More screenshots
Works with the AI Agents you already use
🧠Retrieval Trace Auditor
Audit real RAG evidence traces for missing expected sources, impossible citations, unsupported claims, stale evidence, unused context, and weak routing.
$15
🧠Retrieval Trace Auditor
Example session with this skill installed
{"case_id":"policy-17","query_class":"temporal","route":"vector_only","retrieved_evidence":[{"id":"policy-2024","superseded_by":"policy-2026"}],"expected_evidence_ids":["policy-2026"],"cited_evidence_ids":["citation-ghost"],"claims":[{"claim_id":"claim-1","text":"The 2026 policy replaced the rule.","supporting_evidence_ids":["support-ghost"]}]}
- Read your context and instructions
- Compiled the retrieval trace auditor
Release gate: FAIL
Critical: citation-ghost was cited but never retrieved.
Critical: claim-1 declares support-ghost, which was never retrieved.
High: policy-2026 was expected but absent; temporal query used vector_only.
Boundary: semantic entailment and answer correctness remain unverified.
Connects securely to your tools. The creator never sees your data.
About this skill
Retrieval Trace Auditor inspects the evidence path behind a RAG or knowledge-agent answer. Supply structured JSONL cases with stable retrieved evidence IDs, expected evidence when known, citations, answer claims, declared support IDs, query class, and route. The included deterministic local helper detects expected evidence that was not retrieved, citations or claim support that never appeared in context, claims with no declared support, stale selected evidence, unused retrieved context, and temporal or relational questions routed through vector-only retrieval. It returns severity-ranked findings, per-case dispositions, a release gate, and a review memo. It deliberately does not claim to judge semantic entailment or factual correctness.
ID consistency does not prove that source text semantically entails a claim. Expected evidence is trustworthy only when an authoritative fixture or qualified reviewer established it. The input must expose stable evidence IDs and structured claim support; opaque answer-only logs cannot support the full audit.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
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 24 days ago
Permissions
File Scopes
The helper reads supplied trace JSONL and writes findings, case summaries, JSON, and Markdown locally. It does not call an LLM, vector store, observability platform, or external service.