agentleFS
Sign inStart free
mojopolymojopoly/three-loops/skills/prd/SKILL.md

prd

Skill0 starsChanged 3 months agoMITView on GitHub

Build a plain-language PRD with checkable acceptance criteria — the product-manager entry point to the Intent loop. Use when the operator thinks in features and users rather than code, or when a request needs product framing before technical planning.

125 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

4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 102 edited versions we read keep these.

  • 2

    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. Very specific:

    Start from whatever exists — discovery notes, a support thread, a sketch, a finished /spike, or nothing at all.

    line 17
  2. Distinctive:

    Ask in small batches. For every open decision, present numbered options with a recommendation and its reason — the operator should be …

    line 24
  3. Distinctive:

    No implementation details: If a database, framework, or API name appears, move it out — that's the technical plan's job.

    line 71
  4. Very specific:

    After the PRD is agreed, generate the technical plan (or hand to /spec), then echo the plan back in plain language: what gets built, what …

    line 73

“Common” is measured: kept by at least 6 in 10 of the 102 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

PRD

The PM-flavored sibling of /spec. A PRD stays entirely in the what and why — behavior, users, outcomes — and never touches the how. The agent proposes the technical plan afterward and explains it back in plain language. The PRD's power move is acceptance criteria written in a checkable grammar that requires zero code knowledge but compiles directly into tests and live-verification steps.

Input-first

Start from whatever exists — discovery notes, a support thread, a sketch, a finished /spike, or nothing at all. Use what's brought; ask only what's missing. Arriving empty-handed is fine: the questions below build the PRD from scratch.

Interview style

Ask in small batches. For every open decision, present numbered options with a recommendation and its reason — the operator should be choosing, not authoring:

How should a post that misses its scheduled window behave?
  1. Publish anyway, however late (risk: 4am posts nobody wanted)
  2. Fail visibly with a retry button (recommended — lateness is a promise
     broken; the user decides whether it still makes sense)
  3. Silently drop it (risk: invisible loss of work)

Structure

# <feature> — PRD
YYYY-MM-DD · status: draft | agreed | building | shipped

## Problem
Who hurts, how, and what changes for them if this ships. One paragraph.

## Users & stories
As a <user>, I want <capability>, so that <outcome>. Keep to the 2–5 that
matter.

## Acceptance criteria
The contract. Plain-language, checkable, one behavior per line:
- WHEN <trigger>, the system SHALL <observable response>.
- WHILE <state>, the system SHALL <observable behavior>.
- IF <failure/edge>, THEN the system SHALL <observable response>.
Every line must be verifiable by USING the product — no criterion should
require reading code to check. Failure and edge criteria (the IF lines) are
mandatory: happy-path-only criteria are half a contract.

## Non-goals
What this explicitly does not do. The scope-creep firewall.

## Launch checklist
How we'll know it worked in production: the metric, the log line, the
support question that should stop arriving.

## Open questions
Each with an owner and a default-if-unanswered.

Rules

  • No implementation details. If a database, framework, or API name appears, move it out — that's the technical plan's job.
  • After the PRD is agreed, generate the technical plan (or hand to /spec), then echo the plan back in plain language: what gets built, what it reuses, what it costs in complexity — and get a nod before /decompose.
  • Acceptance criteria become the checkpoint list for /build-supervised and the drive list for /verify-live, and reviewers review against them.
  • Save to docs/specs/YYYY-MM-DD-<name>-prd.md. New user-facing terms go to CONTEXT.md immediately.

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