技能 prove-it-ran
📦

prove-it-ran

v1.0 內容修訂 r1 安全 ⚙️ 外部命令

Verify Tests Ran Before Reporting Completion

Passing claims can hide skipped tests, stale results, or checks that never exercised a change. This skill guides fresh verification and evidence-based completion reports.

支援: Claude Codex Code(CC)
Maintain this Skill? Claim it 🥉 78 銅級

使用我的智慧代理安裝

將此請求複製給你的智慧代理，其中包含權威 Skill 頁面和清單。

智能體請求
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.

你的智慧代理仍應顯示其計畫，並依安全政策請求必要確認。

Agent 可讀資源

當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時，請使用這些連結。

Markdown 詳情 GET /skills/agentkitco-prove-it-ran.md 已簽名 manifest GET /api/skills/agentkitco-prove-it-ran/manifest 已簽名 lockfile GET /api/skills/agentkitco-prove-it-ran/lockfile

測試它

正在使用「prove-it-ran」。 Verify whether my bug fix is covered by the regression test.

預期結果:

  • Illustrative result: the targeted test ran and failed with the source fix temporarily removed.
  • After restoring the fix, the same test passed with exit code zero.
  • The wider suite was not run, so overall suite status remains unverified.

正在使用「prove-it-ran」。 The test command exited successfully. Can I report that the tests passed?

預期結果:

  • Illustrative result: the runner reported zero tests, despite a successful exit code.
  • Test verification is incomplete because no test executed.
  • Check the working directory, runner configuration, and test filename pattern before rerunning.

正在使用「prove-it-ran」。 Summarize release verification when device checks are unavailable.

預期結果:

  • Illustrative result: the local suite ran 212 tests with no failures and exit code zero.
  • The build completed with exit code zero.
  • Not verified: device checks require unavailable hardware. Run the device checks on the target hardware before release.

安全審計

安全
v2 • 2026/10/22 開啟版本化報告

All six static findings are false positives: Markdown formatting, local verification commands, and reporting guidance do not establish malicious execution or reconnaissance. No evidence found of prompt injection, credential access, or data exfiltration in SKILL.md. The regression procedure temporarily changes source files, so users should preserve unrelated edits.

1
已掃描檔案
43
分析行數
0
複核項目
0
已忽略的誤報

風險因素

⚙️ 外部命令 (4)
SKILL.md:20 SKILL.md:22 SKILL.md:23 SKILL.md:29-35
最近一次完成的靜態與語意稽核未偵測到已確認的安全發現。這並不能證明該 Skill 沒有副作用。
審計單位: codex 檢視審計紀錄 →
分享與引用此報告

分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據，不判斷該 Skill 是否安全。

開啟版本化報告
安全評估

複製報告連結

https://skillstore.io/skills/agentkitco-prove-it-ran/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![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)

HTML 徽章

<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>

嵌入卡片

<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>
學術引用 (APA · BibTeX · CFF)

APA 引用

agentkitco. (2026). prove-it-ran security audit report (audit version 2) [Author version 1.0]. Skillstore. https://skillstore.io/skills/agentkitco-prove-it-ran/audits/2

BibTeX 引用

@techreport{agentkitco-agentkitco-prove-it-ran-2026, author = {agentkitco}, title = {prove-it-ran security audit report (audit version 2)}, institution = {Skillstore}, year = {2026}, number = {2}, url = {https://skillstore.io/skills/agentkitco-prove-it-ran/audits/2}, 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 2)" version: "1.0" type: report authors: - name: "agentkitco" date-released: "2026-10-22" url: "https://skillstore.io/skills/agentkitco-prove-it-ran/audits/2" identifiers: - type: other value: "skillstore:agentkitco-prove-it-ran:audit:2" description: "Skillstore immutable audit report identifier"

Skillstore 評分

評分依據 證據置信度: 中
55
架構
85
可維護性
87
內容
65
社群
91
規範符合度

你可以打造什麼

Verify a bug fix

Confirm the regression test fails without the fix and passes after restoration before closing a development task.

Review completion evidence

Check test discovery, skip markers, exit codes, and unverified claims before accepting a change.

Prepare a release verification report

Collect fresh test, lint, type check, and build evidence, with explicit notes for checks that cannot run.

試試這些提示

Verify one test run 
Verify that the relevant tests actually ran for my latest change. Report the command, test count, exit code, and anything unverified.
Check discovery and skips 
Run the relevant tests and confirm changed tests appear in the output. Check discovery settings, skipped tests, and focused test markers.
Prove regression coverage 
Verify this fix with a failing-before, passing-after test. Preserve unrelated edits, restore the fix, and report any verification limits.
Audit all completion claims 
Audit every completion claim for this change. Run project-defined tests, lint, type checks, and builds; report exact commands, evidence, failures, and unverified items.

最佳實務

  • Rerun relevant checks after the latest edit and record exact commands with their output.
  • Preserve unrelated edits before temporarily removing a fix, and confirm restoration afterward.
  • Report failures and unavailable checks explicitly, with practical follow-up verification steps.

避免

  • Treating zero discovered tests or skipped tests as a successful test run.
  • Reusing stale output after changing files.
  • Editing tests, snapshots, or thresholds only to obtain a passing result.

常見問題

Does this skill include a test runner?
No. It guides the agent through verification using the commands and tools already available in your project.
Is exit code zero enough to prove tests passed?
No. Confirm a nonzero test count, correct test discovery, and execution of the relevant tests.
How does it check that a test covers a fix?
It asks for a failing run without the fix and a passing run after restoration, when that procedure is practical.
What happens when a check cannot run?
The report marks it as not verified and explains how the user can check it.
Can earlier test output support the final report?
Not after additional edits. The procedure requires fresh output for the current changes.
How are unrelated failures reported?
Failures are reported in full. They are labeled pre-existing only after confirmation on a clean checkout.

開發者詳細資訊

作者

agentkitco

授權

MIT

作者版本

v1.0

Skillstore 修訂

r1

版本提示

作者聲明的版本不符合 SemVer 規範。

儲存庫

https://github.com/agentkitco/agentkit-dev-skills/tree/a5058856442fcb89bd538b1c01f94558488bfac3/skills/prove-it-ran

引用

18efac79a818d7e997295839638fdd21906cfd1c

維護新鮮度

2026/10/22

使用量

5 次下載 · 0 次瀏覽

檔案結構

📄 SKILL.md

agentkitco 的更多技能

查看全部

相關技能

查看全部