agentleFS
Sign inStart free
grezxunegrezxune/ai-tools/skills/prd/SKILL.md

prd

Skill0 starsChanged 18 days agoMITView on GitHub

PRD format and rules. Use before writing or changing a PRD, or building a feature, in a repo with no `prds/README.md`.

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:

    Write a PRD before building a new feature or changing user-facing behavior.

    line 12
  2. Very specific:

    Keep one PRD per feature at prds/{feature}.md.

    line 14
  3. Distinctive:

    Write requirements as behavior the user sees.

    line 64
  4. Distinctive:

    When the feature touches auth, payments, or personal data, list each risk under Constraints with how you will verify it.

    line 67

“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

PRDs

A PRD records what to build and why, in terms you can build and verify against. How it gets built lives in the code and in the PRD's Decisions section.

When one is needed

Write a PRD before building a new feature or changing user-facing behavior. Bug fixes, refactors, and small tweaks go straight to code. Before building a feature, find its PRD in prds/ and build against it.

Keep one PRD per feature at prds/{feature}.md. When scope or a decision changes mid-build, update the PRD in the same change as the code.

Status

  • draft: open questions remain. Resolve the ones a requirement depends on with me before building that requirement.
  • approved: requirements are settled. Build against them.
  • shipped: every P0 requirement is live. Further changes go in a new PRD.

Template

---
title: Feature name
status: draft
---

## Problem
Who has the problem, what it costs them today, and why it matters now. Two to five sentences.

## Goals
Measurable outcomes with targets, e.g. "80% of new users finish setup in under 2 minutes."

## Non-goals
What this work leaves out on purpose, with the reason for each.

## Users and flows
Who uses it, and the main flow as numbered steps.

## Requirements

### R1 (P0): One sentence describing behavior the user sees
- Given ..., when ..., then ...

### R2 (P1): ...
- Given ..., when ..., then ...

## Constraints
Only what applies to this feature: performance budgets, security and privacy, integrations, migrations or rollout steps, deadlines.

## Open questions
- Blocks R2: the question.

## Decisions
- YYYY-MM-DD: The decision, and the reason.

Priorities: P0 ships in the first release. P1 should ship but can slip. P2 is later.

Writing rules

  • Write requirements as behavior the user sees. "Search returns results in under 300 ms" is a requirement. "Add an index on title" is an implementation choice and goes in Decisions if it matters.
  • Give every requirement acceptance criteria that a person can check in the app or a test can assert.
  • Problem, Non-goals, and Requirements are always present. Leave out any other section that would only say TBD or N/A.
  • When the feature touches auth, payments, or personal data, list each risk under Constraints with how you will verify it.

Building against a PRD

The P0 acceptance criteria are the definition of done. Before calling the feature finished, check every one and report any that fail. Reference requirement IDs (R1, R2) in commit messages and PR descriptions.

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