mikedev115/aetox/aetox-verify
Claude Code and agent skill by mikedev115/aetox
- community
Checking that the SKILL.md file is still in the repository.
ตอนกำลังจะบอกผู้ใช้ว่าสิ่งใดใช้ได้ ผ่าน บิ้วได้ หรือแก้แล้ว ก่อน commit หรือเปิด PR
Install
npx vskill@latest install mikedev115/aetox/aetox-verifySKILL.md
Aetox Verify
No claim without fresh evidence. If the command that proves it was not run in this turn, on this code, the claim is not made.
The gate
Before saying done, fixed, passing, working:
- Name the command that would prove it.
- Run it, whole and fresh. Not the run from before the last edit.
- Read all of it: the exit code, the failure count, the last lines.
- Does the output say what you are about to say? If not, say what it does
say, with the output.
- Only then, the claim, with the evidence beside it.
What proves what
| The claim | What proves it | What does not | |
|---|---|---|---|
| Tests pass | the test command, zero failures | an earlier run; "should pass" | |
| Build succeeds | the build command, exit 0 | the linter passing; the logs looking fine | |
| Linter clean | the linter, zero errors | a partial run extrapolated | |
| Bug fixed | the original symptom, reproduced, now gone | the code changed; the theory sounds right | |
| Regression test works | seen red, then seen green | passing once | |
| It works end to end | the thing, exercised, and its output read | each part passing on its own |
The words that mean stop
"Should work now", "I am confident", "looks right", "the tests will pass": each is a claim made before its command. Run the command instead; if it cannot be run, say that it cannot and why, and say the claim is untested.
Partial verification is reported as partial: what was run, what was not, and what is therefore unknown.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckinginternal/skill/skills/aetox-verify/SKILL.md
Popularity
- Repository stars
- 46
- Repository forks
- 15
- 7-day trend score
- 24
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/mikedev115/aetox/aetox-verify)