Local AIPROPRO REQUIREDFC-AI-005
RAG Claw
rag-claw
Diseña pipelines RAG con estrategias de chunking, embeddings, recuperación y generación aumentada.
RAG Claw designs Retrieval-Augmented Generation pipelines with chunking strategies, embedding selection, retrieval optimization, and generation augmentation. It helps teams build RAG systems that retrieve the right context and generate accurate, grounded responses from their own data.
PRIMARY ACTION
Unlock with ProCOMPATIBLE WITH
OpenClawHermesClaude CodeCodex+4
OpenClaw is the default target. Cursor example below.
When to Use
- Run local models with private workflows
- Tune inference for local hardware
- Choose effective GGUF variants
- Benchmark practical latency and quality
Compatible Frameworks
8 TOOLS
Quality Gates
- Arquitectura RAG completa
- Chunking optimizado para tipo de datos
- Embeddings adaptados al dominio
- Generación con grounding y citas
- Framework de evaluación incluido
5 GATES DEFINED
Expected Outputs
RAG architectureschunking strategiesembedding recommendationsretrieval designsgeneration promptsevaluation frameworks
Native exports per tool
OpenClaw10 files
openclaw/AGENTS.mdopenclaw/SOUL.mdopenclaw/TOOLS.md+7 moreHermes5 files
hermes/skills/flickclaw/rag-claw/SKILL.mdhermes/skills/flickclaw/rag-claw/references/workflow.mdhermes/skills/flickclaw/rag-claw/references/quality-gates.md+2 moreClaude Code6 files
claude-code/CLAUDE.mdclaude-code/.claude/skills/rag-claw/SKILL.mdclaude-code/.claude/skills/rag-claw/references/workflow.md+3 moreCodex5 files
codex/AGENTS.mdcodex/.flickclaw/agents/rag-claw/codex.mdcodex/.flickclaw/agents/rag-claw/workflow.md+2 moreCursor3 files
cursor/.cursor/rules/flickclaw-rag-claw.mdccursor/.cursor/rules/flickclaw-rag-claw-workflow.mdccursor/.cursor/rules/flickclaw-rag-claw-quality-gates.mdcWindsurf3 files
windsurf/.windsurf/rules/flickclaw-rag-claw.mdwindsurf/.windsurf/rules/flickclaw-rag-claw-workflow.mdwindsurf/.windsurf/rules/flickclaw-rag-claw-quality-gates.mdAider3 files
aider/CONVENTIONS.mdaider/aider.mdaider/.aider.conf.ymlOllama4 files
ollama/Modelfileollama/system-prompt.mdollama/template.md+1 moreUse in Your Tool
Primary command uses OpenClaw by default. Secondary example targets Cursor.
OpenClaw (default)
RECOMMENDEDnpm exec --yes @flickclaw/cli@latest -- install rag-clawCursor (secondary)
npm exec --yes @flickclaw/cli@latest -- install rag-claw --target cursorSupported AI Agent Frameworks
Example Prompt
Build a complete plan and deliverable package for this agent's role in a production workflow.