Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
Model Training
Model training is the process of teaching machine learning models to make predictions or decisions based on data. This skill covers comprehensive training workflows including pipeline design, data pre
majiayu000/claude-skill-registry 163
-
phx:document
Write @moduledoc and @doc annotations into Elixir source files. Use ONLY when the user explicitly asks to generate documentation for modules, contexts, or schemas.
majiayu000/claude-skill-registry 163
-
react-patterns
Modern React patterns and principles. Hooks, composition, performance, TypeScript best practices.
majiayu000/claude-skill-registry 163
-
Locust Load Testing
Python-based load testing with Locust for writing user behavior scripts, distributed testing, real-time web UI monitoring, and custom load shapes.
majiayu000/claude-skill-registry 163
-
Dashboard Design
A dashboard is a visual display of key metrics and data points that provides at-a-glance insights for monitoring, analysis, and decision-making. Effective dashboards present the right information at t
majiayu000/claude-skill-registry 163
-
stitch-mcp-apply-design-system
Applies a Stitch Design System to existing screens — updates their colors, fonts, and roundness to match the design system's theme. Requires an assetId from list or create operations.
majiayu000/claude-skill-registry 163
-
bmad-dev-story
Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan"
majiayu000/claude-skill-registry 163
-
revops
Design and improve revenue operations, lead lifecycle rules, scoring, routing, handoffs, and CRM process automation. Use when marketing, sales, and customer success workflows need clearer operational structure.
majiayu000/claude-skill-registry 163
-
debugging
Self-diagnostic debugging - Agent decides diagnostic approach.
Auto-activates on "bug", "error", "debug", "不work", "壞掉" keywords.
AMP principle: Think > Follow - Agent writes own debug tools.
majiayu000/claude-skill-registry 163
-
browse
Complete guide for creating and deploying browser automation functions using the stagehand CLI
majiayu000/claude-skill-registry 163
-
technical-seo-checker
Performs technical SEO audits covering site speed, crawlability, indexability, mobile-friendliness, security, and structured data. Identifies technical issues preventing optimal search performance.
majiayu000/claude-skill-registry 163
-
remotion-best-practices
Best practices for Remotion - Video creation in React
majiayu000/claude-skill-registry 163
-
scaffolding-vue-components
Scaffolds Vue/Nuxt components with Composition API, CSS modules, Vitest tests, and Storybook stories. Use when the user asks to create a Vue component, generate component boilerplate, or mentions Vue 3 architecture.
majiayu000/claude-skill-registry 163
-
vulnerability-scanner
Advanced vulnerability analysis principles. OWASP 2025, Supply Chain Security, attack surface mapping, risk prioritization.
majiayu000/claude-skill-registry 163
-
analyzing-flow-cytometry
Interprets flow cytometry panels for hematologic malignancy classification and minimal residual disease. Use when analyzing flow cytometry, classifying lymphomas/leukemias, or documenting immunophenotyping.
majiayu000/claude-skill-registry 163
-
ioc
IOC extraction, enrichment, and threat intelligence correlation
majiayu000/claude-skill-registry 163
-
git-analysis
Analyze git repository changes, branch differences, and commit history. Use when analyzing branches, comparing changes, examining commit history, or preparing for PR/commit operations.
majiayu000/claude-skill-registry 163
-
move-scanner
Use when the user wants to audit Move smart contracts for security vulnerabilities, scan Aptos or Sui contracts for resource safety, capability leaks, or module upgrade issues, review Move-based DeFi protocols for object model and linear type violations, or analyze cross-module trust boundaries.
majiayu000/claude-skill-registry 163
-
df:execute-objective
Execute all jobs in an objective with wave-based parallelization.
Use when the user wants to build, run, or execute a planned objective.
Triggers on: "execute objective", "run objective", "build objective", "start building", "run the jobs", "let's build"
majiayu000/claude-skill-registry 163
-
state-management
Frontend state management patterns for React apps. Use when implementing Redux Toolkit, Zustand, Jotai, React Query, or any global state management solution.
majiayu000/claude-skill-registry 163
-
data-storytelling
Transform data into compelling narratives using visualization, context, and persuasive structure. Use when presenting analytics to stakeholders, creating data reports, or building executive presentations.
majiayu000/claude-skill-registry 163
-
firmware-analyst
Expert firmware analyst specializing in embedded systems, IoT security, and hardware reverse engineering.
majiayu000/claude-skill-registry 163
-
bird-twitter
Read X/Twitter content via Bird CLI. Actions: read tweets, search, view bookmarks, trending, news, timeline, mentions, lists. Keywords: twitter, x, tweet, trending, bookmarks, timeline.
majiayu000/claude-skill-registry 163
-
spec-driven-collaboration
Generate self-contained collaboration documents for sharing issues with external AI systems (Gemini, ChatGPT, etc.) with structural anti-skip enforcement (Execute-Verify-Record pattern at every step). Interactively gathers context, reads actual code files, loads constitutional constraints, and produces a complete 10-section package ready to paste into the target LLM. Use when the user wants to collaborate with another AI, share an issue for joint problem-solving, get a fresh perspective from a peer LLM, or needs help from an external AI that doesn't have access to the codebase. Make sure to use this skill whenever the user mentions cross-AI collaboration, sharing issues with Gemini/ChatGPT/Copilot, peer review from another AI, or wants a second opinion from an external LLM.
majiayu000/claude-skill-registry 163