Evidence Integrity Suite
Four skills that give any AI agent end-to-end evidence integrity: grade source quality, ground every claim to a real source, stress-test the output adversarially, and audit the final draft for unsupported claims before it ships. Built for teams that can't afford hallucinations.
Works with every agent that reads SKILL.md — Claude Code, Cursor, Codex CLI, Gemini CLI, GitHub Copilot, Windsurf, OpenClaw, and more.
One payment, lifetime access. 4 skills unlock instantly in your library.
30-day refund guarantee
Instant unlock in your library
Free updates from the creator
What's included
4 skills
A reusable rubric that grades every source by type, recency, authority, independence, and corroboration, then ranks them and resolves conflicts by evidence weight.
Audit any AI-generated output for unsupported claims, then verify every factual and technical assertion against its real source before it ships.
Audits any AI draft for unsupported claims — flags each one, grades its source, and returns a substantiation report.
An adversarial self-review gate that hunts your agent's weakest claim, overclaims, and missing limitations before a human sees the output.
See it in action
You say
Grade these sources for the question: "What is the current API rate limit?"
- docs.vendor.com/api-reference - official API reference, updated this quarter: "100 requests/minute per key."
- Vendor engineering blog, 6 months old: explains the 100 req/min limit.
- Third-party tutorial blog, 2022, aggregator site: "the API allows 60 requests/minute."
Your agent does
SOURCE LEDGER Question: What is the current API rate limit?
[A] Official API reference (updated this quarter) Primary, current, authoritative, independent, corroborated -> RELY ON [B] Vendor engineering blog (6 months old) Secondary, slightly dated, non-independent -> CORROBORATE (matches A) [C] Third-party tutorial citing an older limit (2022 aggregator) Tertiary, stale, uncorroborated -> AVOID (superseded by A)
CONFLICT: C states 60 req/min; A states 100 req/min. RESOLUTION: A wins (primary, current). No open conflicts. RECOMMENDATION: Base the answer on A; cite the changelog for corroboration.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.