Agent Skills Hub

c7

Fetches and caches up-to-date SDK and library documentation from Context7 for offline reference.

brightdata

Progressive four-tier URL content scraping with automatic fallback strategy for bypassing bot detection and access restrictions.

beads-workflow

A workflow methodology for converting complex markdown plans into granular, dependency-aware task 'beads' to optimize agent swarm implementation.

atomic-execution

An atomic execution engine that decomposes complex tasks into isolated, verification-gated XML plans to prevent context degradation and maintain architectural integrity.

anthropic-sdk

Integrate Claude AI into your applications with the Anthropic SDK. Supports Messages API, streaming, tool use (function calling), vision, extended thinking, and system prompts.

alignfirst

Collaborative AI protocols for technical specifications, implementation plans, code reviews, and PR descriptions using a structured directory-based workflow.

ai-llm-engineering

Operational hub for LLM system lifecycle, architecture, and deployment. Features include PEFT/LoRA fine-tuning, RAG pipelines, vLLM throughput optimization, automated drift detection, and CI/CD-integrated evaluation frameworks.

massive-context-mcp

Process massive files and large codebases (10M+ tokens) by recursively chunking, sub-querying, and aggregating results to overcome LLM context limits.

gemini-video-understanding

Perform advanced video analysis using Google's Gemini API: summarize content, transcribe audio, extract timestamps, clip segments, and analyze YouTube URLs or local files with support for multiple models and long contexts.

tavily-tools

Unified Python CLI for Tavily AI operations including web search, URL extraction, site crawling, link mapping, and automated deep research reports.

claude-rag-skills

A suite of professional tools for auditing, evaluating, chunking, and scaffolding production-ready RAG pipelines within Claude Code.

ai-llm-patterns

Anthropic Claude integration patterns: streaming, RAG with pgvector, tool use, model selection (Haiku/Sonnet/Opus), prompt caching, and cost management for AI-powered engineering.