GitHub
contextual-retrieval
Anthropic's Contextual Retrieval technique for improved RAG. Use when chunks lose context during retrieval, implementing hybrid BM25+vector search, or reducing retrieval failures.
☆ 98View skill
Browse skills
Explore AI skills for development, content, data and productivity. Compare the description and repository popularity before opening a skill.
Categories
Browse skills
GitHub
agentic-rag-patterns
Advanced RAG with Self-RAG, Corrective-RAG, and knowledge graphs. Use when building agentic RAG pipelines, adaptive retrieval, or query rewriting.
☆ 98View skill
GitHub
prompt-engineering-suite
Comprehensive prompt engineering with Chain-of-Thought, few-shot learning, prompt versioning, and optimization. Use when designing prompts, improving accuracy, managing prompt lifecycle.
☆ 98View skill
GitHub
context-compression
Use when conversation context is too long, hitting token limits, or responses are degrading. Compresses history while preserving critical information using anchored summarization and probe-based validation.
☆ 98View skill
GitHub
mem0-memory
Long-term semantic memory across sessions using Mem0. Use when you need to remember, recall, or forget information across sessions, or when referencing what we discussed last time or in a previous session.
☆ 98View skill
GitHub
langfuse-observability
LLM observability platform for tracing, evaluation, prompt management, and cost tracking. Use when setting up Langfuse, monitoring LLM costs, tracking token usage, or implementing prompt versioning.
☆ 98View skill
GitHub
high-performance-inference
High-performance LLM inference with vLLM, quantization (AWQ, GPTQ, FP8), speculative decoding, and edge deployment. Use when optimizing inference latency, throughput, or memory.
☆ 98View skill
GitHub
cache-cost-tracking
LLM cost tracking with Langfuse for cached responses. Use when monitoring cache effectiveness, tracking cost savings, or attributing costs to agents in multi-agent systems.
☆ 98View skill
GitHub
mcp-server-building
Building MCP (Model Context Protocol) servers for Claude extensibility. Use when creating MCP servers, building custom Claude tools, extending Claude with external integrations, or developing tool packages for...
☆ 98View skill
GitHub
langgraph-supervisor
LangGraph supervisor-worker pattern. Use when building central coordinator agents that route to specialized workers, implementing round-robin or priority-based agent dispatch.
☆ 98View skill
GitHub
golden-dataset-curation
Use when creating or improving golden datasets for AI evaluation. Defines quality criteria, curation workflows, and multi-agent analysis patterns for test data.
☆ 98View skill
GitHub
multimodal-rag
CLIP, SigLIP 2, Voyage multimodal-3 patterns for image+text retrieval, cross-modal search, and multimodal document chunking. Use when building RAG with images, implementing visual search, or hybrid retrieval.
☆ 98View skill
GitHub
implement
Full-power feature implementation with parallel subagents, skills, and MCPs. Use when implementing features, building features, creating features, or developing features.
☆ 98View skill
GitHub
langgraph-checkpoints
LangGraph checkpointing and persistence. Use when implementing fault-tolerant workflows, resuming interrupted executions, debugging with state history, or avoiding re-running expensive operations.
☆ 98View skill
GitHub
prompt-caching
Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token costs for repeated prefixes.
☆ 98View skill
GitHub
alternative-agent-frameworks
Multi-agent frameworks beyond LangGraph. CrewAI crews, Microsoft Agent Framework, OpenAI Agents SDK. Use when building multi-agent systems, choosing frameworks.
☆ 98View skill
GitHub
brainstorming
Use when creating or developing anything, before writing code or implementation plans. Brainstorming skill refines ideas through structured questioning and alternatives.
☆ 98View skill
GitHub
k8spods
Debug and troubleshoot pod issues including crashes, failures, networking, and resource problems
☆ 98View skill
GitHub
flow-debugging
4-phase systematic debugging for flow-fix. NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.
☆ 97View skill
GitHub
flow-finishing-branch
Decide how to complete a development branch: merge, PR, squash, or cleanup.
☆ 97View skill
GitHub
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before as...
☆ 97View skill
GitHub
fractal-docs-generator
目录级 CLAUDE.md 生成。触发：mkdir、create directory、目录结构变更。
☆ 97View skill
GitHub
file-header-guardian
文件头三行契约注释。触发：create file、新建文件、编写代码。
☆ 97View skill
GitHub
flow-attention-refresh
注意力刷新协议。在关键时刻强制读取核心文档，防止目标遗忘。被 flow-dev, flow-ralph 等命令引用。
☆ 97View skill
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.