product analysis

Engineering Community

Skill notes

Step 0: Auto-Detect Available Tools

Before launching any agents, detect what tools are available: 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. Also detect the project type to tailor agent prompts:

Scope Modes

Parse $ARGUMENTS to determine analysis scope: Scope · What it covers · Typical agents full · UX + API + Architecture + Docs (default) · 5 Claude + Codex (if available) ux · Frontend navigation, information density, user journey, empty state, onboarding · 3 Claude + Codex (if available) api · Backend API coverage, endpoint health, error handling, consistency · 2 Claude + Codex (if available)

Phase 1: Parallel Exploration

Launch all exploration agents simultaneously using Task tool (background mode).

Claude Code Agents (always)

For each dimension, spawn a Task agent with subagent_type: Explore and run_in_background: true: Agent A — Frontend Navigation & Information Density Agent B — User Journey & Empty State Agent C — Backend API & Health Agent D — Architecture & Module Structure (full/arch scope only)

Codex CLI Agents (auto-detected)

If Codex CLI was detected in Step 0, launch parallel Codex analyses via background Bash. Each Codex invocation gets the same dimensional prompt but from a different model's perspective: Run 2-3 Codex commands in parallel (background Bash), one per major dimension. Important: Codex runs in the project's working directory. It has full filesystem access. The --full-auto flag (or --dangerously-bypass-approvals-and-sandbox for older versions) enables autonomous execution.

Fluxly profile Runtime and permissions are inferred by Fluxly static checks, not author declarations or runtime test results.
Domain
Engineering
Author-declared agents
No explicit declaration found; this is not inferred or tested compatibility
Static check
88 / 100 · heuristic scan, not runtime safety proof
Runtime evidence
Not run; no isolated runtime test evidence is currently recorded
Author / version / license
@daymade · no license declared
Token usage
Lean
Setup complexity
Guided setup
External API key
Not required
Operating systems
macOS · Linux · Windows
Runtime requirements
Node.js · Python
Detected file/system behavior
  • Read-only
  • Write / modify
  • Shell exec
  • Env read
Network behavior
Local-only
Install commands
None (reference only)

Heads up: Tool permissions are not declared; actual access depends on the runtime.

Output preview product-analysis.preview
# Structured Output

Produce a layered optimization report: ```markdown

Discussion

Powered by GitHub Discussions. Sign in with GitHub to comment, react, or subscribe.