# specdrive

> specdrive — connected-mate-specdrive. Use this tool when you need to enforce spec-driven development and ensure AI coding agents adhere to strict guidelines. Specdrive solves the problem of prompts being forgotten and tools falling short by using specs, scenarios, and proof-gated tasks to guide AI coding. It takes in git-based projects and outputs reviewed and validated code through its MCP server and Mac app interface.

Canonical page: https://skillsregistry.net/skills/connected-mate-specdrive  
JSON: https://api.skillsregistry.net/v1/skills/connected-mate-specdrive

## Description

Spec-driven development, enforced. An MCP server + Mac app that forces AI coding agents through specs, scenarios, proof-gated tasks and independent review — because prompts get forgotten, tools can't be.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/Connected-Mate/specdrive)

## 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": "connected-mate-specdrive"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/connected-mate-specdrive` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/connected-mate-specdrive/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