verify-before-done
Skill39 starsChanged 18 days agoMITView on GitHub
Use before claiming any coding task is finished, fixed, working, or passing — after editing code, changing config, adding dependencies, or fixing a bug. Forces running builds/tests/linters and reading the real output instead of assuming success.
11 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- fvkmizel/soulkeeperedited, first seen Nov 8, 2026
- reddygopalkrishna/developer-agent-skillstheir own version, first seen Nov 8, 2026
- KMaruthi2002/universal-llm-skillstheir own version, first seen Oct 25, 2026
- joaoguirunas/team-ostheir own version, first seen Oct 21, 2026
- jsvillalbat/sevito-skillstheir own version, first seen Oct 20, 2026
- alexderz/agentic-toolboxtheir own version, first seen Oct 17, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- fvkmizel/soulkeeper★ 084% same
Wrote their own version · 10
- reddygopalkrishna/developer-agent-skills★ 8same name
- joaoguirunas/team-os★ 6same name
- alexderz/agentic-toolbox★ 5same name
- GusevV1987/ai-workspace-kit★ 2same name
- MPIsaac-Per/claude-code-loop-patterns★ 2same name
- rrrrrredy/beforedone★ 2same name
- yuchi-chang/no-cape★ 2same name
- KMaruthi2002/universal-llm-skills★ 1same name
- jsvillalbat/sevito-skills★ 0same name
- MirzaMotoTech/agent-craft-for-hermes★ 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 repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- no-invented-codeSkill
- plan-firstSkill
- systematic-debuggingSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
3
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 20
Read the actual output: Look for errors, warnings, skipped tests, and "0 tests ran".
- Distinctive: line 27
If it fails for a reason unrelated to your change, say so explicitly and show the error.
- Distinctive: line 34
Never write "fixed", "works", or "all tests pass" without having run them.
- Very specific: line 42
If verification revealed something non-obvious (a flaky test, a required env var, a slow step), save it with mem_save — title + What / Why …
“Common” is measured: kept by at least 6 in 10 of the 10 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
You may only say a task is done / fixed / working after you have evidence from this session. "It should work" is not evidence.
Checklist
- Find the project's real commands — read
package.jsonscripts,Makefile,pyproject.toml,go.mod, CI files (.github/workflows/*), or the README. Do not guess command names. - Run, in order, whatever exists:
- type check / compile (
tsc --noEmit,go build ./...,cargo check,mypy) - linter (
eslint,ruff,golangci-lint) - tests — the ones touching your change first, then the full suite if it is fast
- the app itself, if the change is user-visible (start it, hit the endpoint, load the page)
- type check / compile (
- Read the actual output. Look for errors, warnings, skipped tests, and "0 tests ran". Exit code 0 with no tests executed is not a pass.
- Reproduce the original problem (for bug fixes) and confirm it no longer happens.
- Re-read your diff (
git diff). Remove debug prints, leftover TODOs, unrelated edits.
If something fails
- Fix it and re-run. Do not report partial success as success.
- If it fails for a reason unrelated to your change, say so explicitly and show the error.
If you cannot verify
Say exactly what was not verified and why, e.g.:
"Code compiles and unit tests pass. I could not run the integration tests (needs a database), so the migration is untested."
Never write "fixed", "works", or "all tests pass" without having run them.
Final report format
- Changed: files and what changed
- Verified: commands run + result
- Not verified: what and why (or "nothing")
Memory
If verification revealed something non-obvious (a flaky test, a required env var, a slow step),
save it with mem_save — title + What / Why / Where / Lesson.
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.