source-check
Skill7 starsChanged 17 days agoMITView on GitHub
Use this after drafting an article, before publish, to verify every factual claim and statistic against a named source.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- frankxai/geninvestor-skillstheir own version, first seen Nov 8, 2026
- agiea-brain/agency-skillstheir own version, first seen Nov 8, 2026
- denolfe/dotfilestheir own version, first seen Nov 2, 2026
- tonysina/claude-skillstheir own version, first seen Nov 1, 2026
- Keremozdemirra/research-agenttheir own version, first seen Oct 19, 2026
- andreijirohdev-labs/gen-ai-labstheir own version, first seen Jul 21, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- denolfe/dotfiles★ 88same name
- tonysina/claude-skills★ 2same name
- agiea-brain/agency-skills★ 1same name
- andreijirohdev-labs/gen-ai-labs★ 1same name
- frankxai/geninvestor-skills★ 0same name
- Keremozdemirra/research-agent★ 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 repository19 other files it gives its agents.
- whetstone-signalSkill
- design-a-grok-botSkill
- overheard-setupSkill
- overheardSkill
- routine-healthcheckSkill
- transcript-healthcheckSkill
- diagram-designSkill
- engineering-playbookSkill
- show-meSkill
- chatgpt-images-browser-playbookSkill
- aeo-geo-siteSkill
- exact-match-intent-seoSkill
- coachSkill
- draftSkill
- no-ai-slopSkill
- outlineSkill
- social-copywritingSkill
- top-editSkill
- x-articleSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Verify every factual claim before publish.
“Common” is measured: kept by at least 6 in 10 of the 6 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
Source check
Verify every factual claim before publish. Read-only except adding a Sources section.
Pass 1 — Extract
Line by line, log factual claims, statistics, attributed statements, historical claims, causal assertions. Skip clearly labeled personal opinion.
Pass 2 — Verify
For each claim, in order: named in the draft, then available files/notes, then a primary web source. Rate: Verified, Unverified, Unsupported, Overstated. Record publication, title, date, URL.
Pass 3 — Quality
Flag single-source lean, stale stats, cherry-picking, vague attribution (“studies show”, “experts agree”), weak outlets.
Pass 4 — Sources section
Numbered list grouped by section. Update, do not duplicate.
Verdict
Solid / Mostly solid / Needs work / Unreliable. Suggest a fix for every problem. Do not rewrite prose.
Original sources only. If a reporter cites a study, cite the study. Personal observation and common knowledge do not need a citation.
Source: adapted from Nadiem Mahmoud, source-check. MIT; see third-party notices.
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.