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

write-prd

Skill0 starsChanged 16 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 of what to build, or /write-prd. 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

6 rules. 0 are common, 4 are distinctive, and 2 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.

  • 2

    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 19
  2. Very specific:

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

    line 32
  3. Distinctive:

    Read AGENTS.md if present.

    line 47
  4. Distinctive:

    Must / Should / Later — do not dump a wishlist into Must.

    line 52
  5. Distinctive:

    No secrets. Unknowns stay unknown.

    line 53
  6. Very specific:

    Leave status draft or review until the authorized human signs problem and success.

    line 54

“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 write-design, not write-architecture, and not shape-work.

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

Is this the right skill?

SignalDo this instead
One-line bug or tiny changeshape-work or implement-change
How we will build an agreed productwrite-design
System boundarieswrite-architecture
Testable functional contractwrite-requirements
Tickets from an existing PRDwrite-dev-tasks
Pitch / problem not yet a PRDwrite-opportunity

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

Required inputs

  • A problem the user can point at, or an accepted opportunity brief
  • AGENTS.md; context/glossary.md if present

Human decisions (do not invent)

  • Who it is for, if not in context
  • Success numbers that are not already measured
  • Must vs later

Procedure

  1. Read AGENTS.md if present. Skim the product enough to avoid inventing a second app.
  2. Find the home: first existing docs/prd/, docs/product/, a path AGENTS.md names, or offer to create docs/prd/.
  3. Name: docs/prd/YYYY-MM-DD-<slug>.md.
  4. Open references/prd-template.md. Copy every heading. Write n/a when unused.
  5. Problem is a hurt, not a solution. Non-goals is non-empty. Success checks are yes/no and at least one fails today. Do not invent a baseline.
  6. Must / Should / Later — do not dump a wishlist into Must. Journeys cover happy, empty, and error when user-facing.
  7. No secrets. Unknowns stay unknown.
  8. Leave status draft or review until the authorized human signs problem and success. Record source revision and approval evidence using the home in context/decision-rights.md; an agent must not promote its own draft to accepted. If scope or success changes, invalidate affected downstream approval and verification.

Output

  • Path: docs/prd/YYYY-MM-DD-<slug>.md
  • Template: references/prd-template.md

Quality bar

  • A stranger can tell shipped vs not from Success
  • Non-goals is non-empty
  • Requirements do not specify tables, frameworks, or folder layout
  • Unused headings are n/a
  • Next names a real skill
  • Accepted status is backed by human approval evidence for this revision

Done

  1. Path or the full text in the reply
  2. The problem in one sentence
  3. Next skill: write-requirements, write-architecture, write-design, or 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