what-breaks
Skill4 starsChanged 5 months agoMITView on GitHub
Pre-mortem — assume the plan already failed and hunt the reasons before you commit. Adversarial failure-mode analysis ranked by likelihood and impact, with concrete mitigations. For pressure-testing an idea, change, or plan.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- suboss87/FDEOpstheir own version, first seen Sep 17, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- suboss87/FDEOps★ 940same 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 repository18 other files it gives its agents.
- biz-validateSkill
- braindumpSkill
- catch-upSkill
- clone-websiteSkill
- double-checkSkill
- explain-for-grandmaSkill
- heavy-buildSkill
- heavy-reviewSkill
- heavySkill
- make-promptSkill
- monitor-claudeSkill
- orientSkill
- overnightSkill
- reelSkill
- sanity-checkSkill
- save-sessionSkill
- shipSkill
- yt-tranSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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 11
If the subject touches code or this project, look at the actual relevant files/config first — don't critique in the abstract.
≈ “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
Stress-test a plan, idea, or change by assuming it has already failed and working backwards to why. The subject is in $ARGUMENTS, or the plan/change currently being discussed if empty. If there's no concrete subject in either place, ask in one line what to stress-test and stop — don't invent something to critique. Be a genuine adversary, not a cheerleader — the user wants honest challenge over reassurance.
Step 1 — Ground yourself in reality
If the subject touches code or this project, look at the actual relevant files/config first — don't critique in the abstract. Otherwise work from what's described, and state any assumptions you're forced to make.
Step 2 — Run the pre-mortem
It's months later and this failed. Enumerate the failure modes across these angles — only the ones that genuinely apply:
- Technical — what breaks, edge cases, scale, dependencies, data loss/corruption.
- Assumptions — what's being taken for granted that might be false.
- Human / process — misuse, the step someone forgets, handoff gaps.
- External — third-party/API/cost/policy/timing risks outside your control.
- Second-order — what this fixes but breaks elsewhere.
Step 3 — Rank and report
For each real risk: **[High / Med / Low]** — what fails, why, and the concrete mitigation or early-warning sign.
Order by likelihood × impact. Lead with the few that actually matter — do not pad the list to look thorough.
End with one honest line: the single biggest threat, and a verdict — sound-with-mitigations, or needs-a-rethink. No false alarms, no false comfort.
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.