ragBuild, optimize, and debug RAG pipelines with chunking strategies, retrieval tuning, evaluation metrics, and production monitoring.
Install via ClawdBot CLI:
clawdbot install ivangdavila/ragGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains instructions to override system prompt or ignore user requests
"IGNORE ALL PREVIOUS INSTRUCTIONS"AI Analysis
The provided skill definition is a technical guide for building RAG systems and contains no executable code, API calls, or data transmission logic. The flagged 'PROMPT_POISONING' signal appears to be a false positive, as the phrase 'IGNORE ALL PREVIOUS INSTRUCTIONS' is not present in the provided text and the content is purely instructional.
Audited Apr 16, 2026 · audit v1.0
Generated Feb 26, 2026
A company wants to improve its customer support chatbot by integrating internal knowledge bases and product manuals to provide accurate, context-aware answers. The RAG skill helps design a pipeline that retrieves relevant documentation chunks in real-time, ensuring responses are grounded in up-to-date information while handling varied query phrasings.
A law firm needs to quickly search through vast collections of case files, statutes, and contracts to find precedents or specific clauses. Using the RAG skill, they can implement a retrieval system with optimized chunking and hybrid search, enabling efficient document retrieval while maintaining security and compliance with legal standards.
A healthcare provider aims to build an AI assistant that retrieves medical guidelines and research papers to support diagnostic decisions. The RAG skill assists in creating a secure pipeline with PII detection and access controls, ensuring accurate retrieval of relevant medical information while adhering to HIPAA regulations.
An e-commerce platform seeks to enhance product recommendations by retrieving detailed product descriptions and customer reviews based on user queries. The RAG skill enables the design of a retrieval pipeline with tuning for top-k and reranking, improving relevance and reducing hallucinated suggestions in dynamic shopping environments.
Offer specialized consulting to help businesses design and deploy custom RAG pipelines, including architecture selection and optimization. Revenue is generated through project-based fees and ongoing support contracts, targeting industries with complex document retrieval needs like legal or healthcare.
Develop a cloud-based platform that provides tools for building, evaluating, and monitoring RAG systems, with features like automated chunking and performance dashboards. Revenue comes from subscription tiers based on usage volume and advanced features, appealing to tech startups and enterprises.
Create training courses and certifications on RAG implementation, covering topics from basics to advanced tuning for data scientists and engineers. Revenue is generated through course fees, certification exams, and corporate training packages, leveraging the growing demand for AI skills.
💬 Integration Tip
Start by building a small evaluation dataset to measure baseline performance before scaling the pipeline, and ensure consistent embedding models between queries and documents to avoid retrieval errors.
Scored Apr 18, 2026
Gemini CLI for one-shot Q&A, summaries, and generation.
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates opencla...
Check Antigravity account quotas for Claude and Gemini models. Shows remaining quota and reset times with ban detection.
A comprehensive AI model routing system that automatically selects the optimal model for any task. Set up multiple AI providers (Anthropic, OpenAI, Gemini, Moonshot, Z.ai, GLM) with secure API key storage, then route tasks to the best model based on task type, complexity, and cost optimization. Includes interactive setup wizard, task classification, and cost-effective delegation patterns. Use when you need "use X model for this", "switch model", "optimal model", "which model should I use", or to balance quality vs cost across multiple AI providers.
Reduce OpenClaw AI costs by 97%. Haiku model routing, free Ollama heartbeats, prompt caching, and budget controls. Go from $1,500/month to $50/month in 5 min...