agentleFS
Sign inStart free
timdevaitimdevai/proteus/skills/prd-builder/SKILL.md

prd-builder

Skill1 starsChanged 5 months agoMITView on GitHub

Walks you through a one-page PRD before any code. Fits in a Notion page, prevents 80% of "we built the wrong thing" outcomes. Trigger phrases: PRD, spec out, product requirement, requirements doc, let's plan this feature properly. /prd <feature> — start the flow.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    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
  1. Distinctive:

    Ask 5 questions in ONE message, not 5 rounds:

    line 56

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

prd-builder

Walks you through a one-page PRD before any code. Fits in a Notion page, prevents 80% of "we built the wrong thing" outcomes.

When to activate

Trigger phrases: PRD, spec out, product requirement, requirements doc, let's plan this feature properly.

Output template

# PRD: <Feature Name>
Author: <name> | Date: <YYYY-MM-DD> | Status: draft

## Problem
<2-3 sentences. Whose pain, how often, what they do today.>

## Goal
<one-sentence outcome>

## Non-goals
- <thing we're not doing>
- <thing we're not doing>

## User stories
- As a <user>, I want to <action>, so that <outcome>.
- (3-5 max)

## Solution sketch
<3-5 sentences on the approach. Diagrams optional.>

## Requirements
- Must: <hard requirement>
- Should: <strong preference>
- Won't (v1): <explicit cut>

## Success metrics
- Primary: <quant metric, target>
- Secondary: <quant metric, target>

## Open questions
- <thing we haven't decided>
- <thing we haven't decided>

## Risks
- <risk> → <mitigation>
- <risk> → <mitigation>

## Timeline (rough)
- Week 1: <milestone>
- Week 2: <milestone>

Process

  1. Ask 5 questions in ONE message, not 5 rounds:
    • What problem? Whose?
    • What's the goal in one sentence?
    • What's explicitly out of scope?
    • How will you know it worked (metric)?
    • What might kill it (risk)?
  2. Compose the PRD draft
  3. Ask "anything missing?"
  4. Save to docs/prd-<feature-slug>.md if user agrees
  5. Suggest the natural next skill: scope-clarifier → tdd-flow → commit-curator

Inputs

  • Rough feature idea from the user
  • Project context (existing PRDs, recent decisions)

Outputs

  • 1-page PRD in markdown
  • (optional) Saved file at docs/prd-<slug>.md

Slash command

/prd <feature> — start the flow.

Why this skill

  • 80% of feature failure traces to skipped problem definition
  • A 200-word PRD prevents 2000 lines of wrong code
  • One-page rule keeps it from becoming "Notion theater"

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free