final-check
Skill0 starsChanged 3 months agoMITView on GitHub
The ship gate — a verification checklist that must pass before any task is declared done. Use as the LAST step of every M/L task, after cleanup, and whenever about to tell the user done, finished, complete, or shipped. No PASS verdict, no done.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- Ipsedo/ArenAItheir own version, first seen Oct 15, 2026
- Phongdnh-uit/swe-skillstheir own version, first seen Oct 5, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- Ipsedo/ArenAI★ 2same name
- Phongdnh-uit/swe-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 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
- handoverSkill
- loopsSkill
- memorySkill
- orientSkill
- planningSkill
- researchSkill
- roadmapSkill
- verificationSkill
- web-testingSkill
- writing-reviewSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 13
Plan exit criteria: Every phase's exit criterion re-verified against the final state — not "it passed earlier".
- Distinctive: line 16
Critique debt: All blocker/major critique findings fixed or explicitly waived by the user.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Final check
Nothing is "done" until this gate passes. Run it AFTER cleanup, on the true final state. If any item fails, the task is not done — loop or escalate.
The gate
- Original request, word by word. Re-read the user's actual message(s), not your summary of them. Every explicit requirement met? Every implicit one? Anything silently reinterpreted along the way?
- Plan exit criteria. Every phase's exit criterion re-verified against the final state — not "it passed earlier". Earlier doesn't count; loops and cleanup happened since.
- Fresh verification run. Execute the verification commands/checks NOW, from clean state, per the verification skill (strongest available verifier, evidence recorded). Paste/record actual results, not recollections.
- Feature differential closed. The planned-vs-delivered table (diff-management skill) has no silent gaps — every gap fixed or explicitly reported.
- Critique debt. All blocker/major critique findings fixed or explicitly waived by the user. Minors documented.
- Artifacts in place. Deliverables at their promised paths, openable, non-empty, final versions (not the draft you meant to replace).
- State persisted. Memory written (memory skill triggers all honored), design decisions recorded, handover current if the session may end.
- Cleanup done. Sweep list from the cleanup skill completed; workspace inspection-ready.
Independence rule
For substantial work, hand this checklist to a fresh subagent along with the original request and the deliverables — the role ships in-repo as the final-checker agent (.claude/agents/final-checker.md). The gate-keeper must not be the author. For small work, self-run it in full skeptic mode.
Reporting
End with an explicit verdict:
- PASS — every item green, evidence recorded. Only now say "done".
- PASS WITH NOTES — done, with documented minor caveats the user should see.
- FAIL — list failing items; return to the loop or escalate to the user. Saying "done" on a FAIL is the single worst protocol violation.
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.

