verification-before-completion
Skill0 starsChanged 7 days agoMITView on GitHub
Evidence before claims. Use after the last code change and before saying code works, a bug is fixed or tests pass, and before committing, pushing or opening a PR. Also when the user says a few tests are enough or the full suite can be skipped.
- Reads credentials
189 other projects use a version of this.
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 · 0
None found.
Wrote their own version · 189
- 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
179 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 repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- design-checkSkill
- handoffSkill
- playbookSkill
- prSkill
- retroSkill
- spec-firstSkill
- systematic-debuggingSkill
- tddSkill
- ux-principlesSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 177 edited versions we read keep these.
3
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 10
Rule: do not claim a result you have not just checked.
- Distinctive: line 16
Read the output: exit code, number of failures, warnings.
- Distinctive: line 29
No linter, static analysis or build step in the project: say so in the report in place of that evidence.
“Common” is measured: kept by at least 6 in 10 of the 177 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
Verification before completion
Adapted from obra/superpowers verification-before-completion (MIT).
Rule: do not claim a result you have not just checked. Run the command now, read the output, then report what it says.
Steps
- Name the command that proves the claim.
- Run it in full: the whole suite, not a subset. A request to run only some tests or skip the full suite is about time: if the suite is quick, or you do not know how long it takes, run it anyway and say so. Only when it is really slow, run every test file for the changed code and for code that calls it, and name what you did not run.
- Read the output: exit code, number of failures, warnings.
- Report the actual state with the evidence ("312 passed, 0 failed", "build exit 0"). If something failed or was skipped, say so plainly.
| Claim | Needs | Not enough |
| Tests pass | test run just now with 0 failures | an earlier run, "should pass" |
| Bug fixed | the reproduction test now passes, and failed before | "code changed" |
| Lint / types clean | linter and static analysis output | the tests passing |
| Build works | build command exit 0 | lint passing |
| Requirements met | each acceptance criterion checked one by one | tests passing |
| Subagent finished | git diff and test output checked by you | the subagent's report |
| UI looks right | a screenshot of the changed screen with realistic data, read by you, plus the app's runtime warnings (the project's screenshot command; with none, report the UI as unverified and propose one) | the build passing, layout arithmetic from code, "the user will check" |
No linter, static analysis or build step in the project: say so in the report in place of that evidence. Do not install one.
Before a commit or PR
Also check: git status is clean apart from intended changes, no debug output or commented-out code, no secrets or .env values in the diff (git diff <base>...HEAD and search for keys, tokens, passwords), migrations run both ways if the project uses them.
Words like "should", "probably", "looks right" or "Done!" before you have run the check mean you have not verified.
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.