Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    RAG Hallucination Root-Cause Analyzer

    1

    Diagnose RAG hallucinations, retrieval failures, and citation errors with a structured root-cause audit.

    $14.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    RAG Hallucination Root-Cause Analyzer

    RAG Hallucination Root-Cause Analyzer

    Example session with this skill installed

    Analyze this RAG trace: User asked for 2024 pricing, but the answer cited 2022 docs despite the 2024 PDF being in the corpus. Here are the retrieval logs and my chunking config.

    • Read your context and instructions
    • Compiled the rag hallucination root-cause

    Root Cause: Freshness & Metadata Filtering. The retriever found the 2024 doc, but the Reranker (Top-3) prioritized the 2022 doc due to higher keyword density. Remediation: Implement a recency-weighted reranking score and add a 'is_superseded' metadata flag to the indexing pipeline.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    RAG pipelines often produce fluent but factually incorrect or poorly cited answers, making them risky for production. Developers frequently struggle to pinpoint whether the failure lies in the chunking strategy, vector retrieval, reranking logic, or the prompt itself.

    What it does

    • Identifies the exact failure stage across the 21-point RAG lifecycle, from corpus quality to citation binding.
    • Performs a design-level audit of chunking configurations, metadata schemas, and retrieval logs to find hidden bottlenecks.
    • Diagnoses specific grounding issues like lost-in-the-middle context, stale index skew, and citation fabrication.
    • Produces a 100-point grounding score and a severity-ranked remediation plan for engineering teams.

    Frameworks & tools

    Compatible with any RAG stack including Pinecone, Weaviate, Milvus, LangChain, LlamaIndex, and various embedding models.

    Why this beats prompting it yourself

    General LLMs often overlook subtle retrieval-stage failures like metadata over-filtering or embedding dimension mismatches. This skill enforces a structured 23-step diagnostic workflow that separates symptoms from root causes, ensuring no stage of the pipeline is ignored.

    Use cases

    • Pre-release safety audits to determine if a RAG workflow is ready for production.
    • Debugging specific user reports of hallucinations or missing citations in search results.
    • Optimizing chunk size and overlap configurations based on evidence-span requirements.
    • Establishing an evaluation matrix for multi-hop questions or complex document sets.

    Known limitations

    This skill does not query live production systems, execute retrieval scripts, or modify vector indexes directly. It relies on provided logs, configurations, and document samples for analysis.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    Does not execute code, query live databases, or modify indexes. Analysis is based on provided logs, configs, and traces. Limited to one coherent RAG workflow per run.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    Permissions

    No special permissions declared or detected

    Listed3 months ago

    What's inside

    Frequently Asked Questions

    You provide the skill with your RAG logs, chunking configurations, and specific examples of failed queries. It then performs a structured audit to determine if the failure occurred during retrieval, reranking, or the generation phase.

    This skill is platform-agnostic and works with any RAG architecture, including those built on LangChain, LlamaIndex, Pinecone, Weaviate, and Milvus. It analyzes the logic and output of your stack rather than requiring direct API access to your production environment.

    Unlike general prompts, this skill uses a specialized 23-step diagnostic workflow designed to identify subtle technical issues like metadata over-filtering and embedding mismatches. It provides a structured 100-point grounding score and a prioritized remediation roadmap that goes beyond simple 'pass/fail' feedback.

    No, this skill operates as a diagnostic auditor. It analyzes your provided data to find the root cause of errors, but it does not directly modify your vector index or execute live retrieval scripts, ensuring your production environment remains secure and unchanged.

    Your purchase includes the full diagnostic skill, the 21-point RAG lifecycle audit framework, and lifetime access to any logic updates or version improvements released by the developer.

    New in Agents & Orchestration