# winnow

> Use this tool when you need to efficiently compress and manage local context for AI agents, solving problems of data redundancy and storage limitations. It takes in text data and outputs compressed content, original text retrieval, and compression statistics. Ideal for use cases where local-first data processing and storage optimization are crucial.

Canonical page: https://skillsregistry.net/skills/jpoindexter-winnow  
JSON: https://api.skillsregistry.net/v1/skills/jpoindexter-winnow

## Description

Enables local-first context compression for AI agents, offering tools to compress text, retrieve original content, and get compression statistics.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/skqnqymowv)
- **Repository:** <https://github.com/jpoindexter/winnow>

## 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": "jpoindexter-winnow"
    }
  }
}
```

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