npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

skill-any-code

v1.0.2

Published

Skill Any Code: CLI tool for large codebase understanding and analysis

Readme

🚢 Skill-Any-Code

Turn any codebase into a navigable skill. 🚢

Understand large codebases without dumping the entire repository into an LLM context window.

skill-any-code is a CLI for engineers who need to understand unfamiliar repositories fast. It analyzes a project, generates structured Markdown summaries, and exposes the result as a project-local skill so humans and coding agents can progressively reveal only the code they actually need.

Why 🎯

Large codebases are hard to understand because raw source code does not come with a map.

Search helps you jump around. LLMs help you explain what you are looking at. But neither solves the real problem: most of the time, you do not need more code. You need the right entry point.

skill-any-code treats codebase indexing as a first-class artifact. Instead of throwing an entire repository at an LLM, it builds a navigable understanding layer on top of the repo and lets you drill down step by step.

Quick Start 🚀

# Install the CLI:
npm i -g skill-any-code

# Initialize the config file:
skill-any-code init

Set your LLM configuration in ~/.config/skill-any-code/config.yaml:

llm:
  base_url: "YOUR_LLM_BASE_URL"
  api_key: "YOUR_LLM_API_KEY"
  model: "YOUR_MODEL_NAME"

Analyze a project:

cd /path/to/your/project
sac

How It Works ⚙️

  1. Analyze — Walk the repo and summarize files + directories into structured Markdown.
  2. Store — Drop results into a predictable, project-local output tree.
  3. Skill — Generate a skill that maps source paths → summaries so agents navigate with progressive disclosure.

Why It's Different ✨

  • 🧩 Not “just summaries” — It turns repository understanding into a reusable navigation layer.
  • 🎯 Context, not noise — It is designed to expose only the context that matters.
  • 🤖 Skill-native — After analysis, tools like Cursor, Claude Code, Codex, and OpenCode can follow the generated skill instead of reading the entire repository blindly.
  • 📂 Structure-first — You start at the root, move into a relevant directory, then drill into the exact file you need.

What You Get 📦

  • 📁 .skill-any-code-result/ — Local analysis tree mirroring your project layout
  • 📝 Markdown — Per-directory and per-file summaries
  • 🔗 Deployed skill — Under project-local skill dirs for supported agent tools, mapping source locations to the right analysis file