Back to Skills

product

verified

Create lightweight product brief (PR/FAQ) that articulates customer need, success criteria, and scope before engineering decomposition. Triggers: "product brief", "customer value", "who is this for", "PR/FAQ", "working backwards", "define success", "scope this".

View on GitHub

Marketplace

agentops-marketplace

boshu2/agentops

Plugin

core-kit

development

Repository

boshu2/agentops
6stars

plugins/core-kit/skills/product/SKILL.md

Last Verified

January 24, 2026

Install Skill

Select agents to install to:

Scope:
npx add-skill https://github.com/boshu2/agentops/blob/main/plugins/core-kit/skills/product/SKILL.md -a claude-code --skill product

Installation paths:

Claude
.claude/skills/product/
Powered by add-skill CLI

Instructions

# Product Skill

Create lightweight product briefs that bridge `/research` and `/formulate` with customer-first thinking.

## Overview

Product briefs force articulation of **why** before **how**. Based on Amazon's PR/FAQ
and Google's Design Doc patterns, this skill ensures the customer problem is understood
before decomposing into engineering tasks.

**Output:** `~/gt/.agents/<rig>/products/YYYY-MM-DD-{topic-slug}.md`

**When to Use**:
- Multi-day work (3+ days)
- User-facing impact isn't immediately obvious
- Multiple valid approaches exist
- Unclear "why should this be built?"

**When NOT to Use**:
- Pure technical debt (no user-facing impact)
- Bug fixes with clear scope
- PM already wrote a PRD
- Single-day tasks

---

## Workflow

```
0.  Rig Detection       -> Determine target rig
0.5 Setup               -> mkdir -p ~/gt/.agents/<rig>/products/
1.  Prior Art           -> Check for existing PRDs/product docs
2.  Customer Discovery  -> Who, pain points, workarounds
3.  Solution            -> Headline, problem mapping
4.  Success Criteria    -> Measurable outcomes
5.  Scope               -> In-scope, non-goals
6.  Output              -> Write product brief
7.  Confirm             -> Verify file, next steps
```

---

## Phase 0: Rig Detection

**CRITICAL**: All `.agents/` artifacts go to `~/gt/.agents/<rig>/` based on the primary codebase.

**Detection Logic**:
1. Identify which rig's code is involved (e.g., files in `~/gt/ai-platform/` → `ai-platform`)
2. If work spans multiple rigs, use `_cross-rig`
3. If unknown/unclear, ask user

| Files Being Read | Target Rig | Output Base |
|------------------|------------|-------------|
| `~/gt/athena/**` | `athena` | `~/gt/.agents/athena/` |
| `~/gt/cyclopes/**` | `cyclopes` | `~/gt/.agents/cyclopes/` |
| `~/gt/daedalus/**` | `daedalus` | `~/gt/.agents/daedalus/` |
| Multiple rigs | `_cross-rig` | `~/gt/.agents/_cross-rig/` |

```bash
# Set RIG variable for use in output paths
RIG="athena"  # or cyclopes, daedalus, _cros

Validation Details

Front Matter
Required Fields
Valid Name Format
Valid Description
Has Sections
Allowed Tools
Instruction Length:
8977 chars