rag-accuracy-optimizerOptimize accuracy for RAG (Retrieval-Augmented Generation) systems. Covers: DB schema design, chunking strategies, retrieval optimization, accuracy testing,...
Install via ClawdBot CLI:
clawdbot install eddieluong/rag-accuracy-optimizerGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Contains instructions to override system prompt or ignore user requests
"Ignore previous instructions"Potentially destructive shell commands in tool definitions
eval (Uses known external API (expected, informational)
raw.githubusercontent.comAI Analysis
The skill definition is a technical guide for RAG system design and contains no executable code or active instructions. The rule-based signals appear to be false positives triggered by example code snippets or hypothetical commands within the documentation, not by operational payloads. The external URL reference is to a common, public raw GitHub domain, typical for referencing example files.
Generated Oct 7, 2026
A customer support RAG system for an insurance company that retrieves policy clauses, exclusions, and coverage details to answer agent and customer questions. The skill's schema patterns and semantic clause-based chunking improve answer precision while reducing hallucinated coverage claims. Metadata tagging by policy_id and clause_number enables traceable citations.
An analyst-facing RAG platform that indexes SEC filings, earnings reports, and market research to answer queries about tickers, periods, and financial metrics. The skill's SQL + vector hybrid design combines numeric aggregation from PostgreSQL with semantic search over report sections. Reranking and multi-query retrieval ensure accurate, citation-backed answers.
A healthcare RAG system that helps clinicians quickly retrieve treatment guidelines, drug interactions, and evidence levels from medical literature. Domain-specific chunking (1 chunk per recommendation) and metadata filters on condition and severity reduce irrelevant results. Anti-hallucination safeguards are critical in this high-stakes regulated environment.
A shopping assistant that answers customer questions about product specs, reviews, and comparisons using RAG over catalog data. The skill's hybrid retrieval combines SQL for exact facts (price, SKU) with vector search for semantic review matching. Metadata like product_id and category enables pre-filtering to accelerate search and improve relevance.
A legal-tech RAG tool that lets attorneys query contracts, clauses, and precedents across large document repositories. Article-and-clause chunking plus hierarchical parent-child retrieval gives both granular matches and broader contract context. Retrieval testing and monitoring modules ensure reliable, auditable answers for compliance-sensitive workflows.
A cloud-hosted RAG accuracy platform offered via monthly or annual subscriptions, tiered by document volume, query throughput, and advanced features like reranking and monitoring. Customers integrate via APIs and SDKs, and the platform continuously optimizes chunking and retrieval for their domains. This model suits enterprises that want a managed solution without building RAG infrastructure in-house.
On-premise or VPC-deployed licensing of the RAG optimizer for large organizations with strict data residency, security, or compliance requirements (e.g., banks, hospitals). The package includes schema design consulting, custom chunking strategies, and ongoing accuracy tuning. Annual license fees are supplemented by premium support and professional services.
A project-based consulting model where experts use the skill to design and optimize client RAG pipelines end-to-end — from DB schema and chunking strategy to retrieval tuning and accuracy testing. Deliverables include architecture blueprints, evaluation reports, and production safeguards. This model targets companies that already have engineering teams but need specialized RAG expertise.
💬 Integration Tip
Start by mapping your domain data to the skill's schema patterns and metadata tagging strategy, then implement chunking and hybrid retrieval before layering in accuracy testing and monitoring. Use the reference files for chunking code and iterate on retrieval parameters based on measured precision and recall.
Scored Oct 7, 2026
Audited Apr 17, 2026 · audit v1.0
Generate ideas fast. Adapt depth and structure to what the user actually needs.
Evaluate any AI skill's quality through step-by-step diagnosis — measuring trigger accuracy, per-step execution (completion/correctness/quality), efficiency,...
通过调用 Prana 平台上的远程 agent 完成以下处理:基于100个热门TradingView Pine Script指标转换的Python技术分析工具集,提供专业的技术指标计算、分析和可视化功能 IMPORTANT: This skill has a mandatory step-by-step proc...
Provides a structured screening for stress perception using the PSS-10 scale as an independent skill in ClawHub.
Spawns real AI-powered OpenClaw sub-sessions to run multiple specialized agents concurrently for content, dev, QA, docs, and autonomous workflows.
Provides comprehensive analysis and comparison of global AI regulations, safety incidents, model evaluations, standards, and international governance for pol...