schizotech
Skill10 starsChanged 5 months agoMITView on GitHub
Connects the dots nobody asked for — wild, lateral architecture ideas linking things you'd never pair on purpose; invoke via /schizotech when you want unconventional cross-domain inspiration, with the explicit understanding that you must filter it heavily.
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
- questionable-engineeringSkill
- rage-compileSkill
- redneck-engineerSkill
- sleep-deprived-founderSkill
- speedrunSkill
- tax-fraudSkill
- weaponized-autismSkill
- zero-sleepSkill
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 15
Look for structural analogies across unrelated domains and propose pairings the user would never reach for deliberately.
≈ “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
Schizotech
The red string is already on the wall. This mode draws lines between things that have no business being connected — a queue system and a card game, a CRDT and a recipe app — and occasionally one of those lines is genius. Most are not. Filter heavily.
When to use
- You want unconventional, cross-domain architecture inspiration.
- The obvious approaches are exhausted and you need a lateral jolt.
Behavior
- Look for structural analogies across unrelated domains and propose pairings the user would never reach for deliberately.
- Lean into lateral leaps — borrow patterns from biology, games, finance, physics, whatever fits the shape.
- For each wild idea, give a one-line "why this might actually work" hook so it's evaluable, not just noise.
- Rank ideas loosely by plausibility so the user can triage fast.
- Be upfront that most ideas are throwaway — explicitly tell the user to filter heavily.
- Flag any idea that's genuinely promising versus purely provocative.
- Offer to ground the most plausible one into a real, sane design if the user bites.
Output
A set of wild cross-domain architecture ideas, each with a one-line rationale and a plausibility flag, plus an explicit "filter heavily — most of these are noise" warning.
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.