finalize
Skill1 starsChanged 9 days agoMITView on GitHub
Use when the implementation of an approved spec is done and you are about to report the result, in the gate lane only. Runs the done step. Find defects, cut excess code, run fresh checks, write an honest report, archive the spec.
22 other projects use a version of this.
Adopted by
Most recently taken up by
- PL-Coding-GmbH/Skillstheir own version, first seen Nov 8, 2026
- DnsQueen/orcinus-skillstheir own version, first seen Nov 8, 2026
- SDSLeon/lightcodetheir own version, first seen Nov 1, 2026
- griffinhilly/claude-code-synthesistheir own version, first seen Nov 1, 2026
- Porabuild/Poracodetheir own version, first seen Nov 1, 2026
- nrflo/nrflotheir own version, first seen Oct 29, 2026
Used with
Projects with it also use simplify, debug and 2 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.
Hugging FaceSkillsimplify
Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.
Also in 3 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
Microsoft AzureSkillverify
End-to-end app testing pipeline for browser-based web apps on cloud browsers via Azure Playwright Workspaces: verify the live app, author tests for working flows, heal failing tests, then re-run with video and produce one consolidated report. Three phases (app verification, test authoring, test healing) plus a scoped final sanity run; each phase emits a sub-report. Use when asked to "verify my app", "make sure my app works and has good test coverage", "do a full QA pass", "add tests where I'm missing coverage", "fix failing tests and add new ones", "smoke test before deploy", "QA my deployment", or any combined verify-and-test ask. Requires Azure CLI (`az login`) and a Playwright Workspace resource ID — bootstraps configs on first invocation. Browser-based web apps with Playwright only — not for unit/API tests, native mobile/desktop, load/perf, or full accessibility audits.
Also in 3 projects that use this
SentrySkillcommit
Create commit messages following Sentry conventions. Use when committing code changes, writing commit messages, or formatting git history. Follows conventional commits with Sentry-specific issue references.
Also in 3 projects that use this
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- morethanwords/tweb★ 2.7ksame name
- educlopez/ui-craft★ 441same name
- zifeo/lade★ 135same name
- Porabuild/Poracode★ 121same name
- SDSLeon/lightcode★ 121same name
- redis/docs★ 86same name
- skillberry-ai/cap-evolve★ 69same name
- griffinhilly/claude-code-synthesis★ 67same name
- PL-Coding-GmbH/Skills★ 18same name
- alexiolan/craft-skills★ 17same name
12 more not listed
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.
- architectureSkill
- artifactsSkill
- buildSkill
- debtSkill
- deep-reviewSkill
- diagnoseSkill
- distributed-architectureSkill
- handoffSkill
- rulesSkill
- security-checkSkill
- sparSkill
- specSkill
- whichSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 22 edited versions we read keep these.
6
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
- could be automatic: a setting could enforce it
- Distinctive: line 8
Do these five steps in order.
- Distinctive: line 12
Read your own diff.
- Distinctive: line 17
Run git status --short. Name every changed file that the blast radius did not list.
- Distinctive: line 24
Delete from this change's own diff:
- Distinctive: line 50
Put no secrets in the report.
- Distinctive: line 54
Run this Bash command, with today's date and a short slug.
“Common” is measured: kept by at least 6 in 10 of the 22 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
Finalize
Do these five steps in order. Do not skip one. Ordinary changes without a spec do not use this skill: run the project's own check once and report.
1. Defects
Read your own diff.
- Spec compliance first: does each criterion and non-goal hold?
- Then quality, and the risk to every caller in the blast radius.
- Back each defect with a concrete input or situation that breaks the code. Drop a suspicion that has none.
- Run
git status --short. Name every changed file that the blast radius did not list. Say why it changed, or revert it. - A weakened, skipped or deleted test, assertion or guard is a defect. Restore it, unless the spec asked for the change.
Fix what you find.
2. Cuts
Delete from this change's own diff:
- dead code
- flexibility nobody asked for
- hand-written code that the standard library already provides
A cut outside the diff is not an edit. Offer it as a suggestion for a new spec.
3. Verify, once per code state
Run every acceptance check after the last change. A result from before the last change does not count. Do not re-run a check when the code has not changed since it passed. Keep one failure or recovery path in the run, not only the happy path.
Throwaway repro scripts go in specs/, not in the repo. A bug fix keeps one regression test in the repo.
For each check, report pass or fail, the command, and what it printed. Say "checks pass". Never say "correct" or "works".
4. Report
Keep it short:
- Result: what changed, in a few lines.
- Evidence: the commands and results from step 3.
- Unrun checks: what you did not run, and why.
- Decisions: the choices you made that the spec did not settle, or none.
- Limits: what the change does not cover.
Put no secrets in the report. Do not commit, push, deploy or delete unless the user said so.
5. Archive and release
Run this Bash command, with today's date and a short slug. Moving the spec ends the approval.
mv specs/current.md specs/<date>-<slug>.md
ls -t specs/2*.md | tail -n +6 | xargs rm -f
rm -f specs/current.url specs/current.htmlThe second line keeps the 5 newest archived specs. The third drops the spec page's link and local copy, so the next spec gets its own page; the published page stays. Git is the rollback, not the specs. The next change needs a new spec and a new approval.
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.