Skene
CLI docs

skene CLI documentation

Analyze codebases for product-led growth opportunities, generate growth plans, and build implementation prompts.

Navigation

skene

A CLI toolkit for analyzing codebases through the lens of Product-Led Growth (PLG) — detecting growth features, revenue leakage, and generating actionable growth plans.

What skene does

  • Analyzes your codebase to detect tech stack, growth features, and revenue leakage patterns
  • Generates a growth manifest — structured JSON output documenting your product's growth surface area
  • Maintains a feature registry — persistent tracking of growth features across analysis runs with merge-update semantics
  • Creates growth plans — a Council of Growth Engineers produces 3-5 high-impact growth loops
  • Builds implementation prompts that you can send directly to Cursor, Claude, or display in your terminal
  • Pushes growth loops upstream — generates Supabase telemetry migrations and deploys to Skene Cloud
  • Validates growth loop implementation — AST-based checks verify that required files and functions are present in your codebase
  • Provides an MCP server exposing 12 tools for AI assistants
  • Supports multiple LLM providers: OpenAI, Gemini, Anthropic, LM Studio, Ollama, and any OpenAI-compatible endpoint

Core workflow

# 1. Create a config file
uvx skene config --init

# 2. Set up your LLM provider and API key interactively
uvx skene config

# 3. Analyze your codebase
uvx skene analyze .

# 4. Generate a growth plan
uvx skene plan

# 5. Build an implementation prompt
uvx skene build

# 6. Login to Skene Cloud
uvx skene login

# 7. Push growth loops to Supabase + upstream
uvx skene push

Key concepts

Growth manifest (growth-manifest.json) — The primary output of the analyze command. A structured JSON file containing your project's tech stack, existing growth features, growth opportunities, and revenue leakage issues.

Growth template (growth-template.json) — A custom PLG template generated alongside the manifest, with lifecycle stages and metrics tailored to your business type.

Growth plan (growth-plan.md) — A markdown document produced by the plan command for your next growth action. Contains 3-5 selected high-impact growth loops with implementation roadmaps, metrics, and week-by-week timelines.

Growth loops — Individual loop definitions (JSON) generated by the build command. Each loop includes file/function requirements, integration points, telemetry specs, verification commands, and success metrics.

Feature registry (feature-registry.json) — A persistent registry of growth features that tracks features across analysis runs. Features are marked active or archived, linked to growth loops, and annotated with growth pillars (onboarding, engagement, retention).

Skene API key — A single key from Skene Cloud that manages all tokens required to use LLM models (plan, build, chat) and authorizes pushing growth loops upstream. One key replaces per-provider API keys for LLM usage and enables cloud push. Get your key at https://www.skene.ai/workspace/apikeys

Documentation

Getting started

Guides

Create

  • Analyze — The analyze command in depth
  • Plan — Generating growth plans
  • Build — Building implementation prompts
  • Push — Pushing growth loops to Supabase and upstream

Manage

  • Login — Authenticating with Skene Cloud upstream
  • Status — Checking growth loop implementation status
  • Features — Managing and exporting the feature registry
  • LLM providers — Configuring OpenAI, Gemini, Claude, local LLMs
  • Configuration — Config files, env vars, and priority

Experimental

  • Chat — Interactive terminal chat

Integrations

Reference

Help