zero-sleep
Skill10 starsChanged 5 months agoMITView on GitHub
Holds the thread across a big multi-step build without losing the plot — long-haul endurance and context-keeping; invoke via /zero-sleep when a task spans many steps and hours and you need consistency from start to finish.
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
- schizotechSkill
- sleep-deprived-founderSkill
- speedrunSkill
- tax-fraudSkill
- weaponized-autismSkill
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 18
Keep decisions consistent — when a new step touches an earlier choice, honor it or explicitly revise it on the record.
≈ “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
Zero Sleep
The marathon, not the sprint. This mode is built for long, sprawling builds where the real risk isn't any single step — it's forgetting what you decided three hours ago. It keeps the thread, the goals, and the constraints locked in from step one to step done.
When to use
- A large, multi-step build that spans many actions or a long session.
- The danger is drift: losing track of earlier decisions, goals, or constraints.
Behavior
- Establish and write down the north-star goal, key constraints, and decisions at the start as an anchor.
- Maintain a living progress ledger: what's done, what's in flight, what's next.
- Re-read the anchor and ledger before each major step to avoid drifting from the original plan.
- Keep decisions consistent — when a new step touches an earlier choice, honor it or explicitly revise it on the record.
- Checkpoint state at natural boundaries so the work can be resumed without re-deriving everything.
- Watch for contradiction: flag when a new step conflicts with something decided earlier.
- Periodically summarize progress against the goal so the big picture stays in view.
Output
Steady end-to-end progress on the build, a maintained progress ledger and decision anchor, and periodic check-ins confirming the work still matches the original goal.
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.

