Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
youtube-downloader
Download videos, audio, playlists, and channels from YouTube and 1000+ websites using yt-dlp. Supports quality selection, format conversion, subtitle download, playlist filtering, metadata extraction, thumbnail download, and batch operations. Use when downloading YouTube videos in any quality (4K, 8K, HDR), extracting audio as MP3/M4A/FLAC, downloading entire playlists/channels, getting subtitles in multiple languages, converting to specific formats, downloading live streams, archiving content, or batch processing multiple URLs. Optimized for reliability with automatic retries, rate limiting, and error handling.
majiayu000/claude-skill-registry 163
-
ru
Repo Updater - automation-friendly CLI for synchronizing GitHub repositories. Keep dozens or hundreds of repos in sync with a single command. Pure Bash with git plumbing, JSON output, meaningful exit codes, parallel sync, and conflict resolution.
majiayu000/claude-skill-registry 163
-
skill-optimizer
Refactors Claude Code skills to reduce token usage 80-95% using Progressive Disclosure Architecture (PDA). Splits monolithic skills into orchestrator + reference files, extracts scripts, creates reference/ directories. Use when optimizing skills, improving skill efficiency, refactoring large/bloated skills, reducing token costs, applying PDA, modularizing skills, breaking down skills, or converting encyclopedia-style skills to orchestrator pattern.
majiayu000/claude-skill-registry 163
-
ava-review
Review AXAML files for Avalonia best practices
majiayu000/claude-skill-registry 163
-
demo-skill
A demo skill that helps with documentation
majiayu000/claude-skill-registry 163
-
character-profile
基于故事文本分析人物特征，生成详细的人物小传。适用于深度理解故事人物设定、为演员塑造角色提供参考、为剧本创作建立人物档案
majiayu000/claude-skill-registry 163
-
resolve-git-issue
Resolve a GitHub issue by implementing a fix and tests; use when asked to fix an issue end-to-end.
majiayu000/claude-skill-registry 163
-
helpscout
Manage customer support with Help Scout's human-focused help desk.
majiayu000/claude-skill-registry 163
-
playwright-local
Build browser automation and web scraping with Playwright on your local machine. Prevents 10 documented errors including CI timeout hangs, extension testing failures, and Ubuntu compatibility issues. Includes stealth mode for anti-bot bypass, authenticated sessions, infinite scroll handling, screenshot/PDF generation, and v1.57 Speedboard performance analysis.
Use when: automating browsers, scraping protected sites, testing with real IPs, bypassing bot detection, generating screenshots/PDFs, or troubleshooting "target closed", "page.pause() hangs CI", "permission prompts block tests", or "Ubuntu 25.10 installation" errors.
majiayu000/claude-skill-registry 163
-
mcp-builder
Create high-quality MCP servers for LLM tool integration.
majiayu000/claude-skill-registry 163
-
agentuity-cli-cloud-thread-delete
Delete a thread. Requires authentication. Use for Agentuity cloud platform operations
majiayu000/claude-skill-registry 163
-
security-standards
Security standards for credential handling and authentication
majiayu000/claude-skill-registry 163
-
payment-integration
Integrate payments with SePay (VietQR, Vietnamese bank transfers) and Polar (global SaaS subscriptions, billing). Use for checkout flows, webhooks, QR codes, subscription management.
majiayu000/claude-skill-registry 163
-
moai-platform-railway
Railway container deployment specialist covering Docker, multi-service architectures, persistent volumes, and auto-scaling. Use when deploying containerized full-stack applications, configuring multi-region deployments, or setting up persistent storage.
majiayu000/claude-skill-registry 163
-
hono
Hono 4.x web framework patterns. Use when building APIs, middleware, routing, or server-side applications. Covers multi-runtime support (Node, Bun, Cloudflare Workers), validation, CORS, and error handling.
majiayu000/claude-skill-registry 163
-
google-adk
Guide for building AI agents with Google ADK (Agent Development Kit). Use when creating multi-agent pipelines, implementing conditional agent branching, designing agent tools with FunctionTool, or debugging agent data flow issues. Covers SequentialAgent, LoopAgent, ParallelAgent patterns, session.state management, output_key chaining, and transfer_to_agent for control flow. Essential for understanding non-obvious ADK behaviors like why SequentialAgent runs ALL agents even after rejection.
majiayu000/claude-skill-registry 163
-
tutorials
majiayu000/claude-skill-registry 163
-
create-ticket
Create implementation tickets with proper format and conventions.
majiayu000/claude-skill-registry 163
-
bookstrap-research
Execute research tasks autonomously by searching for sources, evaluating reliability, ingesting content, and resolving knowledge gaps
majiayu000/claude-skill-registry 163
-
vercel-cli-management
Manage Vercel deployments, projects, domains, and environment variables using Vercel CLI. Use when deploying Next.js applications, managing production/preview deployments, configuring custom domains, or troubleshooting Vercel-specific issues.
majiayu000/claude-skill-registry 163
-
grafana-billing
Query Prometheus and Loki billing metrics from Grafana. Use when discussing observability costs, active series, ingestion rates, storage usage, or cardinality analysis.
majiayu000/claude-skill-registry 163
-
bindcraft
End-to-end binder design using BindCraft hallucination. Use this skill when: (1) Designing protein binders with built-in AF2 validation, (2) Running production-quality binder campaigns, (3) Using different design protocols (fast, default, slow), (4) Need joint backbone and sequence optimization, (5) Want high experimental success rate.
For backbone-only generation, use rfdiffusion. For QC thresholds, use protein-qc. For tool selection guidance, use binder-design.
majiayu000/claude-skill-registry 163
-
boilerplate
Generate framework-specific boilerplate code
majiayu000/claude-skill-registry 163
-
content-discovery
Automated content discovery workflow for scanning multiple data sources
(ArXiv, GitHub, HuggingFace), applying AI-powered semantic filtering and
deduplication, analyzing content quality, downloading images, and publishing
to multiple channels (Hexo blog, Telegram, Discord).
Use this skill when:
- Executing /discover command with task configurations
- Scanning academic papers from ArXiv (via MCP or WebSearch)
- Finding GitHub repositories or HuggingFace models
- Applying semantic AI filtering to avoid duplicate content
- Generating high-quality Chinese summaries and insights
- Publishing structured content with metadata tracking
This skill handles the complete end-to-end discovery pipeline including
data source detection, content filtering, quality validation, image extraction,
and multi-channel publishing.
majiayu000/claude-skill-registry 163