Skene
Skene is a codebase analysis toolkit for product-led growth. It scan your codebase, detect growth opportunities, and generate actionable implementation plans.
Skene is a codebase analysis toolkit for product-led growth. It scan your codebase, detect growth opportunities, and generate actionable implementation plans.
Quick Start
Install and launch the interactive terminal UI:
curl -fsSL https://raw.githubusercontent.com/SkeneTechnologies/skene/main/tui/install.sh | bash
skene
The wizard walks you through provider selection, authentication, and analysis — no configuration needed upfront.
What It Does
- Tech stack detection -- identifies frameworks, databases, auth, deployment
- Growth feature discovery -- finds existing signup flows, sharing, invites, billing
- Feature registry -- tracks features across analysis runs, links them to growth loops
- Revenue leakage analysis -- spots missing monetization and weak pricing tiers
- Growth plan generation -- produces prioritized growth loops with implementation roadmaps
- Implementation prompts -- builds ready-to-use prompts for Cursor, Claude, or other AI tools
- Telemetry deployment --
buildwritessupabase/migrations/*_skene_triggers.sql;pushsends engine + that SQL to upstream - Loop validation -- verifies that growth loop requirements are implemented
- Interactive chat -- ask questions about your codebase in the terminal
Supports OpenAI, Gemini, Claude, LM Studio, Ollama, and any OpenAI-compatible endpoint. Free local audit available with no API key required.
Installation
Terminal UI (recommended)
The TUI is an interactive wizard that guides you through the entire workflow. No prerequisites — the installer handles everything.
# Install the TUI
curl -fsSL https://raw.githubusercontent.com/SkeneTechnologies/skene/main/tui/install.sh | bash
# Launch it
skene
Python CLI
If you prefer the command line, you can run Skene directly with uvx (no install needed) or install it globally:
# Install uv (if you don't have it)
curl -LsSf https://astral.sh/uv/install.sh | sh
# Run directly (no install needed)
uvx skene
# Or install globally
pip install skene
For CLI usage details, see the documentation.
Monorepo Structure
| Directory | Description | Language | Distribution |
|---|---|---|---|
src/skene/ | CLI + analysis engine | Python | PyPI |
tui/ | Interactive terminal UI wizard | Go | GitHub Releases |
cursor-plugin/ | Cursor IDE plugin | — | — |
skills/ | Skene Skills -- composable backend schemas for Supabase | SQL | npm |
The TUI (tui/) is a Bubble Tea app that provides an interactive wizard experience and orchestrates the Python CLI via uvx. Each package has independent CI/CD pipelines.
Contributing
Contributions are welcome. Please open an issue or submit a pull request.
License
Máy chủ liên quan
Scout Monitoring MCP
nhà tài trợPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
nhà tài trợAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
Code Assistant
A Rust-based CLI tool for code-related tasks, operating as an MCP server.
Authless Remote MCP Server
An authentication-free remote MCP server designed for deployment on Cloudflare Workers.
DevContext
Provides developers with continuous, project-centric context awareness. Requires a TursoDB database.
WinTerm MCP
Provides programmatic access to the Windows terminal, enabling AI models to interact with the command line interface.
agent-lsp
A stateful LSP runtime for AI agents: warm language server sessions with 50+ tools for go-to-definition, find-references, diagnostics, rename, and more across 30+ languages.
Buildkite
Integrate with the Buildkite API to search and manage CI/CD pipelines.
Apple HIG
Provides instant access to Apple's Human Interface Guidelines, with content auto-updated periodically.
Bloomfilter
Let AI agents search, register, and manage domains via API
Kontxt
Indexes local code repositories to provide codebase context to AI clients.
Figma MCP Server
Enables AI assistants to interact with Figma via WebSocket for reading data and design analysis.