Skene
About
Skene is a codebase analysis toolkit for product-led growth. It scan your codebase, detect growth opportunities, and generate actionable implementation plans.
Explore
Setup
Install Skene in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/skenetechnologies/skene
Follow the installation instructions in the repository README, then restart your MCP client.
- Analyze a codebase for user journey milestones— ask the assistant to runanalyse-journeyon your repo and return the inferred lifecycle stages with evidence.
- Include database schema evidence— point the assistant at a directory of.sqlfiles via--schema-dirso the analysis also draws on your data model.
- Review milestone confidence and source evidence— have the assistant explain which code paths or tables back each milestone and how confident the detection is.
- Export a journey without specialized stage names— request analysis with--no-specializeto keep the canonical seven-stage lifecycle labels.
Skene reads your codebase and produces auser journeyfor your product: the lifecycle stages a user moves through, the milestones inside each stage, and the code or database evidence that proves each milestone is real.
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.
Skene turns a repository into a singlejourney.yamldescribing your product's user lifecycle, and renders it as an interactive diagram.
- Agentic analysis— two parallel agents read your project: one walks the codebase, one walks your SQL schemas. They each propose candidate milestones, which are then merged and classified into a canonical seven-stage lifecycle.
- Seven-stage user journey— every product maps to the same canonical stages (discovery, onboarding, activation, engagement, retention, expansion, virality) so journeys are comparable across products. Stage names are specialized to your product where useful.
- Evidence-backed milestones— each milestone carries atracked_event, aconfidencescore, and one or moreevidencechips pointing back to the exact code path, database table, or config file that justifies it.
- Journey visualizer— the TUI opens a local web app that lays out the stages as columns, with milestone cards and clickable evidence chips, so you can review the journey alongside the underlying source.
- Code-only, schema-only, or both— run against just a codebase, just a directory of.sqlfiles, or both for richer evidence.
Supports OpenAI, Gemini, Claude, LM Studio, Ollama, and any OpenAI-compatible endpoint.
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
If you prefer the command line, you can run Skene directly withuvx(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 analyse-journey . # Or install globally pip install skene skene analyse-journey .
- --schema-dir <dir>— point at a directory of exported*.sqlfiles to enable the schema agent
- -o <path>— override the output file (default./skene-context/journey.yaml)
- --no-specialize— keep the canonical stage names instead of letting the LLM specialize them
For full CLI usage, see thedocumentation.
Both the Python CLI and the TUI write artifacts to a single bundle directory in your project root, created automatically if missing.
- Default:./skene-context/journey.yaml— the analysed user journey for your product.
- Override:setoutput_dirin.skene.configor pass-o/--outputto write elsewhere.
The TUI (tui/) is a Bubble Tea app that provides an interactive wizard experience and orchestrates the Python CLI viauvx. Each package has independent CI/CD pipelines.
Contributions are welcome. Pleaseopen an issueor submit apull request.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
AI-to-AI code review platform — Claude, Codex, and Gemini cross-check each other via MCP, REST API, and CLI for consensus-based results.
Orchestrates a dual-AI engineering loop where a Primary AI plans and implements, while a Review AI validates and reviews, with continuous feedback for optimal code quality. Supports custom AI pairing (Claude, Codex, Gemini, etc.)
Provides AI assistants with a comprehensive, one-time analysis for complete codebase context and understanding.
Interact with CodeRabbit AI reviews on GitHub pull requests.
FutureAGI EvalOps MCP is a paid remote MCP endpoint for AI SDK eval dashboard. It exposes structured JSON tools, a public server card, token-based access, usage receipts, and audit-ready wor
Automate Google Jules, the AI coding assistant, for tasks like code reviews, repository management, and AI-powered development workflows.
Analyze and visualize code graphs using CodeGPT.
Fourteen hosted MCP servers over Streamable HTTP - code review, agent governance, business-day math, analytics, commerce math and SKILL.md linting - free tier needs no account or credentials.
Code intelligence MCP server - PageRank, blast radius, co-change, hotspots, clone detection across 34 languages in a single Rust binary.
Hybrid decomp tool — AI decides WHERE to split your monolith, deterministic engine COPIES the code. Minimize tokens, maximize syntax validity.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
