Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
exploring-in-parallel
Parallelizes codebase exploration and research by launching multiple subagents simultaneously. Use when exploring codebases, researching questions, investigating bugs, gathering context from multiple sources, or any task requiring search across multiple files, patterns, or directories. Triggers on research, exploration, debugging, "why does this happen", "how does X work", or multi-file investigation.
majiayu000/claude-skill-registry 163
-
skill-router
Analyzes tasks to find the optimal workflow of skills, presents the recommended sequence with rationale, and lets user approve/modify before execution. Use when starting any complex task, wanting help finding the right tools, or needing a structured approach.
majiayu000/claude-skill-registry 163
-
api-client
Centralized TypeScript API client with typed namespaces, automatic token refresh with request deduplication, TanStack Query integration, and consistent error handling.
majiayu000/claude-skill-registry 163
-
cv-content-editor
Edit and update existing CV content using the knowledge base as source of truth. Use when user wants to modify case studies, update experience, refine variants, or improve existing content.
majiayu000/claude-skill-registry 163
-
cursor-keybindings
Manage master Cursor keyboard shortcuts and customize keybindings. Triggers on "cursor shortcuts",
"cursor keybindings", "cursor keyboard", "cursor hotkeys", "cursor commands". Use when working with cursor keybindings functionality. Trigger with phrases like "cursor keybindings", "cursor keybindings", "cursor".
majiayu000/claude-skill-registry 163
-
claude-specific
Claude Code specific instructions for working with this CDK monorepo. General guidance on code generation, refactoring, and feature additions.
majiayu000/claude-skill-registry 163
-
system-design-documentation
Produce C4, ADRs, sequences, and data flow diagrams.
majiayu000/claude-skill-registry 163
-
economist-analyst
Analyzes events through economic lens using supply/demand, incentive structures, market dynamics,
and multiple schools of economic thought (Classical, Keynesian, Austrian, Behavioral).
Provides insights on market impacts, resource allocation, policy implications, and distributional effects.
Use when: Economic events, policy changes, market shifts, financial crises, regulatory decisions.
Evaluates: Incentives, efficiency, opportunity costs, market failures, systemic risks.
majiayu000/claude-skill-registry 163
-
research-agent
Research agent for external documentation, best practices, and library APIs via MCP tools
majiayu000/claude-skill-registry 163
-
spec-validate
Validation loop for speccing. Clarifies requirements through structured questioning before document creation.
majiayu000/claude-skill-registry 163
-
Advanced Testability Ai Ergonomic
Design code for testability and AI/LLM ergonomics with explicit contracts and observable patterns. Use when optimizing code for AI tools, improving testability, or making codebases LLM-friendly.
majiayu000/claude-skill-registry 163
-
docker-git-bash-guide
Comprehensive Windows Git Bash and MINGW path conversion guide for Docker volume mounts and commands
majiayu000/claude-skill-registry 163
-
webgpu-specs
Download WebGPU and WGSL specifications for use as a reference
majiayu000/claude-skill-registry 163
-
ln-782-test-runner
Executes all test suites and reports results with coverage
majiayu000/claude-skill-registry 163
-
safety-training-workflow
majiayu000/claude-skill-registry 163
-
create-spec
Create a new specification through an adaptive interview process with proactive recommendations and optional research. Use when user says "create spec", "new spec", "generate spec", or wants to start a specification document.
majiayu000/claude-skill-registry 163
-
weibo-trends-analyzer
Analyzes Weibo (微博) trending topics and generates creative product ideas based on hot search keywords. Fetches real-time trending data from Weibo API, researches background information and user insights, evaluates product development potential using a 100-point scoring system, and creates an interactive HTML dashboard. Use when analyzing Chinese social media trends, identifying product opportunities from trending topics, or generating market-driven creative product concepts.
majiayu000/claude-skill-registry 163
-
solidity
Expert in Solidity smart contract development with security and gas optimization
majiayu000/claude-skill-registry 163
-
obsidian-issue-from-doc
Convert Obsidian documents into GitHub-ready issues with structured format. Use when transforming specs or design docs into actionable GitHub issues.
majiayu000/claude-skill-registry 163
-
clavix-review
Review code changes with criteria-driven analysis (Security, Architecture, Standards, Performance). Use when reviewing PRs or code changes.
majiayu000/claude-skill-registry 163
-
bug-detector
Detects bugs, logic errors, and edge case handling issues in code. Use when reviewing code for runtime errors, null/undefined handling, type errors, and edge cases. Returns structured bug reports with file paths, line numbers, and suggested fixes.
majiayu000/claude-skill-registry 163
-
kegg-database
Direct REST API access to KEGG (academic use only). Pathway analysis, gene-pathway mapping, metabolic pathways, drug interactions, ID conversion. For Python workflows with multiple databases, prefer bioservices. Use this for direct HTTP/REST work or KEGG-specific control.
majiayu000/claude-skill-registry 163
-
review-typescript
Use this skill when you need to review TypeScript code changes with an extremely high quality bar. This agent should be invoked after implementing features, modifying existing code, or creating new TypeScript components. The agent applies strict TypeScript conventions and taste preferences to ensure code meets exceptional standards.
majiayu000/claude-skill-registry 163
-
smart-skill-loading
Auto-detect and load minimal context from Skills folders using progressive disclosure, trimming 1400 tokens from system prompt through metadata-first loading. Use when optimizing token usage, managing multiple skills, or preventing context bloat. Load YAML metadata first, then conditionally load full SKILL.md only for matched skills based on task triggers. Achieves 10% accuracy improvement via targeted context. Triggers on "optimize skills", "reduce tokens", "smart loading", "skill efficiency".
majiayu000/claude-skill-registry 163