release-audit
Skill1 starsChanged 4 months agoMITView on GitHub
Audit a RigorGraph project before release and produce a local read-only claim-evidence report. Use when preparing a tag, paper, dataset, benchmark, public repository, handoff, or other research release.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- Nizoka/pkinative-mcptheir own version, first seen Nov 1, 2026
- mono/SkiaSharptheir own version, first seen Oct 8, 2026
- newton-physics/newtontheir own version, first seen Oct 8, 2026
- Nizoka/pdfnative-mcptheir own version, first seen Sep 21, 2026
- Akikukeo1/alignment-under-pressure-benchmarktheir own version, first seen Sep 1, 2026
- Omerfaruk-aydn/Agent_OStheir own version, first seen Jul 20, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- newton-physics/newton★ 5.9ksame name
- mono/SkiaSharp★ 5.6ksame name
- Nizoka/pdfnative-mcp★ 2same name
- Akikukeo1/alignment-under-pressure-benchmark★ 1same name
- Omerfaruk-aydn/Agent_OS★ 1same name
- Nizoka/pkinative-mcp★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- adversarial-verifySkill
- capture-claimSkill
- research-intakeSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Read the project config and all .rigorgraph/ records.
- Very specific: line 9
Run rigorgraph audit --json and preserve its stable English codes and enums in machine output.
- Distinctive: line 10
Treat every error as release-blocking.
- Very specific: line 12
Run rigorgraph report --output rigorgraph-report.html and confirm the offline report opens without network access.
“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Release audit
- Read the project config and all
.rigorgraph/records. Reply in the explicit or configured language: English, Traditional Chinese, Simplified Chinese, or Japanese. - Run
rigorgraph audit --jsonand preserve its stable English codes and enums in machine output. - Treat every error as release-blocking. Do not waive missing evidence, self-verification, invalid dependency status, hash mismatch, invalid imported bundle, or cycle failures.
- Review open
DRAFT,PROPOSED,UNDER_REVIEW, andUNCERTAINclaims. Ensure release copy does not present them as verified results. - Run
rigorgraph report --output rigorgraph-report.htmland confirm the offline report opens without network access. - For imported bundles, confirm the report preserves producer, profile, result, and provenance boundaries without presenting them as independent truth or authentication.
- Report the audit status, blocking issues, limitations, report path, and release recommendation. Do not publish, tag, push, or post without explicit authorization.
Use localized headings:
| en | zh-TW | zh-CN | ja |
| Audit status | 稽核狀態 | 审计状态 | 監査状態 |
| Blocking issues | 阻擋問題 | 阻塞问题 | ブロッキング問題 |
| Evidence limitations | 證據限制 | 证据限制 | 証拠の限界 |
| Release recommendation | 發布建議 | 发布建议 | リリース推奨 |
Passing deterministic checks does not establish that every research claim is true.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.