verification-before-completion
Skill1 starsChanged 2 months agoMITView on GitHub
Use when about to claim work is complete, fixed, or passing, before committing or reporting back - requires running a verification command and reading its output before making any success claims; evidence before assertions always.
189 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- DemonDamon/AgenticXtheir own version, first seen Nov 9, 2026
- roundpilot/superpowers-antigravitytheir own version, first seen Nov 8, 2026
- REPOZY/superpowers-optimizedtheir own version, first seen Nov 8, 2026
- lingyired/status-triotheir own version, first seen Nov 8, 2026
- DJtx001/ai-coding-playbooktheir own version, first seen Nov 8, 2026
- Ai-assistant-KIRA/antigravity-harnesstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use chinese-code-review, chinese-commit-conventions and 10 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.
Leodorareluctant259Skillchinese-code-review
中文代码审查规范——在保持专业严谨的同时，用符合国内团队文化的方式给出有效反馈
Also in 8 projects that use this
- Leodorareluctant259Skill
chinese-commit-conventions
中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化
Also in 8 projects that use this
obraSkilldiagnosing-superpowers
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.
Also in 20 projects that use this
jh941213Skilldocs-ci
문서 CI(링크·OpenAPI lint·breaking 게이트·mermaid 검증)나 문서 드리프트 감지(docs.yaml 신선도 검사)를 설치하거나 돌릴 때 사용. 문서 내용 작성은 docs-architecture·docs-interfaces·docs-manuals.
Also in 3 projects that use this
- jh941213Skill
docs-interfaces
API·이벤트 인터페이스 문서(OpenAPI·swagger·AsyncAPI 명세, 엔드포인트 레퍼런스, API 구성도·시퀀스, API CHANGELOG)를 만들거나 코드와 맞출 때 사용. 시스템 구성도는 docs-architecture, API 설계 원칙은 api-design-principles.
Also in 3 projects that use this
- +3 more from Leodorareluctant259
- +4 more from jh941213
Other versions189 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- danielcherubini/skills★ 1410% same
Wrote their own version · 188
- obra/superpowers★ 314ksame name
- jnMetaCode/superpowers-zh★ 8.4ksame name
- openai/plugins★ 7.8ksame name
- farm-fe/farm★ 5.6ksame name
- lingyired/status-trio★ 1.8ksame name
- GanyuanRan/Aegis★ 1.4ksame name
- pcvelz/superpowers★ 1.3ksame name
- DemonDamon/AgenticX★ 1ksame name
- coco-research/coco★ 797same name
- pedronauck/skills★ 649same name
178 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 repository4 other files it gives its agents.
- delegate-or-dieSkill
- doubt-driven-developmentSkill
- j-spaceSkill
- prior-art-searchSkill
The file
Files
Verification Before Completion
Iron Law: NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE.
An unverified "done" is a guess wearing a confident tone. The proof is the check — run fresh and actually read — not the memory of having written the change.
The claim/proof table
| Claim | Requires | Not Sufficient |
| Tests pass | Test command run fresh, full output read, failures = 0 | "I wrote the tests" / an earlier green run |
| Build works | Build command exits 0 | "It looks right" |
| Bug fixed | The original failure scenario re-run, now showing the fix | Code inspection alone |
| Config/service works | The service probed after reload (health check, status endpoint, API call) | File edited + restart claimed |
| Subagent completed | Its report read AND its evidence independently spot-checked | Report says DONE |
| Requirements met | Each requirement mapped to its evidence | A summary paragraph |
Evidence scales to the claim. A one-line typo needs the changed line read back; a feature needs its test, build, or screenshot. What never scales to zero is some fresh, read output.
The gate
- IDENTIFY — What command or probe would prove this claim?
- RUN — Execute it fresh and complete, not "I ran it earlier".
- READ — Full output, exit code, failure count. Not the first line — the verdict.
- VERIFY — Does the output confirm the claim as stated?
- ONLY THEN — Make the claim, citing the evidence.
After proof passes, stop
Report commands, results, and unresolved risk — then stop. No polish, no cleanup, no unrelated tests after the criteria pass. Verification ends a task; it does not open a new one.
Extended from obra/superpowers verification-before-completion and juliusbrussee/caveman verify-and-stop (both MIT); wording adapted.
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.