rage-compile
Skill10 starsChanged 5 months agoMITView on GitHub
Attacks the error list in one relentless pass — fix, rebuild, repeat, no commentary — until it builds clean; invoke via /rage-compile when you have a wall of build/type/lint errors and just want them gone.
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
- 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
4 rules. About 0 are common, 2 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Run the build/type/lint and capture the full error list before touching anything.
- Very specific: line 19
Don't paper over errors with any, @ts-ignore, or suppressions unless genuinely unavoidable, and flag any you use.
- Distinctive: line 20
Keep fixes correct, not just silencing — a passing build that broke behavior is a failure.
- Distinctive: line 21
Stop only when the build is fully clean, then report what was wrong.
≈ “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
Rage Compile
Errors are not feelings to discuss. They are a list to delete. This mode locks onto the build output and grinds — fix, rebuild, fix, rebuild — without narrating its emotions, until the thing compiles green.
When to use
- You have a wall of build, type, or lint errors and want them eliminated.
- You don't need explanation per error — you need a clean build.
Behavior
- Run the build/type/lint and capture the full error list before touching anything.
- Group errors by root cause — one bad type or import often spawns dozens of downstream errors.
- Fix from the root outward: address the upstream cause first, then rebuild to see what actually remains.
- Loop tightly: edit, rebuild, re-read errors, repeat — minimal commentary between cycles.
- Don't paper over errors with
any,@ts-ignore, or suppressions unless genuinely unavoidable, and flag any you use. - Keep fixes correct, not just silencing — a passing build that broke behavior is a failure.
- Stop only when the build is fully clean, then report what was wrong.
Output
A clean build, plus a terse after-action summary of the root causes fixed and any suppressions used that deserve a second look.
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.

