prove
Skill1 starsChanged 15 days agoMITView on GitHub
Show a failing check, then a passing one, on real behavior.
13 other projects use a version of this.
Adopted by
Most recently taken up by
- 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
- dtiger1889-ops/claude-harness-toolboxtheir own version, first seen Oct 12, 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
- dtiger1889-ops/claude-harness-toolbox★ 31same name
- grove/promise-to-proof★ 4same 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
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 30
Do not restate bundled skills.
- Very specific: line 35
When the passing check is real, stop.
“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
When to Use
The change is supposed to be done, or the user asked for a report of what to run. Load this after shape, or after bundled systematic-debugging.
What to do
Done means a check you ran. Show it failing for the right reason, then passing.
Name the surface you exercised: the CLI, the API, the job, the webhook, or the page. A unit test that never calls that surface is not this check. Run the check with terminal.
Report-only mode lists the check, the command, and the expected failure. Do not edit product code in that mode.
A performance claim names the limiter, how many times you repeated it, and the error. Otherwise it is not a result. An unvetted number is not a result.
Do not restate bundled skills. Load them with skill_view:
- A bug with a cheap unit test:
test-driven-development. - Browser exploration of a page:
dogfood. Usebrowser_execonly as that skill directs.
When the passing check is real, stop. Opening a pull request is ship, and only when the user asks.
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.