verify-done
Skill0 starsChanged 4 months agoMITView on GitHub
Use before claiming any task is finished or telling the user "done". Триггеры (RU) — момент завершения работы, перед словами «сделал/готово/работает». Enforces verification-before-completion — run the actual check (tests, build, the command, open the file) and read its real output before reporting done. Applies to code AND to documents/configs.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- domengabrovsek/agent-configtheir own version, first seen Nov 8, 2026
- domengabrovsek/claudetheir own version, first seen Nov 8, 2026
- DefaultPerson/iron-skillstheir own version, first seen Nov 1, 2026
- AbdurRafay2004/handofftheir own version, first seen Oct 13, 2026
- brain-marchine/verify-done-skillstheir own version, first seen Oct 13, 2026
- Roberdan/roberdan-ostheir own version, first seen Oct 11, 2026
Used with
Projects with it also use ship, debug and 1 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.
AWSSkillship
Finalize dev work on an issue branch — update docs, push, and open a PR.
Also in 4 projects that use this
AnthropicSkilldebug
Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.
Also in 3 projects that use this
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 3 projects that use this
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- domengabrovsek/agent-config★ 22same name
- domengabrovsek/claude★ 22same name
- AbdurRafay2004/handoff★ 4same name
- Roberdan/roberdan-os★ 2same name
- brain-marchine/verify-done-skills★ 0same name
- DefaultPerson/iron-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 repository9 other files it gives its agents.
- docx-analytical-ruSkill
- docx-ruSkill
- looperSkill
- managerSkill
- merge-conflict-resolutionSkill
- npm-publish-smokeSkill
- skill-lifecycleSkill
- team-worklogSkill
- worktree-dispatchSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
2
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 15
Document: does the file exist?
- Distinctive: line 19
Only then answer — with specifics on what exactly was checked ("build: 0 errors", "docx opened, table of contents is there").
“Common” is measured: kept by at least 6 in 10 of the 6 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 before "done"
Principle (adapted from superpowers:verification-before-completion): no completion claim without fresh evidence. Words like "should work", "probably", "looks right" are a red flag — they mean it wasn't checked.
Before saying "done"
- Run a real check, don't guess the result:
- Code: tests /
build/ typecheck / actually running the command. - Document: does the file exist? does it open? is the table of contents present and correctly titled? are the required sections there?
- Config/MCP: restart + the tool status is green, the tool actually responds.
- A file that's supposed to land in a specific place: is it there, and is the index/dashboard entry added?
- Code: tests /
- Read the output, not just the exit code. Show an error/warning, don't swallow it.
- Only then answer — with specifics on what exactly was checked ("build: 0 errors", "docx opened, table of contents is there").
Red flags (stop, check again)
- "Should work" / "probably" / "usually does" — not actually checked.
- A test passed on the very first try without a single failure — is it actually testing anything.
- "Done", but the verification command was never run this session.
Why this exists
This formalizes a simple rule: don't report a half-finished task as progress — an unfinished task gets finished, not narrated. The task ends before the answer, not during it.
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.