agentleFS
Gaurav890Gaurav890/everything-agentic-engineering/.claude/skills/create-prd/SKILL.md

create-prd

Skill1 starsChanged 2 months agoMITView on GitHub

Turn a product idea into a rigorous PRD with stable requirement IDs, user journeys, non-goals, edge cases, security/privacy considerations, metrics, and testable acceptance criteria.

44 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use prioritize-features, brainstorm-okrs and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • skytiger6724Skill

    prioritize-features

    Prioritize a backlog of feature ideas based on impact, effort, risk, and strategic alignment with top 5 recommendations. Use when prioritizing a feature backlog, making scope decisions, or ranking product ideas.

    Also in 4 projects that use this

  • skytiger6724Skill

    brainstorm-okrs

    Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.

    Also in 4 projects that use this

  • miovragSkill

    strategy-red-team

    Red-team a PRD, roadmap, or strategy by attacking its load-bearing assumptions before reality does. Steelmans then attacks each claim, ranks failure modes by impact × likelihood × cheapness-to-test, and returns the cheapest test and kill criteria for each. Use when stress-testing a plan, pressure-testing a strategy, challenging assumptions, or preparing a doc for executive review.

    Also in 3 projects that use this

  • launchapp-devSkill

    interview-script

    Create a structured user interview script with warm-up, core exploration, and wrap-up sections. Use when preparing for user research interviews to ensure consistent, insightful conversations.

    Also in 4 projects that use this

  • About-IntelligenceSkill

    beachhead-segment

    Identify the first beachhead market segment for a product launch.

    Also in 4 projects that use this

  • nandanosqlSkill

    customer-journey-map

    Map the complete customer experience across all touchpoints using the NNGroup framework. Identifies pain points, emotions, and opportunities at every stage of the user journey.

    Also in 5 projects that use this

  • +5 more from skytiger6724

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 42 edited versions we read keep these.

  • 4

    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:

    Use this skill when a product idea is vague, requirements are incomplete, or implementation should not begin yet.

    line 8
  2. Distinctive:

    Do not convert an assumption into a fact silently.

    line 32
  3. Distinctive:

    Every acceptance criterion must be observable and testable.

    line 52
  4. Distinctive:

    Do not begin implementation until blocking ambiguity is resolved or explicitly accepted.

    line 103

“Common” is measured: kept by at least 6 in 10 of the 42 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

Create PRD

Use this skill when a product idea is vague, requirements are incomplete, or implementation should not begin yet.

Process

1. Intake

Capture:

  • problem,
  • target user,
  • current workaround,
  • desired outcome,
  • urgency,
  • constraints,
  • known dependencies.

2. Separate epistemic states

Maintain explicit sections:

  • Facts
  • Assumptions
  • Open questions
  • Decisions
  • Non-goals

Do not convert an assumption into a fact silently.

3. Define journeys

For each major persona:

  • trigger,
  • starting state,
  • happy path,
  • alternate paths,
  • recovery paths,
  • terminal state.

4. Define requirements

Use stable IDs:

  • FR-001 functional requirement
  • NFR-001 non-functional requirement
  • AC-001 acceptance criterion

Every acceptance criterion must be observable and testable.

Bad:

The page should feel fast.

Better:

AC-014: On a warm cache under the agreed test environment, the primary route becomes interactive within the defined performance budget and no loading spinner remains after data resolves.

5. Cover non-happy states

Explicitly design:

  • loading,
  • empty,
  • sparse,
  • dense,
  • invalid input,
  • auth failure,
  • authorization failure,
  • offline/network failure,
  • partial failure,
  • retry,
  • timeout,
  • duplicate submission,
  • dependency outage.

6. Security/privacy

Ask:

  • What sensitive data exists?
  • Who may read/write it?
  • Where are trust boundaries?
  • What abuse cases matter?
  • What must never be logged?

7. Success

Define:

  • product outcome,
  • user outcome,
  • operational metric,
  • quality metric,
  • launch gate.

8. Output

Update:

  • docs/10-product/PRD.md
  • docs/10-product/ACCEPTANCE_CRITERIA.md
  • docs/10-product/NON_GOALS.md
  • docs/10-product/OPEN_QUESTIONS.md

Do not begin implementation until blocking ambiguity is resolved or explicitly accepted.

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.