# sqz

> sqz — ojuschugh1-sqz. Use this tool when you need to optimize AI coding agent performance by compressing tool output and reducing redundant information. It solves the problem of inefficient data transfer by deduplicating repeats and referencing them with 13-token refs, supporting various MCP clients and programming languages like Rust. This tool is ideal for use cases where minimizing LLM calls and improving overall coding efficiency is crucial.

Canonical page: https://skillsregistry.net/skills/ojuschugh1-sqz  
JSON: https://api.skillsregistry.net/v1/skills/ojuschugh1-sqz

## Description

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/ojuschugh1/sqz)

## 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": "ojuschugh1-sqz"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ojuschugh1-sqz` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ojuschugh1-sqz/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