crash-out
Skill9 starsChanged 17 days agoMITView on GitHub
Check an answer by trying to disprove it before sending it. Use on factual questions, research, numbers, laws and limits that change by year, API behavior, and debugging conclusions, where a confident wrong answer costs more than a slower right one. Also when the user asks to "검증", "확인해봐", "crash out", or "틀린 데 없는지 봐".
1 other project uses a version of this.
Adopted by
Most recently taken up by
- Jakeschincariol/claude-illegal-codestheir own version, first seen Aug 7, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- Jakeschincariol/claude-illegal-codes★ 11same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository56 other files it gives its agents.
- harness/CLAUDE.mdCLAUDE.md
- academic-research-routerSkill
- accessibilitySkill
- adaptive-project-harnessSkill
- anti-slopSkill
- apple-designSkill
- arenaSkill
- astryx-design-systemSkill
- attention-spanSkill
- copywritingSkill
- croSkill
- cybersecurity-skill-routerSkill
- design-isms-referenceSkill
- design-minimal-blue-pitchdeckSkill
- design-source-routerSkill
- design-specSkill
- diagnosing-bugsSkill
- emil-design-engSkill
- external-review-routerSkill
- frontend-designSkill
- gh-address-commentsSkill
- handoffSkill
- humanize-japaneseSkill
- hyperframes-animationSkill
- hyperframes-audioSkill
- hyperframes-cliSkill
- hyperframes-coreSkill
- hyperframes-creativeSkill
- hyperframes-keyframesSkill
- hyperframes-registrySkill
- hyperframesSkill
- hyperframes-studioSkill
- impeccableSkill
- implement-changeSkill
- leak-checkSkill
- library-docsSkill
- loop-librarySkill
- media-useSkill
- motion-graphicsSkill
- obsidian-memory-routerSkill
- openpencil-cliSkill
- ponytailSkill
- product-marketingSkill
- project-startSkill
- pr-ossSkill
- remove-ai-marksSkill
- requirements-clarificationSkill
- retroSkill
- review-changeSkill
- screenshotSkill
- security-auditSkill
- startup-evidenceSkill
- taste-guided-uiSkill
- team-patternsSkill
- understandSkill
- verification-before-completionSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
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
- Distinctive: line 15
Run the code, command or query when one exists.
- Distinctive: line 16
Read the actual source: the file, the official docs, the statute, the changelog.
- Distinctive: line 17
Search for evidence against the claim, not for it.
- Distinctive: line 19
Check the claims the answer leans on hardest from two independent angles.
- Distinctive: line 25
If a central claim broke, say plainly that the first answer was wrong and what changed.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Crash out
A first draft tends to defend itself. This skill reverses that: after drafting, the job is to break the draft, and only what survives is sent.
Steps
- Draft the answer, but do not send it yet.
- List every claim the answer depends on: facts, numbers, dates, names, versions, limits, API behavior, cause-and-effect statements. If the answer would change when the claim is wrong, it goes on the list.
- Try to disprove each claim with evidence, not by rereading your own reasoning.
- Run the code, command or query when one exists.
- Read the actual source: the file, the official docs, the statute, the changelog.
- Search for evidence against the claim, not for it.
- For anything that changes over time (tax limits, prices, versions, rules), find the current value and its effective date.
- Check the claims the answer leans on hardest from two independent angles.
- Give each claim one verdict:
- Held: attacked and still standing. Note the evidence.
- Unverified: could not confirm or refute. Keep it only with a visible "확인 못 함" label and what would confirm it.
- Broken: disproved. Fix it or remove it.
- Rewrite the answer from held claims only, with unverified ones labeled.
- If a central claim broke, say plainly that the first answer was wrong and what changed. Do not smooth it over.
Output
The checked answer, with unverified points labeled where they appear. Then a short list of the claims that broke and what replaced them. If nothing broke, say so in one line.
Not for
Opinions, style choices, and small tasks with nothing to check. There, a crash-out only slows the answer.
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
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.