Internal methodology for the PRD discovery stage. Produces a concise Product Reference Document for implementation planning.
Scanned 5/28/2026
Install to Claude Code
npx -y skills add GobbyAI/gobby --skill prd --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Prd?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/gobbyai-prd)More formats (shields.io, HTML) on the badges page.
---
name: prd
description: Internal methodology for the PRD discovery stage. Produces a concise Product Reference Document for implementation planning.
version: "1.0.0"
category: methodology
internal: true
triggers: prd, product requirements, acceptance criteria
metadata:
gobby:
audience: agent
depth: 0
---
# prd - Product Reference Document Methodology
Use this skill when acting as the `product-manager` discovery-stage agent.
## Purpose
Turn upstream discovery into product-readable requirements for planning. The
PRD should define goal, users, scope, explicit non-scope, acceptance criteria,
and the planning handoff.
## Method
1. Read the task and all prior discovery marker blocks.
2. Treat upstream discovery as authoritative unless the task description
contradicts it; record contradictions as open planning handoff notes.
3. Define users and workflows concretely enough for implementation planning.
4. Keep scope sharp. Move cleanup or speculative enhancements out of scope.
5. Write acceptance criteria that can become plan deliverables.
## Output
Write only this section shape:
```markdown
## Product Reference Document
### Goal
- <outcome>
### Users
- <user or system actor>
### Scope
- <included behavior>
### Out of Scope
- <excluded behavior>
### Acceptance Criteria
- <observable acceptance criterion>
### Planning Handoff
- <constraint, dependency, or note for planner>
```
Do not write an implementation plan or task manifest. Preserve uncertainty
explicitly instead of silently broadening scope.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.