# leanscreen

> leanscreen — ibrahimmian36-leanscreen. Use this tool when you need to calibrate and refine informal statements into formal Lean 4 statements, leveraging deterministic checks and deep LLM-based analysis to ensure accuracy and faithfulness. It solves problems of inconsistent or ambiguous statement pairs, providing a reliable interface for inputting informal statements and outputting calibrated Lean 4 equivalents. Ideal for use in formal proof development and verification contexts.

Canonical page: https://skillsregistry.net/skills/ibrahimmian36-leanscreen  
JSON: https://api.skillsregistry.net/v1/skills/ibrahimmian36-leanscreen

## Description

A calibrated faithfulness screen for informal↔Lean 4 statement pairs, served over MCP. It provides deterministic checks and deep LLM-based analysis to help draft Lean statements.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **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/xprpe21ycy)
- **Repository:** <https://github.com/ibrahimmian36/leanscreen>

## 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": "ibrahimmian36-leanscreen"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/ibrahimmian36-leanscreen` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/ibrahimmian36-leanscreen/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