prove
Skill31 starsChanged 32 days agoMITView on GitHub
Verifies disputed factual claims in a previous response against actual sources. Use for /prove, "prove it", "did you make that up", "source?", or "where did you get that" about an earlier assertion. Reports confirmed, wrong, or unverified claims with citations and corrects the answer.
13 other projects use a version of this.
Adopted by
Most recently taken up by
- Belweave/hstacktheir own version, first seen Nov 8, 2026
- parcadei/Continuous-Claudetheir own version, first seen Oct 17, 2026
- sdvsignal/done-needs-prooftheir own version, first seen Oct 15, 2026
- pavelsimo/skillstheir own version, first seen Oct 13, 2026
- ilamanov/skillstheir own version, first seen Oct 13, 2026
- wenlan-app/wenlantheir own version, first seen Oct 13, 2026
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- Z3Prover/z3★ 13ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- 7xuanlu/wenlan★ 94same name
- wenlan-app/wenlan★ 94same name
- grove/promise-to-proof★ 4same name
- Belweave/hstack★ 1same name
- corygabrielsen/skills★ 1same name
- ilamanov/skills★ 1same 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.
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
3
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 each claim using the source appropriate to it:
- Distinctive: line 18
If any claim changed, restate the corrected answer briefly.
- Distinctive: line 20
Do not treat absence of contradiction as confirmation, repeat a claim more confidently, or stop while an available source remains unchecked.
“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
Prove the claims
- Extract checkable assertions from the passage the user disputes: numbers, dates, names, paths, decisions, behavior, and source attributions. Prioritize consequential claims. Keep labeled opinions or speculation separate.
- Verify each claim using the source appropriate to it:
- User/project facts: current instructions, state, decisions, and relevant records.
- Artifact or behavior: inspect the file, configuration, logs, or run a harmless demonstration.
- External facts: current authoritative sources, preferably official documentation or primary evidence.
- Resolve contradictory sources rather than treating either as automatically correct. Check dates and the actual artifact where possible. Memory may locate evidence but cannot confirm a claim.
- Report one concise verdict per claim:
- Confirmed: cite supporting evidence.
- Wrong: give the correct fact and cite its source.
- Unverified: name the missing evidence and withdraw the unsupported assertion.
- If any claim changed, restate the corrected answer briefly. Flag any recommendation or action affected by the error.
Do not treat absence of contradiction as confirmation, repeat a claim more confidently, or stop while an available source remains unchecked. Preserve qualifications in the evidence. Use plain language and accessible citations.
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.