verify-claims
Skill17 starsChanged 3 months agoMITView on GitHub
Use before the user reads any draft, memo, literature review, or results write-up — runs an adversarial verification pass that hunts factual errors, unsourced claims, and numbers that don't match the underlying code or output files. Every claim is either cited to an exact file:line or marked UNVERIFIED. Trigger phrases include "verify this draft", "check my numbers", "adversarial verification pass", "did you make this up".
13 other projects use a version of this.
Adopted by
Most recently taken up by
- ji-hun-git/how-to-use-aitheir own version, first seen Nov 15, 2026
- carriegale2710/resume-tailortheir own version, first seen Nov 8, 2026
- pedrohcgs/claude-code-my-workflowtheir own version, first seen Nov 7, 2026
- Thakurvaibhav/platform-agent-harnesstheir own version, first seen Nov 6, 2026
- happier-dev/happiertheir own version, first seen Nov 3, 2026
- jasoncaston/two-body-verifytheir own version, first seen Nov 1, 2026
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- happier-dev/happier★ 2.2ksame name
- pedrohcgs/claude-code-my-workflow★ 1.7ksame name
- indranilbanerjee/digital-marketing-pro★ 934same name
- ShaishavMaisuria/research-paper-lifecycle-skills★ 59same name
- AlessandroCaforio/Academic-Writing★ 17same name
- bhagyamudgal/skills★ 2same name
- Thakurvaibhav/platform-agent-harness★ 2same name
- busycaesar/Harness★ 1same name
- carriegale2710/resume-tailor★ 1same name
- ChenneyZhuang/verify-claims★ 0same name
3 more not listed
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 repository14 other files it gives its agents.
- codex-bridgeSkill
- codex-review-planSkill
- overleafSkill
- plan-debateSkill
- power-firstSkill
- referee-panelSkill
- refresh-pipelineSkill
- review-codex-planSkill
- robustness-batterySkill
- spec-curve-sweepSkill
- stata-preflightSkill
- sync-overleafSkill
- tableSkill
- verify-numbers-pipelineSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 63
Do not fix the prose in this pass.
- Distinctive: line 65
Do not mark something VERIFIED because it looks plausible or matches your memory of an earlier run.
- Distinctive: line 67
Do not soften an UNVERIFIED into "likely correct." The whole point is the honest label.
“Common” is measured: kept by at least 6 in 10 of the 13 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
Verify Claims
Standing closing step on any written output. Run it before the user reads the draft, not after they catch something.
Inputs (infer if obvious, otherwise ask)
- Draft file path (
.tex,.md, or a section of one), plus any companion documents that quote the same results: the response letter, the online appendix, slides. - Where the underlying evidence lives: estimation logs,
results/CSVs, do-files, source PDFs.
Method
Spawn a subagent whose only job is to find errors. Give it the draft and the evidence directories. It must not fix anything, praise anything, or summarize the argument.
For a full paper or several documents, fan out: one subagent per section or document, then merge their lists. A single agent on a whole draft has run out of session before finishing.
For every checkable claim in the draft, it returns one of:
- VERIFIED — with the exact
file:lineof the code, log, or output file the number came from, plus the value found there. - MISMATCH — draft says X, source says Y. Report both values and the source location.
- UNVERIFIED — no source located. Say so plainly. Do not reason backward to a source that "probably" produced it.
Claim types to sweep:
- Numbers — coefficients, standard errors, t-stats, p-values, sample sizes, F-stats, percentages, dates, sample-window endpoints. Cross-check against the estimation log, not against another sentence in the draft.
- Citations — does the cited paper actually make that claim? Check the real paper, not memory. Attribution errors count as factual errors.
- Unsourced assertions — institutional facts, "the literature finds…", magnitude claims, anything phrased as established that has no cite and no output file behind it.
- Internal consistency — same quantity quoted in abstract, text, and table; table N vs. text N; sign language ("increases") vs. the actual coefficient sign.
- Cross-document consistency — the paper, response letter, online appendix and slides quote the same numbers, table/column references and sample; a dropped table leaves no sentence still citing it.
- Claimed changes — anything a previous turn said was done (a table regenerated, a number updated, a file edited): open the file on disk and confirm. A "done" that isn't on disk is a MISMATCH.
Output
A single ranked list, most damaging first, before any prose commentary:
| # | Claim (quoted) | Draft location | Status | Source file:line | Found value |
Rank by: would a referee notice, and does it change the paper's conclusion.
Close with a count: n VERIFIED / n MISMATCH / n UNVERIFIED.
Anti-patterns
- Do not fix the prose in this pass. Show the diff first; the user decides. When fixes are
applied afterwards, list every edit as
file:lineso the user can find each one. - Do not mark something VERIFIED because it looks plausible or matches your memory of an earlier run. Open the file.
- Do not soften an UNVERIFIED into "likely correct." The whole point is the honest label.
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.

