research-record-audit SKILL.md skillA
research-record-audit from arasz/ai-badger is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add arasz/ai-badger/research-record-audit@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- arasz/ai-badger
- Path
features/common/skills/research-record-audit/SKILL.md- Versions recorded
- 5
- Latest version
- v1.0.0, committed Sep 11, 2026
- First version recorded
- Aug 7, 2026
- Size
- 9,692 bytes
- Repository stars
- 3
- License
- MIT
Use when auditing a research record's factual accuracy, citation truth, or grade correctness: adversarially re-derive every load-bearing claim from cited sources, verify quotes verbatim at cited lines, re-run MEASURED claims, audit grade honesty (INFERRED hedged, UNVERIFIED plain), check negative claims for prune/retention explanations, and report ACCURATE/CORRECTED/OVERCLAIMED.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Research Record Audit Adversarially verify a written record (research note, findings doc, review write-up, incident report, changelog) against its cited primary sources. Never trust the record: **re-derive every load-bearing claim from the sources**. The record's author already re-read their own reasoning — the errors live in the sources and in the summary layer, not in re-reading the prose twice. ## When to use - "Adversarially review the research record at <path> for factual accuracy and honesty" - Any request to check a findings document's claims, grades, or open questions against the files/DBs/commands it cites. - Delegated review of a research record for "citation truth, grade correctness, completeness" — the parent expects a verdict (APPROVE / APPROVE-WITH-CHANGES / REJECT) plus numbered findings tagged MUST-FIX / SHOULD-FIX / NIT with file:line on anything wrong. That shape is per-request; the ACCURATE/CORRECTED/OVERCLAIMED shape below is the other common one — ask which, or use the one the parent names. - Verifying a session's or subagent's written work before it ships (quality gate). ## Workflow …
Read the whole file at its exact version.
How to install
mdr add arasz/ai-badger/research-record-audit@sha256:59cd0731b1d1e667The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_aqefsdul577z6b3u)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Aug 7, 2026 and Sep 11, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-09-11 | c8da0f0 | 9,692 B | A | view · diff |
| v1.0.0 | 2026-08-08 | 9006bf5 | 9,690 B | A | view · diff |
| v1.0.0 | 2026-08-07 | 1c2539d | 9,677 B | A | view · diff |
| v1.0.0 | 2026-08-07 | 6c187e9 | 9,697 B | A | view · diff |
| v1.0.0 | 2026-08-07 | 7cebf20 | 9,804 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (9692 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
arasz/ai-badger · 3 stars · license MIT · pushed 2026-10-20 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_aqefsdul577z6b3u GET https://markdownregistry.com/api/v1/resolve?ref=arasz/ai-badger/research-record-audit GET https://markdownregistry.com/api/v1/blob/59cd0731b1d1e667ffd5170cd65c609eb8ba2520358e67e12db75be646909563
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.