πŸ“
WritingJavaScript

PRD

by Joonghyun-Lee-Frieren

PRD is a Writing skill for Claude Code, published by Joonghyun-Lee-Frieren in oh-my-antigravity.

210 stars27 forkson Joonghyun-Lee-Frieren/oh-my-antigravityAdded 2026/09/04Repository updated 2026/06/22
agent-skillsagentic-aiagentic-workflowantigravityantigravity-cliantigravity-ideantigravity-plugingeminigemini-cligemini-cli-extensionsgeminiclimulti-agentoh-my-antigravityoh-my-gemini-clipluginsskills
Install in seconds
Install PRD
Copy PRD into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/Joonghyun-Lee-Frieren/oh-my-antigravity/tree/main/skills/prd ~/.claude/skills/prd

Requires Node.js. Downloads this skill only β€” not the rest of the repository β€” into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Joonghyun-Lee-Frieren/oh-my-antigravity.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/prd/SKILL.md in Joonghyun-Lee-Frieren/oh-my-antigravity
Installs to
~/.claude/skills/prd
Collection
One of 11 skills cataloged from this repository
Category
Writing β€” 1361 skills

What PRD does

PRD locks scope before implementation by defining the problem, in-scope work, non-goals, constraints, and acceptance criteria. Use it when requirements are vague or scope creep is a risk.

PRD is cataloged under Writing on DirSkills. PRD comes from a repository tagged agent-skills, agentic-ai, agentic-workflow, antigravity and antigravity-cli.

Documentation

README

Purpose

Use this skill to lock scope before implementation starts.

Trigger

  • Requirements are ambiguous or too broad
  • Team needs measurable done criteria
  • Scope creep risk is high

Workflow

  1. Write a concise problem statement.
  2. Define in-scope and explicit non-goals.
  3. Define acceptance criteria with evidence requirements.
  4. Capture constraints and dependencies.
  5. Produce handoff notes for execution and verification.

Output Template

## Problem Statement
- ...

## Scope / Non-goals
- ...

## Acceptance Criteria
| Criterion | Evidence Needed | Owner |
| --- | --- | --- |

## Constraints
- ...

## Handoff
- ...

Frequently asked about PRD

  • What else does Joonghyun-Lee-Frieren publish alongside PRD?

    PRD is one of 11 skills that DirSkills catalogs from Joonghyun-Lee-Frieren/oh-my-antigravity, the repository it ships in. Its siblings there include Blueprint, Context Optimize and Deep Dive. Each one is a separate skill with its own page in this directory, installs the same way PRD does, and is maintained by Joonghyun-Lee-Frieren in that same repository. The rest of the collection is listed on the Joonghyun-Lee-Frieren/oh-my-antigravity page.

  • How does PRD compare to other Writing skills?

    PRD ranks #961 by stars among the 1361 Writing skills in this catalog. The most-starred ones next to it are Article Writing, Social Media Content Calendar and Knowledge Comic Creator. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of PRD against them. Open each page to compare what they document and how they install.

More from Joonghyun-Lee-Frieren/oh-my-antigravity

PRD is one of 11 skills cataloged on DirSkills from Joonghyun-Lee-Frieren/oh-my-antigravity.

See all 11 skills β†’
🧩
2026/09/04

Blueprint

Blueprint helps define stable product, UI, and workflow decisions before implementation. Use it to map users, flows, states, content hierarchy, accessibility, and open questions for frontend changes.
Frontend
21027
🧠
2026/09/04

Context Optimize

Context Optimize helps when a conversation gets long, repetitive, or unstable. It identifies stale context and suggests compaction and session rules to keep turns coherent.
AI Engineering
21027
πŸ•΅οΈ
2026/09/04

Deep Dive

Deep Dive helps when requirements are incomplete or conflicting by running a structured interview, recording assumptions, and producing a launch brief. Use it before planning or implementation when scope or acceptance criteria are unclear.
AI Engineering
21027
πŸ› οΈ
2026/09/04

Execute

Execute is used when a task is implementation-ready and needs code changes now. It guides the agent to confirm scope, edit the smallest necessary files, run checks, and report validation and follow-ups.
Automation
21027
🧠
2026/09/04

Learn

Learn automatically evaluates OmA sessions to extract reusable patterns like error fixes, workarounds, and conventions, then saves them as rules. Use it after sessions or when configuring the SessionEnd hook and learned rules.
AI Engineering
21027
πŸ—ΊοΈ
2026/09/04

Oma Plan

Oma Plan helps break non-trivial code changes into phases, tasks, dependencies, and validation steps before editing. Use it when a request needs strategy, sequencing, or a rollback-aware plan.
Automation
21027