# Skim

> Use this tool when you need to compress code for large language models (LLMs) while preserving its structural meaning, to reduce context window sizes and improve processing efficiency. Skim supports multiple programming languages and file formats, including TypeScript, JavaScript, and Python, and offers various compression modes to achieve 60-95% content reduction. It is ideal for use cases where code needs to be transformed for LLM compatibility, such as code summarization, analysis, or generation tasks.

Canonical page: https://skillsregistry.net/skills/luw2007-skim  
JSON: https://api.skillsregistry.net/v1/skills/luw2007-skim

## Description

Code transformation server that intelligently compresses code for LLM context windows while preserving structural meaning. Supports multiple compression modes (structure, signatures, types) achieving 60-95% content reduction. Compatible with TypeScript, JavaScript, Python, Rust, Go, Java, JSON, Markdown, and YAML.

## Trust

- **Trust score (0–1):** 0.87
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/luw2007-skim)
- **Repository:** <https://github.com/luw2007/skim-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "luw2007-skim"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/luw2007-skim` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/luw2007-skim/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt