← Back to Skills Marketplace
Rag Accuracy Optimizer
by
eddie Luong
· GitHub ↗
· v1.3.0
· MIT-0
129
Downloads
0
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install rag-accuracy-optimizer
Description
Optimize accuracy for RAG (Retrieval-Augmented Generation) systems. Covers: DB schema design, chunking strategies, retrieval optimization, accuracy testing,...
Usage Guidance
This skill contains substantial, plausible RAG guidance and runnable Python scripts, but the package metadata currently omits the many provider keys and connection strings the code references. Before installing or running: (1) ask the publisher to list required environment variables and config (OpenAI/Gemini/Anthropic/Cohere API keys, Qdrant/Postgres URLs, DB credentials, etc.); (2) review the included scripts (scripts/*.py) locally to confirm there are no unexpected network endpoints or hardcoded URLs; (3) run the code in a sandbox or isolated environment and provide only least-privilege credentials (use test accounts or scoped API keys); (4) if you plan to let the agent call the skill autonomously, be cautious—LLM prompts in the skill mention system prompts and injection testing, so verify the orchestration code won't leak sensitive content (system prompts, secrets) to external models; (5) consider scanning the code for outbound network calls (requests.post, socket, subprocess, etc.) and restrict network access if you cannot audit thoroughly. If the owner cannot or will not clarify the missing credential declarations, treat the omission as a red flag and prefer not to enable the skill in production.
Capability Assessment
Purpose & Capability
Name, description, and included reference docs/scripts align with an end-to-end RAG accuracy optimizer: chunking, embeddings, hybrid retrieval, reranking, evaluation frameworks and orchestrator patterns. The presence of examples for multiple embedding providers, rerankers, and vector DBs is coherent with the stated purpose.
Instruction Scope
SKILL.md and the reference files contain concrete runtime instructions and code to call embedding/LLM providers, DB clients, and run evaluation pipelines. That scope is appropriate for a RAG optimizer, but parts of the SKILL.md include prompt-injection examples/patterns and LLM prompts — these are probably defensive (detection) patterns but flagged by pre-scan. Also the instructions and examples reference environment variables and external endpoints (OpenAI/Gemini/Anthropic/Cohere, qdrant, Postgres) that are not declared in the registry metadata.
Install Mechanism
This is instruction-first with no install spec. No remote downloads or install scripts are specified, which reduces supply-chain risk. Code files are included in the skill bundle (Python scripts) but nothing in the manifest indicates an installer that would fetch remote code at install time.
Credentials
Registry lists no required env vars or credentials, yet numerous code examples and scripts reference provider keys and connection strings (e.g., OPENAI_API_KEY, GEMINI_API_KEY, ANTHROPIC_API_KEY, Cohere key, Qdrant/Postgres connection info). That mismatch is an incoherence risk: the skill will need multiple external credentials to run as documented but does not declare them. Additionally, the examples suggest connecting to DBs and external services—ensure any keys used are least-privilege and that you understand where network traffic will go.
Persistence & Privilege
The skill does not request always:true, does not declare changes to platform-wide configuration, and is user-invocable. No elevated persistence or forced-inclusion privileges are requested in the manifest.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install rag-accuracy-optimizer - After installation, invoke the skill by name or use
/rag-accuracy-optimizer - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.3.0
**v1.3.0 summary: Major update with expanded references, enriched retrieval/testing scripts, and English documentation.**
- Updated documentation in English for broader accessibility (SKILL.md and references).
- Expanded and clarified advanced RAG, chunking, embedding, retrieval, and orchestrator pattern guides.
- Added or improved accuracy testing, chunk optimization, and embedding benchmarking scripts.
- Enhanced coverage for metadata schemas and domain-specific patterns.
- Improved evaluation and testing framework reference files.
- Broader vector DB and Vietnam NLP guidance.
v1.2.0
**Changelog for rag-accuracy-optimizer v1.2.0:**
- Added orchestrator patterns reference (`references/orchestrator-patterns.md`) to complement the main skill documentation.
- Updated SKILL.md to reference the new orchestrator documentation.
- No major changes to workflow or examples in the main documentation; overall structure and guidance remain consistent.
v1.1.0
Version 1.1.0 — Major update with expanded reference materials and test scripts.
- Added comprehensive reference documents: advanced RAG techniques, embedding models, testing frameworks, vector DB comparisons, and Vietnamese NLP.
- Introduced new scripts for embedding benchmarking and RAGAS evaluation.
- Expanded resources to support learning and experimenting with RAG system optimization.
- Improved overall guidance and breadth for RAG accuracy tuning workflows.
v1.0.0
Initial release of RAG Accuracy Optimizer — a comprehensive guide for maximizing accuracy in Retrieval-Augmented Generation (RAG) systems.
- Covers end-to-end workflow: data/schema design, chunking strategies, retrieval optimization, accuracy evaluation, and production safeguards.
- Provides sector-specific schema design patterns (insurance, finance, healthcare, e-commerce) and detailed metadata strategies.
- Outlines best practices in chunking: semantic, hierarchical, domain-specific, overlap, and chunk enrichment.
- Presents retrieval optimization pipeline: query rewriting, multi-query, hybrid search (vector + BM25), reranking, contextual compression, and filtering.
- Includes practical recommendations for SQL vs Vector DB usage, normalization, and monitoring for deployment.
Metadata
Frequently Asked Questions
What is Rag Accuracy Optimizer?
Optimize accuracy for RAG (Retrieval-Augmented Generation) systems. Covers: DB schema design, chunking strategies, retrieval optimization, accuracy testing,... It is an AI Agent Skill for Claude Code / OpenClaw, with 129 downloads so far.
How do I install Rag Accuracy Optimizer?
Run "/install rag-accuracy-optimizer" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Rag Accuracy Optimizer free?
Yes, Rag Accuracy Optimizer is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Rag Accuracy Optimizer support?
Rag Accuracy Optimizer is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Rag Accuracy Optimizer?
It is built and maintained by eddie Luong (@eddieluong); the current version is v1.3.0.
More Skills