dev-verify
Skill1 starsChanged 16 days agoMITView on GitHub
Verify a code, config or schema change (including refactors and performance work meant to keep behavior the same) before claiming it is complete, fixed, or passing. Select the narrowest evidence that proves the affected behavior, escalating only when blast radius requires it. Not for text-only or docs-only edits.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- EvolutionAPI/evo-nexustheir own version, first seen Oct 8, 2026
- abigayleh/claude-workflow-plugintheir own version, first seen Sep 27, 2026
- evolution-foundation/evo-nexustheir own version, first seen Apr 20, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- EvolutionAPI/evo-nexus★ 545same name
- evolution-foundation/evo-nexus★ 535same name
- abigayleh/claude-workflow-plugin★ 0same 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 repository14 other files it gives its agents.
- .agents/AGENTS.mdAGENTS.md
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- dev-debugSkill
- dev-planSkill
- dev-reviewSkill
- dev-ui-verifySkill
- project-contextSkill
- dev-debugSkill
- dev-planSkill
- dev-reviewSkill
- dev-ui-verifySkill
- dev-verifySkill
- project-contextSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 4 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
4
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
- Distinctive: line 12
Before a completion claim:
- Distinctive: line 15
Run the relevant check fresh after the final relevant change.
- Distinctive: line 16
Read output and exit status.
- Distinctive: line 22
Start with the cheapest check that directly proves behavior:
- Very specific: line 38
If the task materially changed user-facing UI, use dev-ui-verify and include its result in completion evidence.
“Common” is measured: kept by at least 6 in 10 of the 3 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 Before Completion
Evidence before claims.
Gate
Before a completion claim:
- Identify the observable evidence that proves the requested outcome.
- Run the relevant check fresh after the final relevant change.
- Read output and exit status.
- Confirm the check actually covered the affected behavior.
- Report the real result, including failures or material unverified areas.
Verification ladder
Start with the cheapest check that directly proves behavior:
- focused reproduction or test,
- affected integration test,
- typecheck/lint for affected scope,
- relevant build,
- runtime/service verification,
- broader suite when shared infrastructure or contract blast radius justifies it.
A linter does not prove a build. A build does not prove the original bug is fixed. Unrelated passing tests do not prove requirements were met.
Avoid redundant execution
For expensive commands, capture useful output once and inspect/search the captured result instead of rerunning unchanged work. Rerun only after a relevant change or when a new proof requires execution.
If the task materially changed user-facing UI, use dev-ui-verify and include its result in completion evidence.
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.