prove-it
Skill0 starsChanged 5 months agoMITView on GitHub
Don't say a task is done until you can prove it. Triggers right before you'd report work finished (or on /prove-it). For every claim you're about to make — "it works", "tests pass", "the bug is fixed" — it makes you show evidence: run it and paste the real output, or cite the exact file:line. No proof, no "done"; what you couldn't verify, you say so plainly.
27 other projects use a version of this.
Adopted by
Most recently taken up by
- decebal/chief-of-staff-v2their own version, first seen Nov 8, 2026
- SaudSatopay/bullseyetheir own version, first seen Nov 8, 2026
- anotherben/claude-harnesstheir own version, first seen Nov 8, 2026
- SylphxAI/skillstheir own version, first seen Nov 1, 2026
- nagi-studio/skillstheir own version, first seen Nov 1, 2026
- ravidsrk/orca-fleettheir own version, first seen Oct 23, 2026
Used with
Projects with it also use root-cause, challenge and 4 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Ingramradical235Skillroot-cause
Structured root cause analysis using WHERE (MECE decomposition) then WHY (causal structure diagrams) pipeline. Includes coin-flip detection, logical-leap detection, and vicious cycle intervention. Use when buffer enters YELLOW/RED, when metrics stall, or when Actions execute but don't produce results.
Also in 3 projects that use this
michalattSkillchallenge
Pressure-test plans, decisions, and directions by picking and answering the most relevant challenge questions for the current conversation
Also in 3 projects that use this
renatorozasSkillgrill
Adversarial code review. Don't let me ship until the changes pass your scrutiny.
Also in 4 projects that use this
AWSSkillretro
Conduct a retrospective on a coding session.
Also in 3 projects that use this
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
GoogleSkilltdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Also in 3 projects that use this
Other versions27 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 27
- nagi-studio/skills★ 470same name
- AlemTuzlak/skills★ 45same name
- Neko-Catpital-Labs/Invoker★ 20same name
- anotherben/claude-harness★ 7same name
- nadirali1350/vetted★ 5same name
- Xnadir/vetted★ 5same name
- SaudSatopay/bullseye★ 4same name
- drewdrewthis/claude-skills★ 2same name
- dundas/thinkrun★ 2same name
- duvi-ai/skills★ 2same name
17 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, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 25 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 22
On demand: when the user types /prove-it.
- Distinctive: line 43
Do not close the task as done while any claim is unproven and unflagged.
- Distinctive: line 58
Keep it tight. Real evidence only.
“Common” is measured: kept by at least 6 in 10 of the 25 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-it — your agent can't say "done" without proof
You're about to tell the user the task is finished. Before you do, prove it. "This should work now" is the phrase that wastes the most human time in AI coding — it's a guess wearing the costume of a result. prove-it turns every done-claim into a checked claim.
When to run
- Automatically, right before you report a task as done / working / fixed / ready — any closing claim about what the code now does.
- On demand when the user types
/prove-it.
The discipline
- List the claims you're about to make. Each "it works / tests pass / bug fixed / endpoint returns X / handles Y" is a separate claim.
- Back each claim with evidence — one of:
- Ran it. A command you actually executed plus its real, pasted output (test run, the script, a curl, a REPL check). Not a description of what it would print — the actual lines.
- Cited it. The exact
file:line(or diff hunk) that makes the claim true, quoted, when running isn't possible.
- If you can't verify it, say so. "Not verified: no DB to run the migration against" / "couldn't run tests: missing env var". An honest gap beats a confident guess every time.
- Banned without evidence: "should work", "this works now", "done", "fixed", "verified", "I've tested", "looks good", "ready to ship" — none of these may appear unless a proof line backs them in the same message.
The hard rule
Do not close the task as done while any claim is unproven and unflagged. If a claim can't be proven and can't be honestly downgraded to "not verified", it isn't done — keep working or hand the user a clear, specific gap.
Output format
prove-it — N claim(s)
✓ tests pass ran `npm test` → 14 passed, 0 failed [proven: ran]
✓ /orders returns 200 ran `curl -s -o /dev/null -w '%{http_code}'` → 200 [proven: ran]
✓ null guard added payments.ts:42 `if (!user) return 401` [proven: cited]
⚠ handles 1M rows not verified — no dataset that large locally [flagged]
1 claim could not be verified — said so, not claimed.Keep it tight. Real evidence only. The point isn't ceremony — it's that "done" should mean checked, and "I'm not sure" should be sayable out loud.
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.

