# draft-protocol

> draft-protocol — manifold-vectors-draft-protocol. Use this tool when you need to ensure AI tools understand human intent before execution, providing intake governance for AI tool calls. It solves problems of misinterpretation and misexecution by verifying alignment with human goals, making it ideal for critical or high-stakes AI applications. The draft-protocol takes in human intent and AI tool calls as input, producing verified and validated execution plans as output.

Canonical page: https://skillsregistry.net/skills/manifold-vectors-draft-protocol  
JSON: https://api.skillsregistry.net/v1/skills/manifold-vectors-draft-protocol

## Description

DRAFT Protocol — Intake governance for AI tool calls. Ensures AI understands human intent before execution begins.

## Trust

- **Trust score (0–1):** 0.72
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/manifold-vectors/draft-protocol)

## 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": "manifold-vectors-draft-protocol"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/manifold-vectors-draft-protocol` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/manifold-vectors-draft-protocol/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