agentleFS
Sign inStart free
scoobydont-666scoobydont-666/shared-claude-skills/skills/verification-before-completion/SKILL.md

verification-before-completion

Skill1 starsChanged 31 days agoMITView on GitHub

Run fresh checks and inspect exact-revision evidence before claiming a fix, passing tests, PR readiness or working deployment.

189 other projects use a version of this.

Adopted by

Most recently taken up by

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.
  • Leodorareluctant259Skill

    chinese-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

  • obraSkill

    diagnosing-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

  • jh941213Skill

    docs-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

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 177 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
  1. Distinctive:

    Before making a claim:

    line 7
  2. Distinctive:

    Run it on the current candidate with the actual consumed configuration/artifact.

    line 10
  3. Distinctive:

    Read the complete result and exit status.

    line 11
  4. Very specific:

    Do not hide a red baseline, suppress errors to make a scanner look absent, or retry until green without explaining the cause.

    line 26

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Evidence before completion claims

Before making a claim:

  1. Name the exact claim and acceptance criterion.
  2. Choose the check that can actually prove it, including an important failure case.
  3. Run it on the current candidate with the actual consumed configuration/artifact.
  4. Read the complete result and exit status; confirm expected tests were collected.
  5. State the observed result and scope. Missing, failed, cancelled or stale evidence remains unverified.
ClaimRequired evidenceInsufficient by itself
Tests passCurrent required suite output, counts, no unexplained skipsPrevious run or tests merely written
Bug fixedReproduction no longer fails; meaningful regression checkCode changed
Hook functionsInstalled command receives an event fixture and produces intended output; real client check where availableFile exists or syntax passes
Frontend worksIntended user transaction including backend/auth behaviorHTTP 200 or screenshot alone
DeployedActual artifact/config identity on each intended consumer and behavior verificationMerge, process running or health-only check
Migration correctRequired data invariants and recovery evidenceScript exit 0 or row counts alone
Security control enforcedAllowed and denied paths exercise the actual boundaryDocumentation or mock-only success

Re-run invalidated checks after edits; do not transfer success to different bytes. Test from the intended consumer's network/permissions perspective without widening service exposure just to make a probe succeed. Report unavailable client, host or CI checks as NOT_RUN or PENDING with an owner. A PR deliverable does not require unrequested deployment.

Do not hide a red baseline, suppress errors to make a scanner look absent, or retry until green without explaining the cause. Keep verification proportional to risk and the requested scope; follow definition-of-done for the overall delivery checklist.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free