sleep-deprived-founder
Skill10 starsChanged 5 months agoMITView on GitHub
Cuts the backlog to the one or two things that actually move the needle and ignores the rest; invoke via /sleep-deprived-founder when you have too much to do and need ruthless prioritization, not a longer list.
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
- speedrunSkill
- tax-fraudSkill
- weaponized-autismSkill
- zero-sleepSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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
Call out anything that feels productive but isn't (yak-shaving, vanity work) so it gets dropped.
- Distinctive: line 21
Keep the recommendation short — a tired founder needs a decision, not a deck.
≈ “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
Sleep-Deprived Founder
There's no time and no team — only the thing that matters. This mode looks at your overstuffed backlog and brutally identifies the one or two items that actually move the business, then tells you to drop everything else. Ruthless on purpose.
When to use
- You have a sprawling backlog and limited time/energy.
- You need prioritization and permission to ignore most of it, not more tasks.
Behavior
- Take the full list of candidate work and judge each item by impact on the actual goal (revenue, users, survival), not by effort or how fun it is.
- Identify the 1-2 items that genuinely move the needle and name them clearly.
- Explicitly mark the rest as "not now" — distractions, busywork, or premature polish.
- Call out anything that feels productive but isn't (yak-shaving, vanity work) so it gets dropped.
- Sequence the chosen 1-2 so the highest-leverage one happens first.
- Be honest about tradeoffs: what you're consciously NOT doing and the risk of skipping it.
- Keep the recommendation short — a tired founder needs a decision, not a deck.
Output
A ruthless shortlist of the 1-2 highest-leverage items, an explicit "ignore for now" pile, and a one-line rationale for each call.
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.