Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
leta
Fast semantic code navigation via LSP. Load FIRST before ANY code task - even 'simple' ones. Trigger scenarios: (1) fixing lint/type/pyright/mypy warnings or errors, (2) fixing reportAny/reportUnknownType/Any type errors, (3) adding type annotations, (4) refactoring or modifying code, (5) finding where a function/class/symbol is defined, (6) finding where a symbol is used/referenced/imported, (7) understanding what a function calls or what calls it, (8) exploring unfamiliar code or understanding architecture, (9) renaming symbols across codebase, (10) finding interface/protocol implementations, (11) ANY task where you'd use ripgrep to find code or read-file to view a function. Use `leta show SYMBOL` instead of read-file, `leta refs SYMBOL` instead of ripgrep for usages, `leta grep PATTERN` instead of ripgrep for definitions, `leta files` instead of list-directory.
majiayu000/claude-skill-registry 163
-
cabinet-configurator
Cabinet Editor web application development skill. Use when working on Cabinet Editor codebase - a 2D/3D furniture configurator built with Canvas API and Three.js. Covers architecture (Panel and Drawer classes, connections system, virtual panels), coordinate systems, panel/drawer movement logic, cabinet dimension changes (width/height/depth/base), 3D rendering with rank-based depth, ribs system, and drawer box calculations. Essential for debugging, adding features, or understanding how panels/drawers interact with cabinet sizing.
majiayu000/claude-skill-registry 163
-
workflow-methodology
Core development methodology for claude-flow. Enforces TDD (test-first), systematic debugging (4-phase), and verification gates. Use when starting any development task, fixing bugs, or completing features.
majiayu000/claude-skill-registry 163
-
frontend-debug
Autonomously debug frontend issues through empirical browser observation using Chrome DevTools MCP. This skill should be used when debugging UI/UX issues, visual bugs, interaction failures, console errors, or network problems in web applications. Provides systematic 6-phase debugging workflow with GitHub integration, automated verification, and knowledge retention.
majiayu000/claude-skill-registry 163
-
disambiguate-requirements
Break vague requirements into precise business rules (BR-*), constraints (C-*), and formulas (F-*) for code generation. Orchestrates extraction of BR-*, C-*, F-* from REQ-*. Use after requirement-extraction to enable autogeneration.
majiayu000/claude-skill-registry 163
-
matchms
Mass spectrometry analysis. Process mzML/MGF/MSP, spectral similarity (cosine, modified cosine), metadata harmonization, compound ID, for metabolomics and MS data processing.
majiayu000/claude-skill-registry 163
-
managing-docker
Manages Docker development environments. Use for containerized projects, Docker operations, Compose management, and environment setup.
majiayu000/claude-skill-registry 163
-
ci-doctor
Diagnose and fix CI/CD pipeline failures, test errors, GitHub Actions issues, and code scanning alerts.
Use when:
- CI pipeline fails (red build)
- GitHub Actions workflow errors
- Test failures in CI (Vitest, Playwright)
- TypeScript/lint errors blocking builds
- GitHub notifications about failed checks
- "CI is red" or "build failed" or "tests failing"
- Supabase/OpenAPI type generation failures
- Pre-commit hook failures
- GitHub Code Scanning alerts (CodeQL)
- Security vulnerabilities in code
- /security/code-scanning alerts
Triggers: "fix ci", "ci failed", "build broken", "tests failing in ci", "github actions error", "pipeline red", "check failed", "code scanning", "codeql", "security alert", "vulnerability"
majiayu000/claude-skill-registry 163
-
swagger-doc-creator
Swagger Doc Creator - Auto-activating skill for API Development.
Triggers on: swagger doc creator, swagger doc creator
Part of the API Development skill category.
majiayu000/claude-skill-registry 163
-
results-interpretation
Interpret statistical results correctly and comprehensively. Use when: (1) Writing results sections, (2) Discussing findings, (3) Avoiding common misinterpretations, (4) Reporting effect sizes and confidence intervals.
majiayu000/claude-skill-registry 163
-
pr-descriptions
Use when gh pr edit --body fails silently or returns no error but doesn't persist changes - provides fallback pattern using GitHub REST API directly for reliable PR description updates
majiayu000/claude-skill-registry 163
-
hpe-copyright
Check, add, or fix HPE copyright headers in source files. Use this skill when (1) Adding copyright headers to new files, (2) Checking if files have valid copyright headers, (3) Updating outdated copyright years, (4) Preparing code for CI that enforces copyright headers, (5) User mentions "copyright", "HPE header", or "copyright check". Format is "Copyright YYYY-YYYY Hewlett Packard Enterprise Development LP" as a comment on the first line.
majiayu000/claude-skill-registry 163
-
huggingface
Import GGUF models from HuggingFace into Ollama. Pull models directly
using the hf.co/ prefix, track download progress, and use imported
models for inference.
majiayu000/claude-skill-registry 163
-
worktree-task
使用 git worktree + 背景代理会话管理大型任务（默认启动 Claude Code；可用 --codex 快速切到 Codex CLI，或通过 --agent-cmd 指定任意命令）。适合用户希望在不阻塞当前会话的情况下执行大型或多步骤任务。
majiayu000/claude-skill-registry 163
-
posting-bitwarden-review-comments
Formats and posts GitHub PR inline review comments following Bitwarden engineering standards. Use when posting code-specific findings. For summary comments, invoke posting-review-summary skill.
majiayu000/claude-skill-registry 163
-
python-fastapi
Python FastAPI development with uv package manager, modular project structure, SQLAlchemy ORM, and production-ready patterns.
majiayu000/claude-skill-registry 163
-
cpp14-code-review
AUTOSAR C++14およびCERT C++コーディング規約に準拠したC++14コードレビュー。安全性重視のC++システムのコードレビュー、セキュリティ監査、品質評価、静的解析ツール設定を行う際に使用。
majiayu000/claude-skill-registry 163
-
using-elixir-skills
Use when writing Elixir, Phoenix, or OTP code - routes to the correct thinking skill before any code is written
majiayu000/claude-skill-registry 163
-
openai-agent-sdk-skill
Create OpenAI Agents SDK applications in TypeScript/JavaScript. Use when building AI agents, multi-agent systems, voice agents, or any agentic workflow with the OpenAI Agents SDK. Covers agents, tools, handoffs, guardrails, streaming, MCP, and realtime voice agents.
majiayu000/claude-skill-registry 163
-
spec-kit-expert
Specification Kit expert covering RFC 2119 keywords, Gherkin syntax, user story formats, acceptance criteria patterns, and specification best practices. Activates for spec writing, specification format, RFC 2119, Gherkin, BDD, user stories, acceptance criteria, requirements, INVEST criteria, given-when-then, spec-driven development, specification templates.
majiayu000/claude-skill-registry 163
-
game-meta工具
使用game-meta进行策划表相关的操作，包括导出csv文件、更新game-meta工具
majiayu000/claude-skill-registry 163
-
check-library
ライブラリの情報を確認するためのスキル。Next.js、shadcn、その他のライブラリについて、適切なMCPサーバーを使用して最新のドキュメントと使用方法を取得します。
majiayu000/claude-skill-registry 163
-
Convex Agents Files
Handles file uploads, image attachments, and media processing in agent conversations. Use this when agents analyze images, process documents, or generate files.
majiayu000/claude-skill-registry 163
-
redis-config-generator
Generate Redis configuration files and connection code for caching and session management. Triggers on "create redis config", "generate redis configuration", "redis setup", "cache config".
majiayu000/claude-skill-registry 163