# SpecLeft

> Use this tool when you need to map specifications to pytest tests and monitor implementation progress in an offline environment. SpecLeft solves the problem of tracing intent and tracking development progress by providing a Python-based intent tracing MCP. It takes in specs and test implementations as inputs and outputs a mapped relationship between the two, ideal for use cases where offline testing and validation are required.

Canonical page: https://skillsregistry.net/skills/io-github-specleft-specleft  
JSON: https://api.skillsregistry.net/v1/skills/io-github-specleft-specleft

## Description

Python intent tracing MCP: map specs to pytest tests, monitor implementation progress, offline-only.

## Trust

- **Trust score (0–1):** 0.85
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 0.3.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** monitoring
- **Updated:** 2026-09-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.SpecLeft%2Fspecleft)
- **Repository:** <https://github.com/SpecLeft/specleft>

## 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": "io-github-specleft-specleft"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-specleft-specleft` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-specleft-specleft/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