# shell-sieve

> shell-sieve — yulinlina-shell-sieve. Use this tool when you need to efficiently process and refine verbose shell output for AI agent context windows. The shell-sieve tool executes shell commands, compresses output, and intelligently filters errors, taking in shell commands as input and producing refined, error-preserved output. It is ideal for use cases where saving context window space is crucial, such as in log analysis or automated system monitoring.

Canonical page: https://skillsregistry.net/skills/yulinlina-shell-sieve  
JSON: https://api.skillsregistry.net/v1/skills/yulinlina-shell-sieve

## Description

An MCP server that executes shell commands and intelligently compresses, filters, and extracts errors from verbose output to save AI agent context windows. It strips ANSI, collapses repetitive lines, and always preserves error information.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/qhu3os73m5)
- **Repository:** <https://github.com/yulinlina/shell-sieve>

## 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": "yulinlina-shell-sieve"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/yulinlina-shell-sieve` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/yulinlina-shell-sieve/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