Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
research
Comprehensive multi-source research with academic depth. Searches web, social platforms, news, academic databases, and GitHub. Discovers papers, datasets, and open source implementations. Use when conducting research, literature reviews, or investigating any topic.
majiayu000/claude-skill-registry 163
-
arcanea-centaur-mode
Advanced human-AI co-creation methodology - the Centaur Principle in practice. Master the art of combining human creativity with AI capability for results neither could achieve alone.
majiayu000/claude-skill-registry 163
-
Offline-First
PWA patterns and offline functionality in LivestockAI
majiayu000/claude-skill-registry 163
-
gtd
Autonomous task execution from GTD.md items. Use when processing GTD tasks, call prep, outreach, or podcast preparation.
majiayu000/claude-skill-registry 163
-
using-hyperliquid-adapter
How to use Hyperliquid adapter data (meta, funding, candles, orderbooks) and execution surfaces (orders/transfers) in Wayfinder Paths, including required executor wiring.
majiayu000/claude-skill-registry 163
-
m01-ownership
CRITICAL: Use for ownership/borrow/lifetime issues. Triggers: E0382, E0597, E0506, E0507, E0515, E0716, E0106, value moved, borrowed value does not live long enough, cannot move out of, use of moved value, ownership, borrow, lifetime, 'a, 'static, move, clone, Copy, 所有权, 借用, 生命周期
majiayu000/claude-skill-registry 163
-
bun-development
Modern JavaScript/TypeScript development with Bun runtime. Covers package management, bundling, testing, and migration from Node.js. Use when working with Bun, optimizing JS/TS development speed, or migrating from Node.js to Bun.
majiayu000/claude-skill-registry 163
-
visual-verify
Visuelle Verifikation via Puppeteer. Erzwingt echte Sichtprüfung statt theoretischer Code-Analyse. Nimmt Screenshots, analysiert gerenderte Elemente, prüft Kontrast/Layout/Lesbarkeit visuell. Nutze diesen Skill IMMER wenn du behaupten willst dass etwas "funktioniert" oder "gut aussieht". Aufruf mit /visual-verify [view-name oder css-selektor].
majiayu000/claude-skill-registry 163
-
audit-crossrefs
Phase 7: Convert hardcoded cross-references to auto-updating NOTEREF fields
majiayu000/claude-skill-registry 163
-
web-ui-tanstack-table
TanStack Table v8 patterns - useReactTable, column definitions, sorting, filtering, pagination, row selection, virtual scrolling, server-side data
majiayu000/claude-skill-registry 163
-
telegram-bot-builder
Expert in building Telegram bots that solve real problems - from simple automation to complex AI-powered bots. Covers bot architecture, the Telegram Bot API, user experience, monetization strategies, and scaling bots to thousands of users. Use when: telegram bot, bot api, telegram automation, chat bot telegram, tg bot.
majiayu000/claude-skill-registry 163
-
apply-design-system
Apply design tokens and system patterns correctly. Reference for semantic colors, spacing, typography, borders, and shadows. Never use arbitrary values.
majiayu000/claude-skill-registry 163
-
market-report
Create a structured market analysis report with regime, levels, catalysts, and risks.
majiayu000/claude-skill-registry 163
-
aget-provide-feedback
Provide structured feedback with severity classification
majiayu000/claude-skill-registry 163
-
writing-utils
Use this skill when you need to write utility functions for the Next.js app
majiayu000/claude-skill-registry 163
-
scout
(ePost) Use when you need to "find files", "search the codebase", "locate a pattern", "explore the repo", or "what exists for X" — searches across platforms using RAG and grep
majiayu000/claude-skill-registry 163
-
bmad-validate-prd
Validate a PRD against standards. Use when the user says "validate this PRD" or "run PRD validation"
majiayu000/claude-skill-registry 163
-
paper-lab
Self-improving documentation convergence loop. Computes quality deltas between review rounds, identifies recurring issues, applies targeted fixes, and converges on quality thresholds. Uses /review-paper as the quality signal and /create-paper or direct editing for fixes. Tracks convergence trajectory across rounds.
majiayu000/claude-skill-registry 163
-
df:quick
Execute a quick task with DevFlow guarantees (atomic commits, state tracking) but skip optional agents.
Use when the user wants to do something small, quick, or ad-hoc without full objective ceremony.
Triggers on: "quickly do", "just do this", "small task", "quick change", "quick fix", "can you just"
majiayu000/claude-skill-registry 163
-
bsp
BSP geometry skill for Unreal brushes and CSG.
majiayu000/claude-skill-registry 163
-
gcp-coding
Language-agnostic GCP best practices and common pitfalls. Use when writing code that integrates with GCP services (Cloud Run, Secret Manager, Cloud Storage, Pub/Sub, etc.) to avoid anti-patterns and follow Google Cloud's recommended approaches.
majiayu000/claude-skill-registry 163
-
ecosystem-alignment
Upstream version checking, agentskills.io spec compliance audit, Claude Code feature gap analysis. Activates on updates, version checks, or alignment work.
majiayu000/claude-skill-registry 163
-
frontend-testing
Comprehensive frontend testing with Playwright, Cypress, Jest, and React Testing Library. Covers E2E testing, component testing, unit testing, visual regression, and accessibility testing. Use for quality assurance, CI/CD integration, and test automation.
majiayu000/claude-skill-registry 163
-
preview-testing
Comprehensive E2E + Security Tests for Vercel Preview Deployments. Combines Playwright automation with Claude-in-Chrome MCP for interactive debugging. Activate on PR creation, before merge, or manual /preview-test.
majiayu000/claude-skill-registry 163