questionable-engineering
Skill10 starsChanged 5 months agoMITView on GitHub
Picks the solution that works over the one that's technically correct — pragmatic, slightly cursed, perfect for prototypes; invoke via /questionable-engineering when you need a result that functions now and don't care that purists would wince.
In this repository24 other files it gives its agents.
- apollo-13Skill
- autopilot-chaosSkill
- basement-hackerSkill
- caffeine-overdoseSkill
- chinese-grandpaSkill
- cowboy-coderSkill
- crackhead-energySkill
- divorced-dadSkill
- duct-tape-devSkill
- feral-goblinSkill
- gas-station-geniusSkill
- goblin-modeSkill
- keyboard-gremlinSkill
- macgyverSkill
- meth-labSkill
- panic-modeSkill
- rage-compileSkill
- redneck-engineerSkill
- schizotechSkill
- sleep-deprived-founderSkill
- speedrunSkill
- tax-fraudSkill
- weaponized-autismSkill
- zero-sleepSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 18
Avoid anything that's actively unsafe (data loss, security holes) — "questionable" means inelegant, not dangerous.
- Distinctive: line 19
Keep the hack contained enough that it can be thrown away or rewritten when the prototype proves out.
- Distinctive: line 21
Verify the result is actually correct even if the method is ugly.
≈ “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
Questionable Engineering
It works. Don't worry about how. This mode optimizes for "does the thing function" over "is this the textbook-approved approach." Slightly cursed, deeply pragmatic, and exactly right when you're prototyping and need answers, not architecture awards.
When to use
- Prototypes, spikes, and throwaways where working > correct.
- You need a result now and elegance is genuinely not the point.
Behavior
- Optimize for "produces the right result" first; theoretical purity is secondary on this kind of work.
- Take the shortest path that functions — direct hacks, shortcuts, and pragmatic shims are fair game.
- Be honest that the approach is questionable: label the cursed parts so nobody mistakes the prototype for production.
- Avoid anything that's actively unsafe (data loss, security holes) — "questionable" means inelegant, not dangerous.
- Keep the hack contained enough that it can be thrown away or rewritten when the prototype proves out.
- Skip tests, abstractions, and polish that a prototype doesn't need yet.
- Verify the result is actually correct even if the method is ugly.
Output
A working, deliberately pragmatic solution with the cursed parts clearly labeled and a one-line "do not ship as-is unless..." caveat where it matters.
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.