📦

prove-it-ran

Name: prove-it-ran
Author: agentkitco

v1.0 Revisão do conteúdo r1 Seguro ⚙️ Comandos externos

Verify Tests Ran Before Reporting Completion

Completion claims can hide skipped tests, stale results, or checks that never exercised a change. This skill guides fresh verification and reports evidence for each claim.

Suporta: Claude Codex Code(CC)

🥉 78 Bronze

Maintain this Skill? Claim it 🥉 78 Bronze

Instalar com meu Agente

Copie esta solicitação para o seu Agente. Ela inclui a página canônica do Skill e o manifesto.

Solicitação do agente

Review the Skillstore skill "prove-it-ran" from https://skillstore.io/skills/agentkitco-prove-it-ran.md and its manifest at https://skillstore.io/api/skills/agentkitco-prove-it-ran/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Seu Agente ainda deve apresentar o plano e solicitar qualquer confirmação exigida pela política de segurança.

Recursos legíveis por agentes

Use estes links quando um agente de IA, crawler ou script precisar de contexto limpo em vez de ler a página completa.

Detalhe em Markdown GET /skills/agentkitco-prove-it-ran.md manifest assinado GET /api/skills/agentkitco-prove-it-ran/manifest lockfile assinado GET /api/skills/agentkitco-prove-it-ran/lockfile

Testar

Usando "prove-it-ran". Illustrative request: prove that a regression test detects the original bug.

Resultado esperado:

Claim: the regression test detects the defect.
Evidence: one test failed without the fix and passed after the fix was restored.
Exit codes: 1 before restoration and 0 afterward.
Verified: yes for the targeted regression; the wider suite was not run.

Usando "prove-it-ran". Illustrative request: assess a test command that exits successfully but finds no tests.

Resultado esperado:

Claim: the test suite passes.
Evidence: the command exited with code 0, but the runner reported zero tests.
Verified: no; the command did not exercise the changed code.
Next check: confirm the working directory, configuration, and test filename pattern.

Auditoria de segurança

Seguro

v1 • 17/10/2026 Abrir o relatório versionado

All six static findings are false positives involving Markdown formatting, scoped verification commands, or evidence-reporting instructions. No evidence found of prompt injection, credential collection, exfiltration, or malicious command execution. Temporary source changes require care, but the procedure explicitly limits their scope and requires restoration.

Arquivos analisados

Linhas analisadas

Itens de revisão

Falsos positivos ignorados

Fatores de risco

⚙️ Comandos externos (4)

SKILL.md:20 SKILL.md:22 SKILL.md:23 SKILL.md:29-35

A auditoria estática e semântica concluída mais recente não detectou achados de segurança confirmados. Isso não comprova que a skill não tenha efeitos colaterais.

Auditado por: codex

Compartilhar e citar este relatório

Compartilhe o relatório de avaliação versionado, o badge neutro, o cartão incorporável e as citações. A Skillstore apresenta evidências sem decidir se este Skill é seguro.

Abrir o relatório versionado

Copiar link do relatório

https://skillstore.io/skills/agentkitco-prove-it-ran/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Badge Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/agentkitco-prove-it-ran/security.svg)](https://skillstore.io/skills/agentkitco-prove-it-ran?utm_source=security_passport_badge)

Badge HTML

<a href="https://skillstore.io/skills/agentkitco-prove-it-ran?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/agentkitco-prove-it-ran/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Cartão incorporável

<iframe src="https://skillstore.io/embed/skills/agentkitco-prove-it-ran.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Citações acadêmicas (APA · BibTeX · CFF)

Citação APA

agentkitco. (2026). prove-it-ran security audit report (audit version 1) [Author version 1.0]. Skillstore. https://skillstore.io/skills/agentkitco-prove-it-ran/audits/1

Citação BibTeX

@techreport{agentkitco-agentkitco-prove-it-ran-2026,
  author = {agentkitco},
  title = {prove-it-ran security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/agentkitco-prove-it-ran/audits/1},
  note = {Author version 1.0}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "prove-it-ran security audit report (audit version 1)"
version: "1.0"
type: report
authors:
  - name: "agentkitco"
date-released: "2026-10-17"
url: "https://skillstore.io/skills/agentkitco-prove-it-ran/audits/1"
identifiers:
  - type: other
    value: "skillstore:agentkitco-prove-it-ran:audit:1"
    description: "Skillstore immutable audit report identifier"

Pontuação do Skillstore

Por que esta pontuação Confiança das evidências: Médio

Arquitetura

Manutenibilidade

Conteúdo

Comunidade

Conformidade com a especificação

O que você pode criar

Validate a Bug Fix

Confirm that a regression test fails without the fix and passes after restoration before closing a bug.

Review Completion Evidence

Compare implementation claims with fresh test counts, exit codes, and skipped-test evidence during review.

Prepare a Release Checkpoint

Collect build, lint, type-check, and test results while identifying checks blocked by missing infrastructure.

Teste estes prompts

Verify a Single Test

Verify that [test command] actually runs the intended test. Report the test count, exit code, and any skipped tests.

Check Completion Claims

Review these claims: [claims]. Run the relevant project checks and report exact commands, fresh evidence, and anything not verified.

Prove a Regression Test

Verify that [regression test] fails without [fix] and passes with it. Preserve unrelated edits and restore temporary changes. Report any verification limits.

Audit Release Evidence

Audit [release changes] using project-defined tests, lint, type checks, and builds. Check discovery and skips. Report failures, evidence, and environment-dependent gaps.

Boas práticas

Run checks after the latest edits and retain exact commands with their output.
Isolate temporary source reversions, preserve unrelated work, and confirm restoration before continuing.
Separate verified claims from blocked checks and document how remaining checks can be performed.

Evitar

Treating zero tests, skipped tests, or stale output as proof of success.
Changing tests, snapshots, or thresholds solely to make checks pass.
Calling failures pre-existing without confirming them on a clean checkout.

Perguntas frequentes

What does this skill verify?

It guides checks that commands ran, tests exercised the change, and completion claims have recorded evidence.

Does it include its own test runner?

No. It uses the project tools and commands available to the assistant.

Does a zero exit code prove tests passed?

No. The runner must also discover tests, execute the relevant cases, and expose skipped or excluded checks.

Why test without the fix?

A failure without the fix shows that the regression test can detect the original defect.

What happens when a check needs credentials or hardware?

The report marks the check as not verified and explains how the user can perform it.

Can it work with Claude, Codex, and Claude Code?

The report lists all three as supported tools. Actual verification depends on their access to project files and command execution.

Detalhes do desenvolvedor

Autor

agentkitco

Licença

MIT

Versão do autor

v1.0

Revisão da Skillstore

Aviso de versão

A versão declarada pelo autor não é um SemVer válido.

Repositório

https://github.com/agentkitco/agentkit-dev-skills/tree/3de707c7875147b65ddff504d86b0d0dbf713fa7/skills/prove-it-ran

Referência

743429f75b17204d47661a86b577a575ad67517f

Atualidade da manutenção

17/10/2026

Uso

0 downloads · 0 visualizações

Estrutura de arquivos

📄 SKILL.md