- Home
- Skills
- Technical Documentation
- Evidence Guard
Works with the AI Agents you already use
Evidence Guard
Fact-check AI-generated output before it ships: verifies every factual and technical claim against its real source and flags anything unsupported.
$14
Evidence Guard
Example session with this skill installed
Verify the Node version and performance claims in the README and docs/api.md against our package.json and bench results before I ship this release.
- Read your context and instructions
- Compiled the evidence guard
VERIFICATION NOTE — 5 claims checked.
CRITICAL: README:12 — "Supports Node 16" — engines in package.json requires >=18.0.0.
WARNING: docs/api.md — "ultra-low latency" — No benchmark data found to support quantitative claim.
VERDICT: FAIL — 1 critical version mismatch.
Connects securely to your tools. The creator never sees your data.
About this skill
evidence-guard brings regulated-industry evidence standards — the same rigor used to pass medical and scientific MLR and peer review — to any AI-generated output. Before your agent ships documentation, READMEs, PR descriptions, API references, changelogs, or technical claims, evidence-guard forces it to prove every assertion against a real, verifiable source.
The problem: AI agents write confident, plausible text that quietly contains unsupported claims — wrong version numbers, deprecated API references, performance figures with no benchmark, and documentation that drifts away from the actual code. A single model reviewing its own work rarely catches these, because the same bias that produced the claim approves it.
evidence-guard fixes this at the level of substance, not just process. It runs a structured Claims-QC pass: it extracts every factual, technical, and quantitative claim from the output, classifies each one, verifies it against the repo or a citable source, grades the strength of the evidence, and flags risk patterns like version mismatches and doc-vs-code drift. Nothing passes the verdict gate until every critical claim is traceable. The result is a short, audit-ready Verification Note you can drop into a PR or a docs review.
Built by PubsProToolkit, applying the evidence discipline of medical and scientific publishing to everyday agent output.
- Cannot run code for runtime behavior.
- Requires read access to files/sources.
- Opinion-based claims are advisory and cannot be hard-verified.
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
2 uses
Times used to date
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 months ago
Requires
Permissions
No special permissions declared or detected