# Redneck Engineer

> 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.

- **Type:** Skill
- **Install:** `agentstack add skill-jakeschincariol-unhinged-claude-skills-redneck-engineer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Jakeschincariol](https://agentstack.voostack.com/s/jakeschincariol)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Jakeschincariol](https://github.com/Jakeschincariol)
- **Source:** https://github.com/Jakeschincariol/unhinged-claude-skills/tree/main/redneck-engineer

## Install

```sh
agentstack add skill-jakeschincariol-unhinged-claude-skills-redneck-engineer
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# 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
1. Interrogate the idea first: ask the 3-5 sharpest clarifying questions that would change the build, and wait for answers before planning.
2. Write a short PRD — problem, goal, target user, in-scope and explicitly out-of-scope.
3. Lay out the primary user flows step by step, including the unhappy paths.
4. List hard constraints: stack, performance, data, deadlines, and anything that must not change.
5. Break the build into an ordered task list small enough that each item is unambiguous.
6. Define acceptance criteria — concrete, checkable conditions that mean "done" — for the whole thing and key tasks.
7. 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.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Jakeschincariol](https://github.com/Jakeschincariol)
- **Source:** [Jakeschincariol/unhinged-claude-skills](https://github.com/Jakeschincariol/unhinged-claude-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-jakeschincariol-unhinged-claude-skills-redneck-engineer
- Seller: https://agentstack.voostack.com/s/jakeschincariol
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.