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.
☆ 98Voir le skill
Explorer
Explorez des skills pour le développement, le contenu, les données et la productivité. Comparez les descriptions et dépôts.
Catégories
Explorer
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.
☆ 98Voir le 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.
☆ 98Voir le 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.
☆ 98Voir le 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.
☆ 98Voir le 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.
☆ 98Voir le 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.
☆ 98Voir le 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.
☆ 98Voir le 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...
☆ 98Voir le 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.
☆ 98Voir le 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.
☆ 98Voir le 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.
☆ 98Voir le skill
GitHub
implement
Full-power feature implementation with parallel subagents, skills, and MCPs. Use when implementing features, building features, creating features, or developing features.
☆ 98Voir le 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.
☆ 98Voir le 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.
☆ 98Voir le 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.
☆ 98Voir le skill
GitHub
brainstorming
Use when creating or developing anything, before writing code or implementation plans. Brainstorming skill refines ideas through structured questioning and alternatives.
☆ 98Voir le skill
GitHub
k8spods
Debug and troubleshoot pod issues including crashes, failures, networking, and resource problems
☆ 98Voir le skill
GitHub
flow-debugging
4-phase systematic debugging for flow-fix. NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.
☆ 97Voir le skill
GitHub
flow-finishing-branch
Decide how to complete a development branch: merge, PR, squash, or cleanup.
☆ 97Voir le 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...
☆ 97Voir le skill
GitHub
fractal-docs-generator
目录级 CLAUDE.md 生成。触发：mkdir、create directory、目录结构变更。
☆ 97Voir le 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。
☆ 97Voir le 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。
☆ 97Voir le skill
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.