verify
Skill10 starsChanged 4 months agoMITView on GitHub
Run a change (or an artifact) through a test harness built to embarrass it, then record the results as defects. Use instead of asking whether the work is good — never self-grade. Builds acceptance / happy-path / edge / abuse / ambiguity / regression tests plus fake-progress red flags, runs the artifact through them, and returns passes, failures, severity, required patches, and whether it is usable despite failures.
188 other projects use a version of this.
Adopted by
Most recently taken up by
- Doist/todoist-aitheir own version, first seen Nov 9, 2026
- udecode/better-convextheir own version, first seen Nov 9, 2026
- pytorch/heliontheir own version, first seen Nov 8, 2026
- amir20/dozzletheir own version, first seen Nov 8, 2026
- Doist/todoist-clitheir own version, first seen Nov 8, 2026
- codewithmukesh/dotnet-claude-kittheir own version, first seen Nov 8, 2026
Used with
Projects with it also use instinct-export, instinct-import and 9 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.
TheKREATORSSkillinstinct-export
Export instincts from project/global scope to a file
Also in 3 projects that use this
TheKREATORSSkillinstinct-import
Import instincts from file or URL into project/global scope
Also in 3 projects that use this
AviadPSkillrisk-assess
Assess the risk and blast radius of a proposed code change before implementing it. Evaluates CI impact, framework-wide vs localized scope, rollback path, and identifies blindspots. Use when user says "what's the risk", "is this safe", "assess the impact", "risk assess", "blast radius", or before applying framework-wide or CI-affecting changes. Do NOT use for code quality review (use code-quality) or plan validation (use design-validator).
Also in 3 projects that use this
diego-tobalinaSkillbuild-fix
Fix build and compilation errors systematically. Run when build fails.
Also in 6 projects that use this
AaravChadhaSkillsecure
Security review with a confidence gate - a finding exists only with a concrete exploit scenario and a high/medium/low confidence rating; everything else goes to a worth-hardening list, never inflated. Sweeps five surfaces: auth gates, secrets hygiene, injection and unsafe sinks, unsafe deserialization/crypto/transport, and LLM tool-use trust boundaries. Reports only, never fixes. Use when the user asks for a security review or to check vulnerabilities, secrets, or auth.
Also in 3 projects that use this
ArvorCoSkillspecify
Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.
Also in 10 projects that use this
- +1 more from TheKREATORS
Other versions188 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 188
- react/react★ 252ksame name
- facebook/react★ 252ksame name
- garrytan/gstack★ 141ksame name
- oven-sh/bun★ 97ksame name
- anthropics/financial-services★ 41ksame name
- anthropics/financial-services-plugins★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- anthropics/claude-quickstarts★ 19ksame name
- NVIDIA-NeMo/Speech★ 19ksame name
178 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 repository24 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 167 edited versions we read keep these.
2
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 8
Do not grade the artifact.
- Distinctive: line 51
Run the harness BOUND to the artifact it is about, so the evidence names the exact bytes it was gathered against:
“Common” is measured: kept by at least 6 in 10 of the 167 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
/ratchet:verify — the embarrassment harness
Do not grade the artifact. Asking a model "how good is this?" gets you self-praise. This command instead builds a harness designed to embarrass the artifact, then runs it through. Validation, not vibes.
Step 0 — Load state and target
ratchet status
ratchet snapshot repoIdentify the change or artifact under test (usually the last artifact, or the current diff).
Build the harness
Construct all seven, then run the artifact against them:
- Acceptance criteria — the conditions that define "correct".
- Happy-path test — the intended use, working.
- Edge-case tests — boundaries: empty, huge, zero, negative, unicode, concurrent.
- Abuse / misuse tests — hostile or wrong input a real user will eventually send.
- Ambiguity tests — under-specified inputs where behavior is undefined.
- Regression tests — what previously worked and must still work.
- Fake-progress red flags — the tells that this is theater: passes only on the author's example, swallows errors, asserts nothing, tests the mock not the code.
Run the artifact through the harness for real. Where a runtime exists, execute it via Bash — do not simulate a pass in your head. Report the actual result.
Output contract
HARNESS: <the tests, briefly>
RESULTS:
- PASS: <checks that held>
- FAIL: <check> — <what happened> — severity: critical/high/medium/low
RED FLAGS: <any fake-progress tells found, or "none">
USABLE DESPITE FAILURES? <yes/no + one-line reason>
REQUIRED PATCHES: <smallest delta per failure>Serialize
Run the harness BOUND to the artifact it is about, so the evidence names the exact bytes it was gathered against:
ratchet-evolve verify <target> --artifact <id> --test "<the command>" --jsonThat prints verifiedHash and verifiedRev. Carry both into the log append — it
recomputes them and refuses if the file moved (file changed after verification) or if
the artifact was revised after the harness ran (artifact revised after verification).
The hash alone cannot catch a metadata-only revision: retitle an artifact and the file
is untouched while the revision moves, so rev-1 evidence would be stamped onto rev 2.
ratchet-evolve log append '{"target":"<target>","artifactId":"<id>","verdict":"KEEP",
"verification":{...from verify --json...},
"verifiedHash":"<from verify>","verifiedRev":<from verify>,
"seam":{"seamMatch":"exact","independentFromBuilderMethod":true,...}}'On RED, record every failure as a defect and go patch:
ratchet defect add '{"severity":"...","summary":"verify: <failure>","artifact":"<id>","feature":"<ledger feature id>"}'
ratchet ledger update tests '{"feature":"<id>","name":"<test>","status":"fail"}'
ratchet score confidenceOn GREEN, the run has earned the ending — close the artifact:
ratchet artifact close <id>Next: on red, /ratchet:patch the failures then re-run /ratchet:verify. On green, the
close above, then /ratchet:compile. A change isn't done because it typechecks — it's done
because the harness couldn't embarrass it, and the proof is bound to that exact revision.
Revising the artifact invalidates it: no proof → no close.
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.

