verify-work
Skill17 starsChanged 14 days agoMITView on GitHub
Check a completed delegated task against its requirements and shared contracts. Use with review-diff for an independent verifier review.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- danielvm-git/bigpowerstheir own version, first seen Nov 6, 2026
- buildomator/buildomatortheir own version, first seen Nov 4, 2026
- Astatide1337/Skillstheir own version, first seen Oct 20, 2026
- linellazatin/skillstheir own version, first seen Oct 17, 2026
- tonygorb/skillstheir own version, first seen Oct 15, 2026
- hassan-mohiddin/freeflowtheir own version, first seen Oct 4, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- danielvm-git/bigpowers★ 288same name
- hamzafarooq/claude-code-starter★ 145same name
- buildomator/buildomator★ 102same name
- hassan-mohiddin/freeflow★ 5same name
- tonygorb/skills★ 2same name
- aprameyak/coding-skills★ 1same name
- Astatide1337/Skills★ 1same name
- linellazatin/skills★ 1same name
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 repository32 other files it gives its agents.
- AGENTS.mdAGENTS.md
- aboutSkill
- answerSkill
- attack-testsSkill
- audit-experimentSkill
- bugSkill
- ci-watchSkill
- commitSkill
- contextSkill
- delegateSkill
- documentSkill
- evalSkill
- featureSkill
- impact-mapSkill
- implement-workSkill
- mrSkill
- mutation-checkSkill
- perfSkill
- previewSkill
- refactorSkill
- requestSkill
- review-diffSkill
- reviewSkill
- run-experimentSkill
- screen-designSkill
- screen-paritySkill
- setupSkill
- sibling-path-mapSkill
- specSkill
- sweepSkill
- test-hardeningSkill
- work-graphSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
1
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 22
Shared contracts: When the brief names a contract between implementers (types, props, schemas), check every consumer uses it as its owner …
“Common” is measured: kept by at least 6 in 10 of the 8 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
verify-work
Apply the common work contract within this task’s scope. It owns applicable pre-action evidence, product implementation obligations and completion requirements; this skill supplies the method. Current common guidance already delivered or read may be reused.
Task boundary
You are a verifier spawned for an independent review. Your main job is to find where the changed code gives a wrong result. Agent reports are claims, not evidence. Never edit, create or delete files in the repository, and never commit, stash, checkout or reset. Repro scripts go in a temporary folder outside the repository.
Procedure
Begin with review-diff's Establish expected behavior check, then apply these task-level checks. Derive the conditions from the original requirement sources before reading the implementer's explanation or prior evidence; compare them with the brief's acceptance criteria and flag omissions or contradictions.
- Mechanical results. Apply review-diff's mechanical-results step to the owned files and the final change, respecting the task's forbidden commands. Check actual test execution and results, not just the exit code.
- Required outcomes. Match the brief's required behavior and unchanged contracts to executed checks on the final change. Read the assertions or interaction evidence and expected versus observed result. Return review-diff's per-outcome verification results, including evidence gaps, for the main's completion decision. A worker's claim, test name or absence of findings is not a passing behavior check. Report gaps without inventing extra requirements.
- Failing tests. For each, decide from the spec whether the implementation or the test is wrong and say which agent fixes it. A test asserting behavior the spec does not define is an open question.
- Weak tests. Judge the implementer's and tester's tests with the behavior-tests check; a test that would still pass with the behavior broken is a quality defect.
- Shared contracts. When the brief names a contract between implementers (types, props, schemas), check every consumer uses it as its owner defined it — names, optional versus required, units, call order. A mismatch is a FAIL citing both sides.
- Parallel units. You review the whole task once, after every unit is done, so look for defects between units as well as inside them.
A defect whose fix is outside owned files still fails an outcome if it breaks the requested result. Report the defect and ownership boundary; do not expand edit permission. Unrelated existing defects remain report-only. Missing proof is unverified; an unresolved expectation needs a decision. Neither is PASS. Keep review conclusions bounded by the inspected scope, and do not score.
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.

