verify-build
Skill0 starsChanged 6 months agoMITView on GitHub
Post-implementation verification checklist run before declaring work complete.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- HeyEddi-com/heyeddi-skillstheir own version, first seen Aug 25, 2026
- seldonframe/seldonframetheir own version, first seen Jul 7, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- seldonframe/seldonframe★ 40same name
- HeyEddi-com/heyeddi-skills★ 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 repository13 other files it gives its agents.
- clean-commitSkill
- context-budgetSkill
- craft-principlesSkill
- debug-circuitSkill
- meeting-driverSkill
- memory-curatorSkill
- output-guardSkill
- plan-firstSkill
- pm-docsSkill
- ship-cycleSkill
- simplify-codeSkill
- sprint-flowSkill
- task-resumeSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
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 14
After implementation is complete, run this verification checklist before declaring the work done.
- Distinctive: line 54
After completing implementation, run through this checklist item by item.
- Distinctive: line 67
If any item fails, fix it before proceeding.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Verify Build
After implementation is complete, run this verification checklist before declaring the work done.
Verification Checklist
Functional
- All acceptance criteria from the plan are met
- The happy path works end-to-end
- Edge cases identified in the plan have been handled
- Error states produce useful messages, not crashes
Code Quality
- No commented-out code left behind
- No TODO comments without linked issues
- No hardcoded secrets, API keys, or environment-specific values
- No unused imports or dead code introduced
- Functions are under 50 lines (or justified if longer)
Testing
- Tests pass locally
- New code has test coverage for critical paths
- No tests were disabled or skipped to make the build pass
Security
- User input is validated at system boundaries
- No SQL injection, XSS, or command injection vectors introduced
- Secrets are loaded from environment variables, not committed
- Dependencies added are from trusted sources with active maintenance
Integration
- Changes work with the existing codebase (no regressions)
- Database migrations (if any) are reversible
- API changes are backward-compatible or versioned
How to Use
After completing implementation, run through this checklist item by item. Report the results to the user as a summary:
Verification Complete:
Functional: PASS (4/4)
Code Quality: PASS (5/5)
Testing: PASS (3/3)
Security: PASS (4/4)
Integration: PASS (2/2)
Ready to commit.If any item fails, fix it before proceeding. Do not report partial passes as complete.
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.