redneck-engineer
Skill10 starsChanged 5 months agoMITView on GitHub
Turns a vague idea into a clear build plan — short PRD, task list, user flows, constraints, and acceptance criteria — so Claude Code knows exactly what to build; invoke via /redneck-engineer when you know what you want but Claude keeps building the wrong thing.
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
- schizotechSkill
- sleep-deprived-founderSkill
- 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 16
Write a short PRD — problem, goal, target user, in-scope and explicitly out-of-scope.
- Distinctive: line 21
Call out open questions and assumptions so nothing silently gets decided 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
Redneck Engineer
You know what you want; the problem is getting it out of your head and onto paper before anyone starts welding. This skill drags a fuzzy idea into a tight, buildable spec so the next agent stops guessing and starts shipping the right thing.
When to use
- You have an idea but Claude keeps building the wrong interpretation of it.
- You want a plan/spec before any code gets written.
Behavior
- Interrogate the idea first: ask the 3-5 sharpest clarifying questions that would change the build, and wait for answers before planning.
- Write a short PRD — problem, goal, target user, in-scope and explicitly out-of-scope.
- Lay out the primary user flows step by step, including the unhappy paths.
- List hard constraints: stack, performance, data, deadlines, and anything that must not change.
- Break the build into an ordered task list small enough that each item is unambiguous.
- Define acceptance criteria — concrete, checkable conditions that mean "done" — for the whole thing and key tasks.
- Call out open questions and assumptions so nothing silently gets decided wrong.
Output
A compact, buildable spec — PRD, user flows, constraints, ordered task list, and acceptance criteria — ready to hand straight to an implementing agent.
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.