Agent Skills Hub

langgraph

Expert LangGraph architect skill for designing stateful, multi-actor AI agent workflows with robust persistence, conditional branching, and ReAct patterns.

find-skills

Discover and install agent skills to extend your DeerFlow capabilities. Use this to find tools, workflows, or specialized knowledge for tasks like coding, testing, and deployment.

nano-pdf

Edit and modify PDF documents using natural-language instructions via the nano-pdf command-line interface.

use-railway

Operate Railway infrastructure: manage projects, services, databases, object storage, deployments, environments, variables, logs, and performance metrics.

inno-prepare-resources

Automates research resource preparation by loading instances, searching GitHub for codebases, building dataset descriptions, and downloading arXiv papers.

context-degradation

Diagnose, isolate, and mitigate LLM context failures like lost-in-middle, poisoning, distraction, and context clash to improve agent reliability.

tavily-web

Advanced web search, content extraction, and site crawling capabilities using the Tavily API, optimized for AI agent research and data gathering.

qras

A local RAG semantic memory system using Qdrant and Ollama. Ideal for recalling workspace files, notes, project decisions, and user preferences with high-relevance vector search.

shadcn-ui

Implement shadcn/ui components: installation, Vite/TanStack Router configuration, CLI command management, and Tailwind CSS integration.

tpmjs-tool-creator

Development guide for creating and publishing TPMJS tools using the blocks CLI, AI SDK v6, and npm registry patterns.

debug-hooks

Systematic debugging workflow for Claude Code hooks. Use to troubleshoot non-firing hooks, output errors, or unexpected behavioral issues.

doc-coauthoring

A structured workflow for co-authoring documentation, technical specs, and proposals, guiding users through context gathering, collaborative refinement, and reader verification.