paper-integrity-audit
Skill9 starsChanged 3 months agoNo licenceView on GitHub
Zero-context cross-model audit of paper integrity before submission. Routes to four complementary audit packs depending on what to verify: (1) citation-audit — bibliography integrity (hallucinated authors, wrong years, fabricated venues, wrong-context citations), (2) paper-claim-audit — every number, comparison, and scope claim against raw result files, (3) experiment-audit — experimental integrity (fake ground truth, normalization fraud, phantom results, insufficient scope), (4) result-to-claim — judge what claims experimental results actually support vs what they don't. All four use fresh cross-model reviewer threads (via Codex MCP) with NO prior context to prevent confirmation bias. Use before submission, before sending to advisor, or whenever you need a hard integrity check. Triggers: audit paper, check citations, verify references, citation audit, check claims, verify numbers, experiment audit, integrity check, result audit, 审查引用, 审查数据, 实验诚实度, 审计实验, 论文数字核对, 引用核对, claim 审查.
In this repository26 other files it gives its agents.
- ablation-plannerSkill
- analyze-resultsSkill
- auto-review-loopSkill
- experiment-implementSkill
- experiment-planSkill
- formula-derivationSkill
- idea-creatorSkill
- idea-discoverySkill
- novelty-checkSkill
- paper-figureSkill
- paper-illustration-image2Skill
- paper-illustrationSkill
- paper-posterSkill
- paper-self-reviewSkill
- paper-slidesSkill
- paper-talkSkill
- paper-writing-coreSkill
- rebuttalSkill
- research-litSkill
- research-refine-pipelineSkill
- research-refineSkill
- research-reviewSkill
- research-wikiSkill
- resubmit-pipelineSkill
- sediment-top-journal-writingSkill
- slides-polishSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
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.