agentleFS
Sign inStart free
rpraharajrpraharaj/ai-engineer/skills/write-prd/SKILL.md

write-prd

Skill1 starsChanged 15 days agoMITView on GitHub

Write a product requirements document — problem, audience, goals, non-goals, and testable success. Use when the user asks for a PRD, product spec, requirements, or "what should we build." Do not write product code. Do not PRD a one-line bug.

28 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use stakeholder-update, prioritize and 5 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.
  • AnthropicSkill

    stakeholder-update

    Generate a stakeholder update tailored to audience and cadence. Use when writing a weekly or monthly status for leadership, announcing a launch, escalating a risk or blocker, or translating the same progress into exec-brief, engineering-detail, or customer-facing versions.

    Also in 3 projects that use this

  • blueOctopusAISkill

    prioritize

    Also in 3 projects that use this

  • VercelSkill

    agent-browser

    Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

    Also in 3 projects that use this

  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 4 projects that use this

  • GoogleSkill

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 4 projects that use this

  • BlockSkill

    frontend-design

    Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

    Also in 3 projects that use this

  • +1 more from google

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not implement. Do not invent users, metrics, or legal constraints.

    line 14
  2. Very specific:

    If the product ask is already tiny (one behavior, success is obvious), say so and offer shape-work.

    line 26
  3. Distinctive:

    Read AGENTS.md if present.

    line 28
  4. Distinctive:

    Ask at most a few blocking questions (who it is for, what success looks like, contradicting goals).

    line 32
  5. Very specific:

    Use the first that exists: docs/prd/, docs/product/, docs/requirements/, a path AGENTS.md names.

    line 36
  6. Very specific:

    If none: write in the reply, and offer to create docs/prd/ in this repo's markdown style.

    line 38
  7. Distinctive:

    No secrets. Mark unknowns as unknowns.

    line 53
  8. Very specific:

    Do not implement. Next is usually write-design (how), write-architecture (new boundaries), or write-dev-tasks if they only want a breakdown.

    line 68

“Common” is measured: kept by at least 6 in 10 of the 24 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

Write PRD

Capture what to build and why. This is not a technical design (write-design), not system shape (write-architecture), and not an implementable slice (shape-work).

Do not implement. Do not invent users, metrics, or legal constraints.

Is this the right skill?

SignalDo this instead
One-line bug, typo, or clear small changeshape-work or implement-change
How we will build an already-agreed productwrite-design
System boundaries / durable shapewrite-architecture
Tickets from an existing PRDwrite-dev-tasks
Why we picked library Xrecord-decision

If the product ask is already tiny (one behavior, success is obvious), say so and offer shape-work. Do not pad a PRD.

Read AGENTS.md if present. Skim only enough of the product to avoid inventing a second app.

Ask only when blocked

Ask at most a few blocking questions (who it is for, what success looks like, contradicting goals). Do not ask what you can see in the repo or an existing PRD.

Find the home

Use the first that exists: docs/prd/, docs/product/, docs/requirements/, a path AGENTS.md names.

If none: write in the reply, and offer to create docs/prd/ in this repo's markdown style.

Name the file like existing PRDs. If there are none, docs/prd/YYYY-MM-DD-<slug>.md.

Write

Copy headings from references/prd-template.md in this skill directory. Keep every heading; write n/a when a section does not apply. Do not invent extra sections. If that file is missing, use the same headings: Summary, Problem, Current behavior, Audience, Goals, Non-goals, Scope, Success, User stories, Journeys, Requirements, UX notes, Analytics, Privacy and data, Constraints, Dependencies, Rollout, Risks, Assumptions, Open questions, Next.

Fill from the user and the repo:

  • Problem is a real hurt, not a solution in disguise.
  • Non-goals is non-empty.
  • Success checks are yes/no (command, UI observation, metric this product already has). At least one would fail today. Do not invent a baseline.
  • Must / Should / Later — do not dump a wishlist into Must.
  • Journeys cover happy, empty, and error when the change is user-facing.
  • No secrets. Mark unknowns as unknowns.

Quality

  • A stranger could tell shipped vs not from Success.
  • Requirements do not specify tables, frameworks, or folder layout (that is write-design).
  • Unused sections are n/a, not deleted.
  • Next names a real skill.

Done

  1. Path or the full text in the reply
  2. The problem in one sentence
  3. Blocking questions, or none

Do not implement. Next is usually write-design (how), write-architecture (new boundaries), or write-dev-tasks if they only want a breakdown. Tiny first slice: shape-work.

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