# pickysteve

> pickysteve — kernellord-pickysteve. Use this tool when you need to automatically route skills and pick context for Claude Code, Cursor, and Aider, solving the problem of manual skill selection and filtering for MCP prompts. It takes in prompts and outputs the most suitable skill, streamlining the development process. Ideal for use in git-based projects requiring efficient skill routing and context management.

Canonical page: https://skillsregistry.net/skills/kernellord-pickysteve  
JSON: https://api.skillsregistry.net/v1/skills/kernellord-pickysteve

## Description

Skill router and context picker for Claude Code, Cursor, and Aider. Auto-picks the right skill for every prompt, with prompt-injection filtering for MCP.

## Trust

- **Trust score (0–1):** 0.59
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/KernelLord/pickysteve)

## 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": "kernellord-pickysteve"
    }
  }
}
```

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