Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
pmc-simulate-tester
Simulate the tester workflow step-by-step with real ticket system. Executes test loading, running, verification, and merging with explicit ENTER/EXIT stage declarations. Use this skill to debug, understand, or manually run the tester workflow.
majiayu000/claude-skill-registry 163
-
GitHub CLI
Expert help with GitHub CLI (gh) for managing pull requests, issues, repositories, workflows, and releases. Use this when working with GitHub operations from the command line, creating new releases, or bumping package versions.
majiayu000/claude-skill-registry 163
-
Skill development
This skill should be used when the user asks to "create a skill", "write a new skill", "improve a skill description", "organize skill content", "update skill references", "update skill workflows", "review a skill", "test a skill", "add a reference", "add a workflow", "add a template", or needs guidance on skill structure, progressive disclosure, or skill development best practices.
majiayu000/claude-skill-registry 163
-
python-setup
Python environment setup on your computer for Badger 2350 development. Use when installing Python, setting up virtual environments, installing development tools like mpremote or ampy, or configuring the computer-side development environment for Badger 2350 projects.
majiayu000/claude-skill-registry 163
-
backend-code-organisation
Kotlin backend layering and packaging guidelines
majiayu000/claude-skill-registry 163
-
gemini-genai
Google python-genai SDK for Gemini 3 Flash, Gemini 3 Pro, and Gemini models. Use when building with Google's Gemini API, google-genai, implementing thinking/reasoning, structured outputs, function calling, image generation, or multimodal. Triggers on "gemini", "google ai", "genai".
majiayu000/claude-skill-registry 163
-
cover-letter
Create tailored cover letters that complement your resume. Use after generating a resume with /resume-builder. Requires the generated resume to ensure consistency in achievements and messaging.
majiayu000/claude-skill-registry 163
-
async-patterns-guide
Guides users on modern async patterns including native async fn in traits, async closures, and avoiding async-trait when possible. Activates when users work with async code.
majiayu000/claude-skill-registry 163
-
market-sizing-analysis
This skill should be used when the user asks to "calculate TAM", "determine SAM", "estimate SOM", "size the market", "calculate market opportunity", "what's the total addressable market", or requests market sizing analysis for a startup or business opportunity.
majiayu000/claude-skill-registry 163
-
release-skill
Bump version, update changelog, commit, tag, push, and build release installer
majiayu000/claude-skill-registry 163
-
pm-delegation-patterns
Common delegation patterns for PM agent
majiayu000/claude-skill-registry 163
-
skill-creator
Guide for creating effective skills. This skill should be used when users 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
-
outline-builder
Convert a taxonomy (`outline/taxonomy.yml`) into a bullet-only outline (`outline/outline.yml`) with sections/subsections.
**Trigger**: outline builder, bullet outline, outline.yml, 大纲生成, bullets-only.
**Use when**: structure 阶段（NO PROSE），已有 taxonomy，需要生成可映射/可写作的章节与小节骨架（每小节≥3 bullets）。
**Skip if**: 已经有批准过且可映射的 outline（避免无意义 churn）。
**Network**: none.
**Guardrail**: bullets-only；移除 TODO/模板语句；每小节至少 3 个可检查 bullets。
majiayu000/claude-skill-registry 163
-
create-pr-github-oocx-tfplan2md-uat
majiayu000/claude-skill-registry 163
-
Global Validation
Implement comprehensive validation using Zod schemas for type-safe validation on both client and server, with server-side validation as the security boundary (never trust client input). Use this skill when validating user inputs, creating API endpoints that accept data, implementing forms, defining data schemas, validating file uploads, creating validation middleware, implementing Firestore security rules or Supabase RLS, or writing validation rules for any user-provided data. Apply when working on API route handlers, form components with React Hook Form, validation middleware, Zod schema definitions (schemas/*.ts, validation/*.ts), Firestore security rules (firestore.rules), Supabase RLS policies, or any code that accepts external input. This skill ensures server-side validation always (client-side is for UX only), Zod for schema validation with TypeScript type inference (z.infer<typeof schema>), validation middleware factory for Express/Bun APIs, React Hook Form + zodResolver for forms, user-friendly error messages (not technical jargon), input sanitization with DOMPurify for HTML content, file upload validation (type whitelist, size limits with multer), Firestore security rules with data type and length validation, FluentValidation for .NET APIs, database-level constraints enforcement, fail-early validation principles, and environment variable validation with Zod on application startup.
majiayu000/claude-skill-registry 163
-
bundle-performance
Monitor JavaScript bundle size and execution performance. Use when tracking bundle size, identifying large chunks, or optimizing load performance.
majiayu000/claude-skill-registry 163
-
unknown-brownbull-taskflow
majiayu000/claude-skill-registry 163
-
ios-swift-development
Develop native iOS apps with Swift. Covers MVVM architecture, SwiftUI, URLSession for networking, Combine for reactive programming, and Core Data persistence.
majiayu000/claude-skill-registry 163
-
ring:dev-implementation
Gate 0 of the development cycle. Executes code implementation using the appropriate
specialized agent based on task content and project language. Handles TDD workflow
with RED-GREEN phases. Follows project standards defined in docs/PROJECT_RULES.md.
majiayu000/claude-skill-registry 163
-
mcp-skill-creator
Meta-skill for creating workflow-optimized skills from MCP servers. Use when users want to create a custom skill that integrates one or more MCP servers into a specialized workflow. The user provides MCP server configurations and describes their work scenario (workflow, preferences, SOPs), and this skill generates a new skill with optimized scripts following Anthropic's MCP + code execution best practices.
majiayu000/claude-skill-registry 163
-
openwebf-app-debugging-devtools
Debug WebF app runtime issues with Chrome DevTools (console/network/elements) and JS-side troubleshooting. Use when the user mentions DevTools console, network tab, stack traces, blank screen, layout measurement issues, or failing network requests.
majiayu000/claude-skill-registry 163
-
hardcoded-credential-finder
Hardcoded Credential Finder - Auto-activating skill for Security Fundamentals.
Triggers on: hardcoded credential finder, hardcoded credential finder
Part of the Security Fundamentals skill category.
majiayu000/claude-skill-registry 163
-
codex-collab
【WHEN】当用户命令中明确包含"codex协作"、"codex协同"、"与codex合作"等指令时启用； 【WHEN】当用户要求使用 codex MCP 工具进行代码分析、原型生成、review 等协作开发场景时启用。 【WHEN NOT】不用于单独的代码实现任务、不用于纯文档编写、不用于不涉及 codex 的常规开发流程。
majiayu000/claude-skill-registry 163
-
datacommons-client
Work with Data Commons, a platform providing programmatic access to public statistical data from global sources. Use this skill when working with demographic data, economic indicators, health statistics, environmental data, or any public datasets available through Data Commons. Applicable for querying population statistics, GDP figures, unemployment rates, disease prevalence, geographic entity resolution, and exploring relationships between statistical entities.
majiayu000/claude-skill-registry 163