Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
vercel-blob
Integrate Vercel Blob for file uploads and CDN-delivered assets in Next.js. Supports client-side uploads with presigned URLs and multipart transfers for large files.
Use when implementing file uploads (images, PDFs, videos) or troubleshooting missing tokens, size limits, client upload failures, token expiration errors, or browser compatibility issues. Prevents 16 documented errors.
majiayu000/claude-skill-registry 163
-
vibe-help
Quick reference cheatsheet for all agentic-loop commands including Ralph.
majiayu000/claude-skill-registry 163
-
til
Write TIL(Today I Learned) documents to ~/dev/TIL/{category}/. "Why" focused storytelling, conclusion first, mermaid diagrams, code examples. Auto-categorize (python, java, spring, nodejs, ai, etc). **Proactively use this skill** when user mentions "TIL", "TIL로 작성", "TIL 문서", "학습 노트 작성" without explicit /til command.
majiayu000/claude-skill-registry 163
-
figma-ai
Provides comprehensive guidance for Figma AI features including AI-powered design tools, automation, and AI-assisted design workflows. Use when the user asks about Figma AI, needs to use AI features in Figma, or automate design tasks with AI.
majiayu000/claude-skill-registry 163
-
tzurot-testing
Vitest testing patterns for Tzurot v3. Use when writing tests, debugging test failures, or mocking dependencies. Covers mock factories, fake timers, and promise rejection handling.
majiayu000/claude-skill-registry 163
-
automating-chrome
Automates Google Chrome and Chromium-based browsers via JXA with AppleScript dictionary discovery. Use when asked to "automate Chrome tabs", "control browser with JXA", "Chrome AppleScript automation", "Chromium browser scripting", or "browser tab management". Covers windows, tabs, execute(), tunneling patterns, and permissions.
majiayu000/claude-skill-registry 163
-
db-seeder
This skill should be used when seeding databases with realistic fake data for development, testing, or staging environments. Supports PostgreSQL, MySQL, SQLite, MongoDB with ORM-based seeding (SQLAlchemy, Django, Prisma) and Faker library for generating realistic test data. Use when the user needs to populate databases with sample data, create test fixtures, or set up development/staging environments with realistic data.
majiayu000/claude-skill-registry 163
-
my-vue-rules
This is a new rule
majiayu000/claude-skill-registry 163
-
python-best-practices
Provides Python patterns for type-first development with dataclasses, discriminated unions, NewType, and Protocol. Must use when reading or writing Python files.
majiayu000/claude-skill-registry 163
-
quillbot
AI paraphrasing and writing enhancement tool.
majiayu000/claude-skill-registry 163
-
tool-discovery
Guide for discovering and using MCP tools via the discover_tools meta-tool. Use this skill when asked to perform tasks that require finding the right tools, when you see only discover_tools in your available tools, when asked "what tools are available", "find tools for X", or when planning multi-step workflows across JIRA, Slack, WhatsApp, or Google Docs.
majiayu000/claude-skill-registry 163
-
java-architect
Expert Java architect specializing in Java 21, Spring Boot 3, and Jakarta EE ecosystem. This agent excels at designing enterprise-grade applications with modern Java features, microservices architecture, and comprehensive enterprise integration patterns.
majiayu000/claude-skill-registry 163
-
fosmvvm-serverrequest-test-generator
Generate comprehensive ServerRequest tests using VaporTesting infrastructure. Use when testing any ServerRequest type (ShowRequest, ViewModelRequest, CreateRequest, UpdateRequest, DeleteRequest) against a Vapor server.
majiayu000/claude-skill-registry 163
-
Performing Security Code Review
This skill enables Claude to conduct a security-focused code review using the security-agent plugin. It analyzes code for potential vulnerabilities like SQL injection, XSS, authentication flaws, and insecure dependencies. Claude uses this skill when the user explicitly requests a security audit, asks for a code review with a focus on security, or mentions security concerns related to code. The security-agent plugin then provides structured security findings with severity ratings, code locations, impact assessments, and remediation guidance.
majiayu000/claude-skill-registry 163
-
wandb-plot
Shared skill entrypoint for Claude Code. See the canonical skill file at:
wandb-plot/SKILL.md
majiayu000/claude-skill-registry 163
-
fastapi
FastAPI patterns for Australian-first API development
majiayu000/claude-skill-registry 163
-
Convex Cron Jobs
Scheduled function patterns for background tasks including interval scheduling, cron expressions, job monitoring, retry strategies, and best practices for long-running tasks
majiayu000/claude-skill-registry 163
-
readme-updater-u9401066-pubmed-search-mcp-7ce38387
majiayu000/claude-skill-registry 163
-
integration-development
Guide for creating new OAuth-based integrations in the Orient codebase. Use when adding external service integrations (APIs like Linear, GitHub, Slack, Notion, etc.), implementing OAuth flows, or creating catalog-based integration manifests. Covers the full integration lifecycle from manifest definition to tool implementation.
majiayu000/claude-skill-registry 163
-
docx
Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks
majiayu000/claude-skill-registry 163
-
erpnext-syntax-hooks
Deterministic syntax for Frappe hooks.py configuration. Use when Claude needs to configure app events, scheduler tasks, document events, fixtures, boot session, jenv customization, or website routing. Covers v14/v15/v16 including extend_doctype_class. Triggers: hooks.py, doc_events, scheduler_events, fixtures, app_include_js, override_whitelisted_methods.
majiayu000/claude-skill-registry 163
-
extractor
Extract content from any document using the Preset-First Agentic Pipeline. Auto-detects format and document type (scientific papers, requirements specs, etc.). Supports PDF, DOCX, HTML, XML, PPTX, XLSX, EPUB, Markdown, images. Use when user says "extract this", "convert to markdown", "process pdf", or provides a document.
majiayu000/claude-skill-registry 163
-
neon-async-db
This skill should be used when setting up and managing reliable, high-performance asynchronous database connections for Neon Serverless PostgreSQL using SQLModel and SQLAlchemy's async capabilities.
majiayu000/claude-skill-registry 163
-
atomic-tools-brainblend-ai-atomic-agents-2
This skill should be used when the user asks to "create a tool", "implement BaseTool", "add tool to agent", "tool orchestration", "external API tool", or needs guidance on tool development, tool configuration, error handling, and integrating tools with agents in Atomic Agents applications.
majiayu000/claude-skill-registry 163