agentleFS
tejastn10tejastn10/workbench/skills/planning/write-prd/SKILL.md

write-prd

Skill1 starsChanged 2 months agoMITView on GitHub

Draft a PRD using Tejas's template and house conventions — table header, `---` divider between every section, emoji H2s, outlines for prose and tables for structured data. Interview for the missing pieces before writing; never invent goals, metrics, or scope. Use when asked to "write a PRD", "draft a spec", "turn this into a PRD", or to flesh out a feature doc.

28 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use stakeholder-update, prioritize and 7 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

  • SentrySkill

    write-docs

    Create or update documentation pages for the Abacus docs site. Use when adding new documentation, updating existing pages, or ensuring docs stay in sync with code changes. Ensures pages follow Starlight patterns and build correctly.

    Also in 3 projects that use this

  • SentrySkill

    write-tests

    Write tests following project conventions. Use when adding new tests or modifying existing ones.

    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

    grill-me

    A relentless interview to sharpen a plan or design.

    Also in 4 projects that use this

  • +1 more from getsentry

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 24 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:

    Interview for the gaps: Ask one focused question at a time.

    line 23

“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 a PRD

Fills in docs/templates/PRD.md. The template is the source of truth for structure and formatting — don't restructure it.

When to use

  • A feature or project needs a written spec before build.
  • A rough idea / thread / ticket needs to become a reviewable document.
  • An existing PRD needs a section fleshed out.

Process

  1. Read the template so the output matches it exactly (section order, emoji headers, --- between every section, table header block).
  2. Gather what exists — the ticket, the thread, any design doc, the code if the problem is in-repo. Quote real numbers; don't estimate impact silently.
  3. Interview for the gaps. Ask one focused question at a time. The sections that almost always need input:
    • Problem / why now — what's the trigger, what does the status quo cost.
    • Goals — must be measurable or observable. Push back on vague ones.
    • Non-goals — ask explicitly "what's out of scope?" — this is the section people skip and reviewers fight over.
    • Success metrics — metric, baseline, target. If there's no baseline, say so.
    • Rollout — flag name, migration steps, rollback path.
    • Open questions — every one gets an owner and a needed-by date.
  4. Draft it. One sentence under the title. Fill the header table. Write Summary last, once the body is settled — it should stand alone.
  5. Mark unknowns as > **TBD:** … blockquotes rather than inventing an answer.
  6. Save to docs/prd/<slug>.md in the target repo. Start Status at Draft.

House conventions

  • Header is a table. One --- between every section. Emoji H2s as in the template.
  • Outlines (nested bullets) for prose sections; tables for user stories, functional requirements, rollout phases, risks, metrics, open questions.
  • [bracketed] placeholders get replaced; delete the italic guidance lines as each section is written.
  • Conventional-commit the doc: docs: add PRD for <feature>.

Anti-patterns

  • ❌ Inventing goals, metrics, or scope to fill a section. Ask or mark TBD.
  • ❌ Reordering or renaming the template's sections.
  • ❌ A Summary that only makes sense after reading the rest.
  • ❌ Non-goals left empty.
  • ❌ Prose where the template wants a table.

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.