Product Analysis

Runs a multi-agent product audit by spawning parallel Claude Code tasks and optionally Codex CLI processes to analyze your codebase from different angles. It auto-detects what tools you have installed and scales accordingly, no setup prompts. You get quantified findings like "47 interactive elements on first screen" and "3 features with duplicate entry points" across UX, API, architecture, and docs. The synthesis phase cross-validates where agents agree or disagree, which is useful for catching blind spots. Supports scoped analysis (just UX, just API) and can invoke competitors-analysis for side-by-side comparison. Best for pre-launch audits or when you need hard numbers about complexity creep.

skills.sh installs: 909
GitHub stars: 1.5K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add daymade/claude-code-skills --skill product-analysis --agent claude-code

Installs into .claude/skills of the current project.

Files

Product Analysis

Multi-path parallel product analysis that combines Claude Code agent teams and Codex CLI for cross-model test-time compute scaling.

Core principle: Same analysis task, multiple AI perspectives, deep synthesis.

How It Works

/product-analysis full
         │
         ├─ Step 0: Auto-detect available tools (codex? competitors?)
         │
    ┌────┼──────────────┐
    │    │              │
 Claude Code         Codex CLI (auto-detected)
 Task Agents         (background Bash)
 (Explore ×3-5)      (×2-3 parallel)
    │                   │
    └────────┬──────────┘
             │
      Synthesis (main context)
             │
      Structured Report

Step 0: Auto-Detect Available Tools

Before launching any agents, detect what tools are available:

# Check if Codex CLI is installed
which codex 2>/dev/null && codex --version

Decision logic:

If codex is found: Inform the user — "Codex CLI detected (version X). Will run cross-model analysis for richer perspectives."
If codex is not found: Silently proceed with Claude Code agents only. Do NOT ask the user to install anything.

SKILL.md on GitHub