agentleFS
RorroRojas3RorroRojas3/maf-agents/.claude/skills/prd/SKILL.md

prd

Skill0 starsChanged 2 months agoMITView on GitHub

Write Product Requirements Documents and break features into epics and user stories with acceptance criteria, priorities, estimates, and dependencies. Use when asked to write a PRD, spec out or scope a feature, define requirements, build a backlog, break a feature into stories, or turn requirements into GitHub issues.

130 other projects use a version of this, 8 of them edited.

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

  • 0

    Common

    Most of the 107 edited versions we read keep these.

  • 2

    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. Very specific:

    Follow the canonical schema in references/prd-template.md — do not invent a different outline.

    line 45
  2. Distinctive:

    Use concrete, measurable criteria.

    line 49
  3. Very specific:

    No fabricated constraints: If the user didn't specify a stack, deadline, or metric target, ask, or mark it TBD and record it under …

    line 62
  4. Very specific:

    Traceability: Every functional requirement maps to at least one story.

    line 64
  5. Very specific:

    Write the PRD to docs/prd/<feature-slug>.md (create the folder if needed) unless the user specifies another location.

    line 68
  6. Distinctive:

    Read only what the task calls for:

    line 72

“Common” is measured: kept by at least 6 in 10 of the 107 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

Product Requirements Document (PRD)

Overview

Produce production-grade PRDs that bridge business vision and technical execution: a clear problem statement, measurable success criteria, and a feature broken down into epics and user stories a team can actually pick up.

When to use

  • Starting a new product or feature development cycle
  • Translating a vague idea into a concrete, testable specification
  • Breaking a feature into epics and user stories with acceptance criteria
  • Building a backlog or creating GitHub issues from requirements
  • Stakeholders need a unified "source of truth" for project scope

Not for implementation plans. A PRD says what to build and why. How to build it — file-level steps, architecture choices, task sequencing — belongs to the planning flow (plan mode, Planner Expert), which should reference the PRD's story IDs.

Workflow

1. Discover

Identify what you don't know before writing anything. The seven gaps that matter:

  1. Problem & why now — what pain, and what makes it urgent?
  2. Users — who is this for; which roles or personas?
  3. Scope boundary — what is explicitly in and out?
  4. Success metrics — how will anyone know it worked?
  5. Constraints — stack, budget, deadline, compliance?
  6. Auth model — are there protected resources; who can do what?
  7. Existing code touchpoints — what does this integrate with or replace?

Close the gaps per your operating mode: an interactive session asks the user directly (3–5 questions, bulleted, conversational); an autonomous agent returns the questions to its caller or proceeds and records each guess in the PRD's Assumptions & open questions section. Never silently invent an answer.

2. Analyze

Ground the PRD in the real codebase before drafting. Find the current architecture, similar existing features, the auth mechanism, and telemetry conventions — the Technical considerations and Epics & user stories sections must name real integration points, not hypothetical ones.

3. Draft

Follow the canonical schema in references/prd-template.md — do not invent a different outline. Decompose the feature using the rules in references/story-breakdown.md. Iterate: present the draft and ask for feedback on specific sections.

Quality bar

Use concrete, measurable criteria. Avoid "fast", "easy", or "intuitive".

# Vague (BAD)
- The search should be fast and return relevant results.
- The UI must look modern and be easy to use.

# Concrete (GOOD)
+ The search must return results within 200ms for a 10k record dataset.
+ The search algorithm must achieve >= 85% Precision@10 in benchmark evals.
+ The UI must achieve a 100% Lighthouse Accessibility score.
  • No fabricated constraints. If the user didn't specify a stack, deadline, or metric target, ask, or mark it TBD and record it under Assumptions & open questions.
  • Every story is testable. Each acceptance criterion is observable behavior someone could verify.
  • Traceability. Every functional requirement maps to at least one story; IDs (FR-n, EP-n, US-xxx) are stable so plans, commits, and issues can reference them.

Output

Write the PRD to docs/prd/<feature-slug>.md (create the folder if needed) unless the user specifies another location.

References

Read only what the task calls for:

ReferenceRead when
references/prd-template.mdStructuring or drafting the document — the canonical schema and final checklist
references/story-breakdown.mdDecomposing a feature into epics and user stories: slicing, INVEST, acceptance criteria, priorities, estimates, dependencies
references/github-issues.mdOnly after the user has explicitly confirmed creating GitHub issues from the PRD

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.