agentleFS
Sign inStart free
Ai-assistant-KIRAAi-assistant-KIRA/antigravity-harness/skills/verification-before-completion/SKILL.md

verification-before-completion

Skill1 starsChanged 17 days agoApache-2.0View on GitHub

Use before claiming a task is complete, fixed, tested, deployed, or working. Requires fresh command output and concrete evidence for every completion claim, and forbids "should work" or "probably fixed" statements.

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, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 177 edited versions we read keep these.

  • 4

    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:

    Write down each claim you plan to make.

    line 19
  2. Distinctive:

    Run that check now, in this workspace.

    line 21
  3. Distinctive:

    Read the full output and the exit status.

    line 22
  4. Distinctive:

    If the task is complete and verified, record the recovery with Harness².

    line 65

“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

Verification Before Completion

The rule

Claims need evidence. "Done" is a factual statement, and the proof is output from a command you just ran. What happened earlier, or what the code looks like, is not proof.

Steps

  1. Write down each claim you plan to make.
  2. For each one, name the command or observation that proves it.
  3. Run that check now, in this workspace.
  4. Read the full output and the exit status.
  5. Report the claim next to its evidence. If a check could not run, say that plainly instead of implying success.

What counts as proof

ClaimMinimum evidence
Tests passTest command, summary line, zero exit status
Build succeedsBuild command and the produced artifact
Bug is fixedRegression test that failed before and passes now
Lint or typecheck is cleanThe command and its clean output
API contract worksRequest/response or contract test output
UI worksManual steps with a screenshot or recording, or an E2E test
Dependency is installedInstall from a clean environment, then an import check
Migration is safeRun against a representative database and check rollback
Deployment is healthyHealth endpoint, logs, and version or commit confirmation
Performance improvedBefore and after measurements on the same workload

How to phrase results

Use:

  • "python -m pytest passed: 42 passed in 3.1s."
  • "Build succeeded; artifact at dist/app.js."
  • "I could not run the browser test because X, so the UI is unverified."

Avoid:

  • "Should work now."
  • "Probably fixed."
  • "Tests likely pass."
  • "I believe the build is clean."
  • Any claim based only on reading code.

When a check cannot run

Name the blocker, what you tried, and what remains unverified. Offer the smallest next check the user can run. Never turn an unverified change into a learned rule or a success message.

Finish

If the task is complete and verified, record the recovery with Harness². If it is not verified, leave it as a candidate observation, not a rule.

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