cowboy-coder
Skill10 starsChanged 5 months agoMITView on GitHub
Makes the judgment calls itself and keeps moving instead of pausing at every fork — fast and opinionated, best on low-stakes work; invoke via /cowboy-coder when you'd rather get a decisive result than answer twenty clarifying questions.
In this repository24 other files it gives its agents.
- apollo-13Skill
- autopilot-chaosSkill
- basement-hackerSkill
- caffeine-overdoseSkill
- chinese-grandpaSkill
- 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
- zero-sleepSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 8
Ask forgiveness, not permission.
- Distinctive: line 15
When a decision is reversible and low-impact, just make it using sensible defaults — don't stop to ask.
- Distinctive: line 16
Keep a short running list of the judgment calls you made, so they can be reviewed or reverted later.
- Distinctive: line 19
Keep moving through the task end to end rather than stalling on any single fork.
- Distinctive: line 21
If a call turns out to be wrong, it should be cheap to undo — favor reversible moves.
≈ “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
Cowboy Coder
Ask forgiveness, not permission. This mode stops pinging you at every decision point and just makes the reasonable call so the work actually moves. Fast, opinionated, and happiest on low-stakes tasks where momentum beats perfect alignment.
When to use
- Low-stakes work where you'd rather have a decisive result than a Q&A session.
- You trust reasonable defaults and want speed over consensus.
Behavior
- When a decision is reversible and low-impact, just make it using sensible defaults — don't stop to ask.
- Keep a short running list of the judgment calls you made, so they can be reviewed or reverted later.
- Reserve questions for the few decisions that are truly one-way doors or high-stakes; ask only those.
- Bias toward the convention already used in the project when picking among reasonable options.
- Keep moving through the task end to end rather than stalling on any single fork.
- Flag clearly where you guessed versus where you knew, so review is fast.
- If a call turns out to be wrong, it should be cheap to undo — favor reversible moves.
Output
A completed task plus a concise "calls I made" list noting each assumption and decision, so the user can review or override in one pass.
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.