agentleFS
Cody-SimsCody-Sims/agent-skills/skills/verification-before-completion/SKILL.md

verification-before-completion

Skill0 starsChanged 4 months agoMITView on GitHub

Verifies completion claims against inspected artifacts and relevant post-change command results. Use before reporting work done, fixed, passing, working, or ready, including subagent results; evidence must match the current state and claimed scope.

190 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

6 rules. 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 178 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
  1. Distinctive:

    Do not claim success from expectation, stale evidence, or a worker's summary.

    line 13
  2. Distinctive:

    Verify the final relevant state without rerunning unchanged checks ceremonially.

    line 14
  3. Distinctive:

    Do not replace a required full suite with a focused test.

    line 22
  4. Distinctive:

    Run checks after the final relevant change.

    line 23
  5. Distinctive:

    Keep a compact record of command, tested state, scope, result, and artifact.

    line 25
  6. Distinctive:

    Check dependent service readiness for runtime reproductions.

    line 31

“Common” is measured: kept by at least 6 in 10 of the 178 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

Verification Before Completion

Do not claim success from expectation, stale evidence, or a worker's summary. Verify the final relevant state without rerunning unchanged checks ceremonially.

Procedure

  1. Name the claim and evidence that would prove it: reproduction, tests, build, lint, type checks, or artifact inspection. Match evidence to the claim.
  2. Inspect the final diff or artifact. Choose the smallest check covering the changed behavior and its edges, plus every repository-required gate. Do not replace a required full suite with a focused test.
  3. Run checks after the final relevant change. Read actual output and exit status; a nonzero exit is failure even when the log contains a success message. Keep a compact record of command, tested state, scope, result, and artifact.
  4. Reuse recorded output from this session, including an earlier turn, only when it followed the final relevant change and the tested inputs, dependencies, configuration, environment, and artifacts remain unchanged. Otherwise rerun. A cached pass, previous-session result, or worker summary alone is insufficient.
  5. For a bug fix, rerun the original failing case and confirm the symptom is gone. Check dependent service readiness for runtime reproductions; an unavailable prerequisite is not proof of a product defect or a successful fix.
  6. For delegated work, inspect actual artifacts and recorded command output/exit status. Do not trust only a completion message. Verify shared integration separately; serialize gates that write the same generated or temporary state.
  7. Widen or repeat checks for failures, integration risk, changed tested state, or required gates, not merely a new handoff. Preserve every required case and assertion; disclose pre-existing or unavailable checks rather than hiding them.

Evidence boundaries

  • Build success does not prove tests, lint, types, or runtime behavior.
  • A focused test does not prove a full suite.
  • Correct-looking code does not prove the original symptom is fixed.
  • Shorter instructions or smaller outputs do not prove lower billed usage, faster completion, or better task quality; those require matched measurements.

Output

Return a nonempty outcome with the supporting evidence appropriate to the request and any unresolved limitation. Keep logs and repeated checklists out of the final handoff; retain exact evidence for inspection. Never describe partial, blocked, or unverified work as complete.

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.