Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
complete-agentic-jobs-to-earn-money
Browse, reserve, complete, and submit AgentPMT bounty jobs to earn credits using wallet-signed API calls. Use when the agent needs to earn credits, find available work, complete tasks for payment, or interact with the AgentPMT jobs board. Covers the full lifecycle from listing jobs through payout.
majiayu000/claude-skill-registry 163
-
status
Memory health dashboard showing line counts, topic files, capacity, stale entries, and recommendations.
majiayu000/claude-skill-registry 163
-
git-version-control
Master Git workflows, branching strategies, collaboration, and version control best practices. USE THIS for branch management, commit workflows, merging, rebasing, pull requests, conflict resolution, Git hooks, collaborative development, or version control strategy questions. Include when user mentions Git, branches, PR/MR, commits, merging, collaboration workflows, or version control.
majiayu000/claude-skill-registry 163
-
analyzing-network-flow-data
majiayu000/claude-skill-registry 163
-
jira-implement
This skill should be used when implementing the requirements in a JIRA ticket.
majiayu000/claude-skill-registry 163
-
arch
Load architecture patterns from the Claude Code Optimization Framework. Supports hybrid, mono, ms (microservices), and sls (serverless) patterns.
majiayu000/claude-skill-registry 163
-
context-engineering
Check context usage limits, monitor time remaining, optimize token consumption, debug context failures. Use when asking about context percentage, rate limits, usage warnings, context optimization, agent architectures, memory systems.
majiayu000/claude-skill-registry 163
-
claude-agent-sdk
Build AI agents using the Claude Agent SDK. Covers query functions, ClaudeSDKClient, custom tools, MCP servers, hooks, permissions, subagents, and browser control (Chrome extension, dev-browser skill). Use when creating agents, adding tools, configuring agent behavior, or automating browser tasks.
majiayu000/claude-skill-registry 163
-
create-agent
Create and validate domain agents. USE WHEN create agent, new agent, agent structure, validate agent, check agent, domain agent. AgentSearch('create-agent') for docs.
majiayu000/claude-skill-registry 163
-
soft-predict-future
Activate this skill for ANY future-oriented question. Triggers include: "Will [X]?", "Who will win [X]?", "What happens to [X]?", "Can [X] succeed?", "What's the future of X?", foresight analysis, scenario planning, STEEEP analysis, futures cone, prediction requests, or any question about a future outcome. Year is NOT required — the engine infers the horizon. Also activate when the user says "predict", "forecast", "what are the odds", "scenario analysis", or asks about competitive races, technology adoption, geopolitical shifts, or market dominance. REQUIRES web search to be enabled — if web search is unavailable, tell the user before proceeding.
majiayu000/claude-skill-registry 163
-
clinpgx-database
Access ClinPGx pharmacogenomics data (successor to PharmGKB). Query gene-drug interactions, CPIC guidelines, allele functions, for precision medicine and genotype-guided dosing decisions.
majiayu000/claude-skill-registry 163
-
ruby-pro
Write idiomatic Ruby code with metaprogramming, Rails patterns, and performance optimization. Specializes in Ruby on Rails, gem development, and testing frameworks. Use PROACTIVELY for Ruby refactoring, optimization, or complex Ruby features.
majiayu000/claude-skill-registry 163
-
skill-check
Validate Claude Code skills against the agentskills specification. Catches structural, semantic, and naming issues before users do.
majiayu000/claude-skill-registry 163
-
financial-model-review
Reviews startup financial models for investor readiness — validating unit economics, stress-testing runway scenarios, and benchmarking metrics against stage-appropriate targets. Use when user asks to 'review my financial model', 'check my projections', 'validate my unit economics', 'stress-test my runway', 'analyze my burn rate', 'review my spreadsheet model', or provides an Excel spreadsheet, CSV, or financial projections for evaluation. Supports Excel (.xlsx), CSV, Google Sheets exports, documents, and conversational input. Do NOT use for market sizing (use market-sizing), pitch deck feedback (use deck-review), or general spreadsheet editing, accounting, or tax preparation.
majiayu000/claude-skill-registry 163
-
providing-performance-optimization-advice
Provide comprehensive prioritized performance optimization recommendations for frontend, backend, and infrastructure. Use when analyzing bottlenecks or seeking improvement strategies. Trigger with phrases like "optimize performance", "improve speed", or "performance recommendations".
majiayu000/claude-skill-registry 163
-
validate_paper_links
Validate paper note links against actual paper references and influence
majiayu000/claude-skill-registry 163
-
nw-research-methodology
Research output templates, distillation workflow, and quality standards for evidence-driven research
majiayu000/claude-skill-registry 163
-
wecom
Send messages to WeCom (企业微信) via webhooks using MCP protocol. Works with Claude Code, Claude Desktop, and other MCP clients.
majiayu000/claude-skill-registry 163
-
github-release
Create a GitHub release with auto-generated release notes from commits since the last tag. Uses conventional commits to categorize changes into Features, Bug Fixes, and maintenance sections.
majiayu000/claude-skill-registry 163
-
analyze-results
Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.
majiayu000/claude-skill-registry 163
-
deepagents-architecture
Guides architectural decisions for Deep Agents applications. Use when deciding between Deep Agents vs alternatives, choosing backend strategies, designing subagent systems, or selecting middleware approaches.
majiayu000/claude-skill-registry 163
-
seo-aeo-content-quality-auditor
Audits content for SEO and AEO performance with scored reports, severity-ranked fix lists, and projected scores after fixes. Activate when the user wants to audit, review, or score content for SEO or AEO compliance.
majiayu000/claude-skill-registry 163
-
kit
Kit (formerly ConvertKit) API integration with managed OAuth. Manage email subscribers, forms, tags, sequences, broadcasts, and custom fields.
Use this skill when users want to manage their email marketing lists, create or update subscribers, manage tags, or work with email sequences and broadcasts.
For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).
majiayu000/claude-skill-registry 163
-
strategic-planning-facilitator
Facilitates strategic planning sessions for small to mid-size businesses. Guides through vision/mission refinement, SWOT analysis, goal setting with OKRs, strategic initiative prioritization, and execution roadmap creation.
majiayu000/claude-skill-registry 163