verification
Skill0 starsChanged 3 months agoMITView on GitHub
Prove that a claim, output, or fix actually works using evidence, not confidence. Use whenever about to say "done", "fixed", "works", "passes", or "should be fine" — any completion claim needs this skill first, even for small changes and even when the work obviously looks right.
47 other projects use a version of this.
Adopted by
Most recently taken up by
- yagizdo/quivertheir own version, first seen Nov 15, 2026
- vercel/vercel-plugintheir own version, first seen Nov 12, 2026
- neuraforge-cl-es/adaptive-engineeringtheir own version, first seen Nov 8, 2026
- facebook/docusaurustheir own version, first seen Nov 8, 2026
- maideps/ai-harness-frameworktheir own version, first seen Nov 8, 2026
- Lanqiao-Luca/ai-java-workflowtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use evidence-driven-writing, experiment-results-planning and 10 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.
Norman-burySkillevidence-driven-writing
Use when writing or revising Introduction, Related Work, background, literature synthesis, or any section where references must drive claims
Also in 3 projects that use this
Norman-burySkillexperiment-results-planning
Use when designing experiments, result tables, mock planning data, evaluation protocols, or results sections before real data are final
Also in 3 projects that use this
- +10 more from Norman-bury
Other versions47 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 47
- facebook/docusaurus★ 67ksame name
- open-metadata/OpenMetadata★ 16ksame name
- openai/plugins★ 7.8ksame name
- hi-godot/godot-ai★ 3.4ksame name
- Norman-bury/research-writing-skill★ 3.4ksame name
- Norman-bury/articlewriting-skill★ 3.4ksame name
- forcedotcom/salesforcedx-vscode★ 1ksame name
- vercel/vercel-plugin★ 336same name
- Lanqiao-Luca/ai-java-workflow★ 335same name
- s3s-project/s3s★ 315same name
37 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 repository20 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brainstormSkill
- cleanupSkill
- context-managementSkill
- critiqueSkill
- debuggingSkill
- design-decisionsSkill
- diff-managementSkill
- fan-outSkill
- final-checkSkill
- handoverSkill
- loopsSkill
- memorySkill
- orientSkill
- planningSkill
- researchSkill
- roadmapSkill
- web-testingSkill
- writing-reviewSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 39 edited versions we read keep these.
5
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 23
Verify the requirement, not the implementation: the question is "does it do what was asked", not "does my code run".
- Distinctive: line 24
Test the failure path too: a verifier that passes everything is broken.
- Distinctive: line 25
Verify at boundaries: empty input, maximum size, wrong type, missing dependency, non-ASCII text, concurrent/repeated invocation — whichever …
- Distinctive: line 26
After ANY later change (cleanup, formatting, "one tiny fix"), re-verify.
- Distinctive: line 30
Every factual claim gets a source or a computation behind it.
“Common” is measured: kept by at least 6 in 10 of the 39 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
Verification
Confidence is not evidence. A thing is verified when you have run a check that COULD have failed and watched it pass. Verification that cannot fail is theater.
Pick the strongest available verifier
Strongest first — drop down only when the stronger option genuinely doesn't exist:
- Execution — run the code, command, or script; observe actual output. For files: open/parse the real artifact (render the docx, run the notebook, load the CSV).
- Automated checks — tests, linters, type checkers, schema validators, link checkers. Run from clean state; cached green is not green.
- Independent recomputation — redo the calculation a different way (different tool, different method) and compare. Never verify math by re-reading the math; compute it programmatically.
- Fresh-agent inspection — subagent with no authorship bias checks the deliverable against the requirement.
- Line-by-line self-review — weakest; acceptable only for trivial changes, and still against the original requirement, not memory of it.
Rules of evidence
- Record WHAT was run, the ACTUAL result, and WHEN. "Tests pass" without the command and output is a claim, not evidence.
- Verify the requirement, not the implementation: the question is "does it do what was asked", not "does my code run".
- Test the failure path too: a verifier that passes everything is broken. When feasible, break the thing intentionally once to confirm the check catches it.
- Verify at boundaries: empty input, maximum size, wrong type, missing dependency, non-ASCII text, concurrent/repeated invocation — whichever apply.
- After ANY later change (cleanup, formatting, "one tiny fix"), re-verify. The most embarrassing failures ship in the commit after the verified one.
Verifying claims in content (research, docs, analysis)
- Every factual claim gets a source or a computation behind it. Mark anything unverifiable as an assumption, visibly.
- Numbers: recompute from raw data. Quotes: check against the original. Links: fetch them.
- Dates and "current" facts: check against today's date, not training memory.
Output
A verification record (in the plan's ledger, the critique file, or the final-check report): check performed → command/method → actual result → verdict.
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.

