Ships with octo. Installing the plugin gets this command.
⚡ How it fires
How this command gets triggered: by you, by Claude, or both.
Fires itselfClaude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/prd-score
👁️ Context preview
What this command does when you run it.
Path to the PRD file to score (relative or absolute)
📊 Stats
Stars3,869
Forks362
LanguageShell
LicenseMIT
📦 Ships with octo
</> Command definition
prd-score.md
---command: prd-score
description: Score an existing PRD against the 100-point AI-optimization framework
arguments:
- name: file
description: Path to the PRD file to score (relative or absolute)
required: true
---## STOP - DO NOT INVOKE /skill OR Skill() AGAIN
This command is already executing. The PRD file to score is: **$ARGUMENTS.file**
## Instructions
Score the PRD against the 100-point AI-optimization framework.
### Step 1: Load the PRD
Read the file at `$ARGUMENTS.file` using the Read tool.
### Step 2: Evaluate Against Framework
Score each category:
#### Category A: AI-Specific Optimization (25 points)
- Sequential Phases: 0-10 pts (phases ordered by dependencies, each 5-15 min work)
- Explicit Non-Goals: 0-8 pts (dedicated Non-Goals section with explicit boundaries)
- Structured Format: 0-7 pts (FR codes, consistent headings, Given-When-Then criteria)
#### Category B: Traditional PRD Core (25 points)
- Problem Statement: 0-7 pts (quantified pain points, metrics)
- Goals & Metrics: 0-8 pts (SMART goals, P0/P1 priorities)
- User Personas: 0-5 pts (named personas with scenarios)
🟡 Gemini CLI — Completeness and industry standards bias (catches missing sections)
🧭 Antigravity CLI — Alternate model perspective when installed
🔵 Claude — AI-optimization and structure bias (catches poor phasing)
**Rigorous workflow:**
1. Dispatch the PRD to 2-3 available providers, each scoring independently using the same 100-point framework
2. Collect individual scores and category breakdowns
3. Synthesize consensus: highlight where providers agree (high confidence) and where they diverge (areas to investigate)
4. Present combined score with per-provider variance
**Why this works:** Different models flag different weaknesses. Codex catches implementation gaps, Gemini catches industry-standard omissions, Antigravity adds another external-model challenge when installed, and consensus scoring reduces single-model bias.
### Step 5: Offer Improvements
After scoring, offer:
1. Revise the PRD - Apply top recommendations
2. Add missing sections - Generate specific missing content
3. Reformat for AI - Convert to AI-optimized structure
4. Export score - Save report to a file
**BEGIN NOW - read and score the PRD at: $ARGUMENTS.file**
