# Draft Review

> Use this tool when you need to review and refine AI-generated content, such as PR descriptions, tickets, or messages, to ensure accuracy and quality. It provides a human-in-the-loop review step with a split-pane editor and live markdown preview, allowing users to modify and approve or reject drafts. Ideal for workflows involving GitHub, Linear, Slack, email, and other platforms, where precision and context-aware review are crucial.

Canonical page: https://skillsregistry.net/skills/sgasser-draft-review  
JSON: https://api.skillsregistry.net/v1/skills/sgasser-draft-review

## Description

Provides a human-in-the-loop review step for AI-generated content. When an AI assistant drafts a PR description, ticket, or message, this server opens a local browser window with a split-pane editor showing editable text alongside a live markdown preview. Users can modify the draft and approve it with a keyboard shortcut or reject it to request changes. Supports context-aware workflows for GitHub, Linear, Slack, email, and generic targets, with optional tool chaining to pass approved content directly to subsequent MCP operations.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** version-control
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/sgasser-draft-review)
- **Repository:** <https://github.com/sgasser/draft-mcp-server>

## 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": "sgasser-draft-review"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sgasser-draft-review` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sgasser-draft-review/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