Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
perf-analyzer
WHEN: Performance analysis, bundle size optimization, rendering, Core Web Vitals, code splitting
WHAT: Bundle analysis + large dependency detection + re-render issues + useMemo/useCallback suggestions + LCP/FID/CLS improvements
WHEN NOT: Code quality → code-reviewer, Security → security-scanner
majiayu000/claude-skill-registry 163
-
post-pr-review
Self-review and fix PR issues after creating a PR. Use after PR creation, when user says "PRレビュー", "セルフレビュー", "PR修正", or "review my PR". Runs pr-review-toolkit and fixes critical/important issues and suggestions.
majiayu000/claude-skill-registry 163
-
run-insights-recovery
Analyzes completed runs to provide effort assessment, recovery recommendations, and next-session guidance. Use immediately after user saves a run, asks "how did I do?", or requests recovery advice.
majiayu000/claude-skill-registry 163
-
performance-debug
Diagnose system performance issues including CPU, memory, disk, and network. Use when the user says "server is slow", "high CPU", "out of memory", "disk full", "performance issues", or asks to debug system performance.
majiayu000/claude-skill-registry 163
-
git-bisect-debugging
Use when debugging regressions or identifying which commit introduced a bug - provides systematic workflow for git bisect with automated test scripts, manual verification, or hybrid approaches. Can be invoked from systematic-debugging as a debugging technique, or used standalone when you know the issue is historical.
majiayu000/claude-skill-registry 163
-
docs-write
Write documentation following Metabase's conversational, clear, and user-focused style. Use when creating or editing documentation files (markdown, MDX, etc.).
majiayu000/claude-skill-registry 163
-
sdd-tasks
majiayu000/claude-skill-registry 163
-
python-debugger
Debug Python errors, exceptions, and unexpected behavior. Analyzes tracebacks, reproduces issues, identifies root causes, and provides fixes.
majiayu000/claude-skill-registry 163
-
oe-backend-prod-hardening
Production hardening review for the OpenEvent backend. Use when scanning for LLM smells, noisy prints, swallowed exceptions, dev-only defaults, fallback diagnostic leakage, and inconsistent error/logging patterns; produce a prioritized, PR-sized cleanup plan.
majiayu000/claude-skill-registry 163
-
python-uv-dev
Python development using the `uv` package manager. Use this skill when working with Python projects that use `uv` for dependency management, when initializing new Python projects, or when the user mentions `uv`, `pyproject.toml`, or asks about Python package management best practices.
majiayu000/claude-skill-registry 163
-
scientific-brainstorming
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
majiayu000/claude-skill-registry 163
-
cache-observability
Track cache hit rates, latency, and detect cache-related issues
majiayu000/claude-skill-registry 163
-
generate-questions
Generate high-quality bilingual programming quiz questions for Codle. Use this skill when creating new quiz questions that test deep understanding rather than rote memorization.
majiayu000/claude-skill-registry 163
-
git-commands
Git command conventions for pikru. Use when running any git commands to avoid blocking on interactive pager.
majiayu000/claude-skill-registry 163
-
ios-watch-logs
Start real-time log streaming from connected iPhone to console and file. Shows only app's explicit log messages with [APP] prefix. Use when monitoring app behavior, debugging, or viewing logs.
majiayu000/claude-skill-registry 163
-
skill-creator
Guide for creating effective skills. Use this skill when you want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
majiayu000/claude-skill-registry 163
-
cli-tech-stack
CLIツール開発の技術スタック・規約定義
majiayu000/claude-skill-registry 163
-
zod-extract
Find inline Zod schemas and move them to validations/ directory
majiayu000/claude-skill-registry 163
-
running-skills-edd-cycle
Guides evaluation-driven development (EDD) process for agent skills. Use when setting up skill testing workflows, creating skill evaluation scenarios, or establishing Claude A/B feedback loops for skill validation. Provides development methodology, not content guidance.
majiayu000/claude-skill-registry 163
-
pydantic-model-generator
Auto-generate Pydantic models from schema descriptions with type hints, validation rules, examples, and JSON schema export. 75% token savings (2,000→500).
majiayu000/claude-skill-registry 163
-
app-builder
Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents. Use for creating new applications, scaffolding projects, or building features from scratch.
majiayu000/claude-skill-registry 163
-
context-daddy
Context management tools for Claude Code - provides intelligent codebase mapping with Python, Rust, and C++ parsing, duplicate detection, and MCP-powered symbol queries. Use this skill when working with large codebases that need automated indexing and context management.
majiayu000/claude-skill-registry 163
-
post-change-verification
Mandatory verification protocol after code changes for Go projects. Use after any code modification to ensure quality.
majiayu000/claude-skill-registry 163
-
equilateral-agents-refactored
Multi-agent orchestration system sử dụng Claude subagents thực tế từ thư mục agents/ cho security reviews, code quality analysis, deployment validation, infrastructure checks. Auto-activates với orchestrator-worker pattern và extended thinking mode.
majiayu000/claude-skill-registry 163