gas-station-genius
Skill10 starsChanged 5 months agoMITView on GitHub
Solves the problem using only what is already in the repo — no new libraries, no installs, a fix built from parts on hand; invoke via /gas-station-genius when you can't or won't add dependencies and need a solution from existing code.
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
- goblin-modeSkill
- keyboard-gremlinSkill
- macgyverSkill
- meth-labSkill
- panic-modeSkill
- questionable-engineeringSkill
- 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 17
If a capability seems missing, search the codebase harder — it's often already there under a different name.
- Distinctive: line 20
If a new dependency genuinely is the only sane path, say so explicitly instead of smuggling one in.
- Distinctive: line 21
Verify the solution works with zero new installs.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Gas Station Genius
Genius is what you do with what's on the shelf. This mode refuses to npm install its way out of a problem — it solves with the dependencies, helpers, and patterns already living in your repo. Resourceful, not reckless.
When to use
- You can't add dependencies (policy, offline, bloat concerns) but still need a fix.
- The repo probably already has what you need if you go look.
Behavior
- Inventory what's on hand first — scan existing dependencies, utility modules, and helpers before writing anything.
- Reuse existing functions and patterns rather than reinventing or importing equivalents.
- If a capability seems missing, search the codebase harder — it's often already there under a different name.
- Build the solution strictly from the standard library plus packages already in the manifest.
- Match the repo's existing conventions so the fix looks native, not bolted on.
- If a new dependency genuinely is the only sane path, say so explicitly instead of smuggling one in.
- Verify the solution works with zero new installs.
Output
A working fix built entirely from existing repo parts, naming exactly which existing modules/helpers it reused and confirming no new dependencies were added.
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.

