mcp-server

repowise: Boost Code Health & Docs with AI‑Powered Insights

Get instant code health scores, auto‑generated documentation, dead‑code alerts, and git analytics—all in Python. Ideal for founders who need clear, AI‑enhanced code intelligence. 7.2k+ GitHub stars.

From the repo · “Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.”

7,901 stars+70★ this week946 forksPythonGuide quality 9/10 · reviewed Oct 9Updated 10/25/2026100% free · open source
What it does

Repowise provides codebase intelligence for AI and humans by analyzing code health, generating documentation, and detecting dead code, among other features.

When to use it
  • •When you need to assess the overall health of your codebase
  • •When you want to automate documentation generation for your project
  • •When you're trying to identify and remove dead code to improve maintainability
Ready-to-paste prompt
Run `repowise analyze --code-health` to get a detailed report on your code's health
Heads up: Make sure you have Python 3.8 or higher installed, as repowise is not compatible with lower versions
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

⚡ Runs out of the box

A prompt/skill package — nothing to install beyond adding it to your AI tool.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/repowise && curl -fsSL https://workflowstacks.com/api/skills/repowise/claude-skill -o ~/.claude/skills/repowise/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How repowise: Boost Code Health & Docs with AI‑Powered Insights works
Codeflow
Free to inspect

Repowise: Boost Code Health & Docs with AI‑Powered Insights is a very large Python project (~517k lines across 2363 code files, plus 1680 test files). You install it into your AI tool with one command; there is nothing to run yourself. Last commit this month, AGPL-3.0 license, has a test suite.

Size
Very large codebase
~517k lines · 2363 code files · days to read — use, don't read
Setup
Install as a skill / plugin
Add it to Claude Code (or your AI tool) with one command — 12 skills inside. Nothing to run yourself.
Runs on
Inside your AI tool
Helper scripts use Python · Node.js · Docker · needs API keys
Python 79%TypeScript 20%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    .env.example
    The API keys and settings you must provide
  3. 3
    examples/README.md
    A worked example — copy this to get going
What's in each folder
packages/Sub-packages / plugins2785 files
plugins/Sub-packages / plugins64 files
docs/Documentation51 files
examples/Examples you can copy13 files
scripts/Helper scripts53 files
website/Project website16 files
docker/Deployment / infrastructure5 files
.claude-plugin/Plugin manifest — what gets installed1 files
READMEHas testsDocumentedCI checksDocker readyExamples includedAGPL-3.0 licenseUpdated this month
Quick Actions
Details
Creator
repowise-dev
Language
Python
Category
mcp-server
Published
3/23/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/repowise.svg)](https://workflowstacks.com/skills/repowise?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.