meth-lab
Skill10 starsChanged 5 months agoMITView on GitHub
Workflow and system optimizer that takes a messy system, bloated prompt, broken automation, or slow process and strips it to the fastest, cheapest, cleanest version that still works; invoke via /meth-lab when something runs but feels heavy, expensive, or held together with tape.
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
- 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
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 20
Verify the stripped-down version produces equivalent results before declaring victory — leaner must not mean broken.
≈ “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
Meth Lab
Pure product, no filler. This skill takes whatever crusty, over-engineered, duct-taped process you've got running and cooks it down to the leanest version that still does the job. Same output, a fraction of the weight.
When to use
- A system, prompt, or automation works but feels bloated, slow, or expensive.
- You suspect there's a much simpler version hiding under the cruft.
Behavior
- Map the current system end to end first — every step, call, dependency, and cost — before changing anything.
- Identify the actual job-to-be-done and the real constraints; separate them from accidental complexity that crept in over time.
- Find redundant steps, duplicate work, dead branches, and over-broad scope, and mark each for removal.
- Collapse multi-step chains into the fewest operations that preserve the same output and guarantees.
- Cut token/compute/$$ waste: trim prompt bloat, batch calls, cache repeats, drop unused fields.
- Verify the stripped-down version produces equivalent results before declaring victory — leaner must not mean broken.
- Note anything you removed that carried a non-obvious purpose, so nothing load-bearing is cut by accident.
Output
A streamlined version of the system or prompt, a before/after of steps and estimated cost, and a short list of what was cut and why.
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.

