agentleFS
librosdeialibrosdeia/builder-method-claude-plugin/skills/prd/SKILL.md

prd

Skill0 starsChanged 5 days agoMITView on GitHub

Phase 2 of the Builder Method — turn the concrete idea into a PRD (product requirements document) with numbered user flows and acceptance criteria, written to builder/02-prd.md. Use after the Idea phase, when the user wants to define exactly what to build, or runs /builder:prd.

129 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use context-optimize, usecase 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.
  • ibahgatSkill

    context-optimize

    Improve context efficiency and cache stability for long or complex sessions.

    Also in 3 projects that use this

  • gabriellstSkill

    usecase

    Create an application use case. Use when implementing business operations like CreateOrder, ProcessPayment, CancelBooking. Use this skill for any command/mutation that orchestrates domain logic, whether simple CRUD or complex multi-step transactions with sagas. Dispatch hub — routes to typescript/go variants by file extension.

    Also in 3 projects that use this

  • jidechaoSkill

    modern-go

    Modernize Go code by applying version-appropriate idioms and APIs (gofix-style transformations). Scans go.mod for the Go version, then transforms Go source files to use modern patterns—from Go 1.0 through 1.26+. Use when the user says "现代化","现代Go语言", "地道的", "idiomatic", "modernize", "modern-go", "update Go code", "gofix", or wants to upgrade Go idioms.

    Also in 3 projects that use this

  • ulises-jeremiasSkill

    trd

    WHAT — Draft and review a Technical Requirements Document (TRD) using the template, typically

    Also in 3 projects that use this

  • jidechaoSkill

    loop-it

    Automated issue loop with checkpoint/resume: fetch open GitHub issues → dependency-aware topological sort → implement each issue end-to-end → review with /review-it → document with /note-it → ship with /ship-it → repeat. Persists state to .loop-state.json for crash recovery. Triggers on: loop-it, loop issues, auto implement, 批量实现, 循环实现, 实现所有issue, 恢复循环, resume loop.

    Also in 3 projects that use this

  • snarktankSkill

    ralph

    Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json.

    Also in 16 projects that use this

  • +2 more from jidechao

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 106 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the PRD has debt (it was generated by a gate), offer to review it first, as gates.md explains.

    line 18
  2. Very specific:

    If the file already exists, follow "Existing outputs" in state-rules.md (revise it, never overwrite the user's edits).

    line 34
  3. Very specific:

    If the subagent tool isn't available, do the review yourself, with the same checklist (${CLAUDE_PLUGIN_ROOT}/agents/prd-reviewer.md).

    line 48
  4. Distinctive:

    every flow has at least one acceptance criterion.

    line 57
  5. Distinctive:

    Ask the user to approve the PRD.

    line 61
  6. Distinctive:

    update the progress page.

    line 64

“Common” is measured: kept by at least 6 in 10 of the 106 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

Phase 2 · PRD

Goal: a document precise enough for Claude to build from as autonomously as possible. Input: builder/01-idea.md. Output: builder/02-prd.md, with its flows mirrored into state.flows.

Read and follow:

  • ${CLAUDE_PLUGIN_ROOT}/skills/_shared/tone.md
  • ${CLAUDE_PLUGIN_ROOT}/skills/_shared/state-rules.md
  • ${CLAUDE_PLUGIN_ROOT}/skills/_shared/gates.md: apply the PRD gate first.
  • ${CLAUDE_PLUGIN_ROOT}/skills/prd/references/prompts.md (the method's original intent)

If the PRD has debt (it was generated by a gate), offer to review it first, as gates.md explains.

Step 1 · clarify

Set phases.prd.status to in_progress. Read 01-idea.md. Find what is still undefined, and ask about it in small batches:

  • users and roles;
  • the main things each user does;
  • data (what is stored, how sensitive it is);
  • rules and limits (e.g. "cancel up to 24 h before");
  • edge cases (what if a slot is taken, what if there's no connection…);
  • privacy, and tone and look.

Plan before writing: summarise what you understood in a short list and get a yes.

Step 2 · write

If the file already exists, follow "Existing outputs" in state-rules.md (revise it, never overwrite the user's edits). Otherwise: write builder/02-prd.md from ${CLAUDE_PLUGIN_ROOT}/skills/prd/templates/02-prd.md. Translate the section headings to the user's language. Keep these markers exactly, because other phases rely on them:

  • each flow heading is ### F<n> — <name> (F1, F2…; the long dash —);
  • each flow has an acceptance list. In English it is written Acceptance: with items of the form When <situation>, then <result>. In other languages, translate the words but keep the same structure.

Each flow is one thing a user does from start to finish ("Book a slot", "Cancel a booking"). Aim for 3–8 flows in a v1.

Mirror the flows into state.flows: { "id": "F1", "name", "acceptance": [...], "tasks": [], "validation": "pending" }. Set project.hasFrontend if it is still null.

Step 3 · review

Delegate the review to the prd-reviewer subagent (Agent tool, subagent_type: "builder:prd-reviewer", or prd-reviewer if that's how it's listed). Give it the paths of 01-idea.md and 02-prd.md. It returns a numbered list of proposed changes; it doesn't edit files.

Show the user the proposals in plain language and apply the ones they accept. If the user asked you to proceed with defaults, apply the ones marked "important". Make sure the "Design notes" section describes the user flows from the user's point of view.

If the subagent tool isn't available, do the review yourself, with the same checklist (${CLAUDE_PLUGIN_ROOT}/agents/prd-reviewer.md).

Step 4 · polish (optional)

Offer one more pass over the flows, looking for friction and confusing steps. Skip it (skipped) if the user declines or asked for defaults.

Finish

Check that:

  • every flow has at least one acceptance criterion;
  • state.flows matches the document;
  • hasFrontend is true or false.

Ask the user to approve the PRD. Then:

  • set review: reviewed and mark the phase done;
  • set currentPhase to design, or to build if hasFrontend is false; in that case also set Design to not_applicable;
  • update the progress page.

Close by suggesting /builder:next.

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.