Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
mcp-developer
Model Context Protocol development expert. Use when creating MCP servers, clients, or tools that enable AI agents to interact with external systems, APIs, and development environments.
majiayu000/claude-skill-registry 163
-
architecture-design
PRD・機能設計からアーキテクチャ設計書（docs/architecture.md）を作成する。 「アーキテクチャ設計して」「技術選定して」「インフラ設計」「システム構成を決めて」 「技術スタックを決めて」「非機能要件の設計」などの依頼時に発火。 技術選定（理由付き）・レイヤー設計・データ戦略・セキュリティ・スケーラビリティを出力。
majiayu000/claude-skill-registry 163
-
multi-tenant-patterns
majiayu000/claude-skill-registry 163
-
generic-fullstack-ux-designer
Professional UI/UX design expertise for full-stack applications. Covers design thinking, user psychology (Hick's/Fitts's/Jakob's Law), visual hierarchy, interaction patterns, accessibility, performance-driven design, and design critique. Use when designing features, improving UX, solving user problems, or conducting design reviews.
majiayu000/claude-skill-registry 163
-
webpack
Webpack module bundler configuration and optimization. Loaders, plugins, code splitting, build optimization. Trigger: When configuring Webpack bundler, setting up loaders/plugins, or optimizing bundle size.
majiayu000/claude-skill-registry 163
-
streaming-ssr-hydration
Design streaming SSR pipelines with predictable hydration behavior and progressive interactivity.
majiayu000/claude-skill-registry 163
-
error-code-guide
设计一致的错误码，遵循 PREFIX_CATEGORY_NUMBER 格式。
使用时机：定義错误码、建立错误处理、设计 API。
关鍵字：error code, error handling, error format, API errors, 错误码, 错误处理。
majiayu000/claude-skill-registry 163
-
wrap-session
End-of-session documentation workflow that updates README, CHANGELOG, agent context files, and creates session logs. Use when wrapping up a working session, when asked to document session progress, when preparing handoff documentation, or when the user says "wrap up", "end session", "document progress", or "save session".
majiayu000/claude-skill-registry 163
-
technical-seo
Use when diagnosing crawl/index issues, performance regressions, or structured data gaps.
majiayu000/claude-skill-registry 163
-
prd-update-decisions
Update PRD based on design decisions and strategic changes made during conversations
majiayu000/claude-skill-registry 163
-
scoring
Motto: Style counts. Context matters. Story trumps numbers.
majiayu000/claude-skill-registry 163
-
Root Cause Tracing
Systematically trace bugs backward through call stack to find original trigger
majiayu000/claude-skill-registry 163
-
pattern-detection
Detect and document existing code patterns in a codebase. Use to maintain consistency with established conventions when writing new code.
majiayu000/claude-skill-registry 163
-
Newman Testing
Newman/Postman collection testing patterns for API testing with environment variables, test assertions, and reporting. Use when building API tests, running Newman collections, testing REST APIs, validating HTTP responses, creating Postman collections, configuring API test environments, generating test reports, or when user mentions Newman, Postman, API testing, collection runner, integration tests, API validation, test automation, or CI/CD API testing.
majiayu000/claude-skill-registry 163
-
github-prs
Use when responding to PR comments, updating PRs, or handling PR feedback as an AI agent. Ensures proper identification and use of MCP tools.
majiayu000/claude-skill-registry 163
-
e2e-tests-studio
REQUIRED when modifying any file in packages/playground-ui or packages/playground. Triggers on: React component creation/modification/refactoring, UI changes, new playground features, bug fixes affecting studio UI. Generates Playwright E2E tests that validate PRODUCT BEHAVIOR, not just UI states.
majiayu000/claude-skill-registry 163
-
document
Imported skill document from anthropic
majiayu000/claude-skill-registry 163
-
coding-agents
Spawn and control external coding agents (Claude Code, Codex, OpenCode, Pi) for delegating tasks. Use when (1) user asks to run another coding agent, (2) delegating subtasks to a different AI tool, (3) running multiple agents in parallel on separate issues, (4) spawning an agent in an isolated environment or worktree, (5) user mentions "codex", "opencode", "pi agent", or running "another claude".
majiayu000/claude-skill-registry 163
-
tech-stack-evaluator
Comprehensive technology stack evaluation and comparison tool with TCO analysis, security assessment, and intelligent recommendations for engineering teams
majiayu000/claude-skill-registry 163
-
variant-analysis
Find similar vulnerabilities and bugs across codebases using pattern-based analysis. Use when hunting bug variants, building CodeQL/Semgrep queries, analyzing security vulnerabilities, or performing systematic code audits after finding an initial issue.
majiayu000/claude-skill-registry 163
-
view-results
View and analyze Hawk evaluation results. Use when the user wants to see eval-set results, check evaluation status, list samples, view transcripts, or analyze agent behavior from a completed evaluation run.
majiayu000/claude-skill-registry 163
-
correct-course-pablolion-bmad-plugin
Determine how to proceed when major change discovered mid-implementation. Phase 4 Implementation
majiayu000/claude-skill-registry 163
-
capacitor
Use when working with capacitor components - adding capacitor patterns, parsing capacitor MPNs, extracting capacitance values, voltage ratings, dielectric types, or package codes from capacitor part numbers.
majiayu000/claude-skill-registry 163
-
cruise-com
Search and book cruises, compare cruise lines, and manage cruise reservations through Cruise.com
majiayu000/claude-skill-registry 163