prd
SkillWeb & browsingGenerate Product Requirements Document from feature intent/description
Use prd in Claude, ChatGPT or Ahel Desktop
Free. Sign in, add prd and connect your AI. About a minute.
Also: Claude Code · Cursor · Codex
Then ask your AI: use the prd skill
Details
Instructions available. Your AI can read the instructions. Execution depends on the setup they require.
Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.
No other account needed.
Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.
What this skill tells your AI
The instructions your AI receives, as published by porcupine-md/anoa-browser in .claude/skills/core/prd/SKILL.md and read by Ahel’s review.
Context
You are a product analyst creating a PRD for project {{project_name}} ({{project_type}}). Stack used: {{stack}}.
This PRD will be used as input for the Jonggrang development workflow, where each user story will become one atomic task handled by an AI agent in a single iteration.
Instructions
-
Analyze the given feature intent/description: "{{input.feature}}"
-
Create a PRD with the following structure:
- Overview: Feature summary in 2-3 sentences
- Problem Statement: What problem this solves
- User Stories: List of user stories in the format "As a [role], I want [action], so that [benefit]"
- Acceptance Criteria: Per user story, what must be true for it to be considered complete
- Technical Notes: Technical considerations, dependencies, constraints
- Out of Scope: What is NOT included in this feature
-
Ensure each user story:
- Is small enough to be completed in 1 context window (~30 minutes of agent work)
- Has testable acceptance criteria
- Does not overlap file ownership with other stories (if possible)
- Has a clear priority (1 = highest)
-
Save the PRD to
tasks/prd-{{input.feature | slugify}}.md -
Ask the user whether the PRD is acceptable or needs revision
-
After approval, convert to
.jonggrang/jonggrang-tasks.jsonformat:
Script
#!/bin/bash
# Create tasks directory if not exists
mkdir -p tasks
Validation
- PRD file saved in
tasks/prd-*.md - Each user story has acceptance criteria
- Each story is sufficiently atomic (completable in 1 iteration)
- Priorities assigned to all stories
- .jonggrang/jonggrang-tasks.json updated with new tasks
Examples
Input
feature: "User authentication with email and social login"
Output PRD (excerpt)
# PRD: User Authentication
## Overview
Implement user authentication system supporting email/password
and social login (Google, GitHub) with session management.
## User Stories
### Story 1: Email Registration (Priority: 1)
As a new user, I want to register with my email and password,
so that I can create an account.
Acceptance Criteria:
- POST /api/auth/register accepts email + password
- Email validated (format + uniqueness)
- Password hashed with bcrypt (min 8 chars)
- Returns JWT token on success
- Returns 422 on validation error
- Tests: happy path, duplicate email, weak password
Files: src/routes/auth.ts, src/services/auth.ts, tests/auth.test.ts
Signals
- GitHub stars
- 28
- Forks
- 3
- Last commit
- Oct 2026
Advanced
- Item type
- skill
- Key
prd-porcupine-md- Source
- github.com/porcupine-md/anoa-browser
github.com/porcupine-md/anoa-browser
More in Web & browsing
Skill · browser-use
More in Web & browsingwebapp-testing
Skill · anthropics
More in Web & browsingplaywright-cli
Skill · microsoft
More in Web & browsingbenchmark
Skill · affaan-m
More in Web & browsingopen-source
Skill · browser-use
More in Web & browsingdeploy-to-vercel
Skill · vercel-labs
More in Web & browsing