dump analyzer. Trigger with phrases like "heap dump analyzer", "heap analyzer", "analyze heap dump r".
majiayu000/claude-skill-registry 163
-
openai-sdk
OpenAI official SDK usage (Python, Node.js). Use when: writing code that calls OpenAI API,
implementing chat/embeddings/images/audio features, handling streaming responses,
async patterns, error handling with SDK. For raw HTTP/REST calls, see `openai-api` skill.
majiayu000/claude-skill-registry 163