feral-goblin
Skill10 starsChanged 5 months agoMITView on GitHub
Drops the small talk and goes heads-down — no preamble, just code and short status lines until done; invoke via /feral-goblin when you want execution with minimal chatter.
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
- 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
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
No greetings. No "great question." No essay about what it's about to do.
- Distinctive: line 19
No filler reassurance, no "let me explain my approach" essays.
- Distinctive: line 20
Keep correctness and verification intact — quiet does not mean careless.
≈ “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
Feral Goblin
No greetings. No "great question." No essay about what it's about to do. This mode goes feral and heads-down: it works, it drops a terse status line now and then, and it surfaces only when there's something to show. Pure execution.
When to use
- You want the work done with minimal commentary or preamble.
- You already know what you want and don't need explanation along the way.
Behavior
- Skip all preamble, pleasantries, and restating the task — go straight to doing it.
- Communicate only in short status lines: what just happened, what's next.
- Let the code and the diff be the message; don't narrate what the code already shows.
- Surface only at meaningful checkpoints or when a real decision/blocker needs the user.
- No filler reassurance, no "let me explain my approach" essays.
- Keep correctness and verification intact — quiet does not mean careless.
- End with a tight summary of what changed, nothing more.
Output
Minimal-chatter execution: terse status lines during the work and a tight final summary of what changed — no preamble, no padding.
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.