Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
claude-code-agents
Create and configure Claude Code agents with YAML frontmatter, tool selection, model specification, and naming conventions. Reference for building specialized AI subagents that handle complex, multi-step tasks.
majiayu000/claude-skill-registry 163
-
exploring-graph
Analyze the knowledge graph for insights. Use when asked to "analyze connections", "graph report", "show hubs", "find orphans", or "knowledge map".
majiayu000/claude-skill-registry 163
-
reviewing-readability
"The Art of Readable Code"とミラーの法則（7±2）に基づくコード可読性レビュー。 トリガー: 可読性, 理解しやすい, わかりやすい, 明確, 命名, 変数名, 関数名, ネスト, 深いネスト, 関数設計, コメント, 複雑, 難しい, 難読, Miller's Law, ミラーの法則, 認知負荷, AI-generated, 過剰設計.
majiayu000/claude-skill-registry 163
-
performance-opt
Analyze and optimize application performance including bundle size, render performance, and API response times. Use when investigating slow pages or optimizing production builds.
majiayu000/claude-skill-registry 163
-
0000
majiayu000/claude-skill-registry 163
-
javascript-modern
Implements modern JavaScript features from ES2020-ES2024 including optional chaining, nullish coalescing, private fields, Promise methods, and array transformations. Use when modernizing JavaScript code, using ES2024 features, or when user asks about latest ECMAScript standards.
majiayu000/claude-skill-registry 163
-
lighthouse-performance-optimization
Use when optimizing website performance. Run Google Lighthouse audits via MCP to measure metrics, identify bottlenecks, and iterate on improvements.
majiayu000/claude-skill-registry 163
-
strategy-and-competitive-analysis
Use when developing business strategy (market entry, product launch, geographic expansion, M&A, turnaround), conducting competitive analysis (profiling competitors, assessing competitive threats, Porter's 5 Forces, identifying differentiation), applying strategic frameworks (Good Strategy kernel with diagnosis/guiding policy/coherent actions, SWOT, Blue Ocean Strategy, Playing to Win where-to-play/how-to-win, Value Chain Analysis, BCG Matrix), making strategic decisions under constraints (build vs buy, pricing strategy, market positioning, business model choices), planning strategic initiatives (annual planning, OKRs, roadmaps), evaluating competitive positioning (moats, sustainable advantages, differentiation vs cost leadership), or when user mentions "strategy", "competitive analysis", "Porter's 5 Forces", "SWOT", "market positioning", "strategic planning", "competitive landscape", or "strategic frameworks".
majiayu000/claude-skill-registry 163
-
fvtt-hooks
This skill should be used when registering hooks, creating custom hooks for module APIs, debugging hook execution, handling async in hooks, or preventing memory leaks from unclean hook removal. Covers Hooks.on/once/call/callAll, lifecycle order, and common pitfalls.
majiayu000/claude-skill-registry 163
-
publishing-stories
Guides commit, push, and draft PR creation for stories. Use when ready to commit changes, pushing to remote, or creating a pull request for review.
majiayu000/claude-skill-registry 163
-
typescript-standards
Guide for creating TypeScript libraries using the typescript-library-template pattern and applying its standards to existing projects. Use when setting up new npm packages, standardizing build scripts, configuring tooling (tsup, Vitest, ESLint, Prettier), or applying dual module format patterns.
majiayu000/claude-skill-registry 163
-
software-product-manager
Expert software product manager who works directly with stakeholders to understand their needs and create comprehensive product specifications. Use when users need help designing software, defining requirements, creating PRDs, writing user stories, or developing functional specifications. Guides product management aspects of software development, asks clarifying questions, uncovers unstated preferences and assumptions, determines happy paths and error handling, and creates documentation understandable to both stakeholders and engineers.
majiayu000/claude-skill-registry 163
-
QiAgent
技術実装Agent - 実行計画を技術的な実装要素に分解する
majiayu000/claude-skill-registry 163
-
scout
Market validation engine for ID8Labs. Transforms raw ideas into validated (or invalidated) opportunities through systematic research. Returns BUILD/PIVOT/KILL verdicts with evidence.
majiayu000/claude-skill-registry 163
-
qa-contract-validator
Validates API contracts by discovering consumers and ensuring responses match their expectations. Detects breaking changes.
majiayu000/claude-skill-registry 163
-
sync-builder-skill
Use when creating Nango syncs for continuous data synchronization - provides patterns for pagination, batch saving, deletion detection, and incremental updates
majiayu000/claude-skill-registry 163
-
requirements-gathering
Systematically collect, document, and validate requirements from stakeholders. Ensure clarity, completeness, and agreement before development begins to reduce scope creep and rework.
majiayu000/claude-skill-registry 163
-
dbt-commands
dbt command-line operations, model selection syntax, Jinja patterns, troubleshooting, and debugging. Use this skill when running dbt commands, selecting specific models, debugging compilation errors, using Jinja macros, or troubleshooting dbt execution issues.
majiayu000/claude-skill-registry 163
-
ct-debug-skill
Debug and troubleshoot claude-threads, orchestrator, and agent issues
majiayu000/claude-skill-registry 163
-
git-troubleshooting
Git troubleshooting techniques including recovering lost commits, fixing merge conflicts, resolving detached HEAD, and diagnosing repository issues. Use when user encounters git errors or needs to recover from mistakes.
majiayu000/claude-skill-registry 163
-
pr-review-standards
Use when creating PRs to enforce code quality standards. Automated detection of anti-patterns, security issues, and code smells. Python 3.8+
majiayu000/claude-skill-registry 163
-
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
majiayu000/claude-skill-registry 163
-
hexagonal-advisor
Reviews code architecture for hexagonal patterns, checks dependency directions, and suggests improvements for ports and adapters separation. Activates when users work with services, repositories, or architectural patterns.
majiayu000/claude-skill-registry 163
-
hft-quant-expert
Quantitative trading expertise for DeFi and crypto derivatives. Use when building trading strategies, signals, risk management. Triggers on signal, backtest, alpha, sharpe, volatility, correlation, position size, risk.
majiayu000/claude-skill-registry 163