todokan-review-loop

# Todokan Review Loop

Use this workflow for autonomous handling of `doing` items.

**Note:** The MCP server only returns tasks where `aiEnabled: true` by default. Users send tasks to AI via a "Send to AI" button, which sets `aiEnabled: true`, `assignee: 'ai'`, and `status: 'doing'`. This skill will only see tasks that users have explicitly sent to AI.

## Role Model

- Act as the Key Account Manager (KAM) as the single user-facing voice.
- Keep one consistent tone and ownership in comments.
- Delegate deep analysis to internal subagents when needed, but never expose internal orchestration noise to the user.

## Workflow

1. List habitats.
2. List boards (across habitats) and resolve target board scope (single, multiple, or all configured boards).
3. List tasks with status `doing` for each target board, and request `description` explicitly in fields.
4. For each task:
   - Read task fields (title, description, labels, dueDate, priority, status).
   - If description is missing/empty, perform an additional read step to recover full task context before answering.
   - Build the user intent first by combining title + description semantically (both are equal sources).
   - Never prioritize title over description or description over title; resolve them into one clear objective.
   - Read the entire comment thread (not only latest comment).
   - Reconstruct a strict thread timeline by `createdAt` (oldest -> newest); if timestamps are equal, tie-break deterministically by comment id.
   - Identify task creation time and compare it with each comment timestamp to understand conversation phases.
   - Identify the latest comment by `createdAt`.
   - Count total comments.
   - Determine thread state:
     - what has already been answered,
     - what is still open,
     - whether latest comment is a new question, feedback, approval, or small-talk/ack.
   - Run a quick context sweep in Todokan:
     - check related tasks in same board (title/labels/status),
     - optionally insp...

# Todokan Review Loop Skill

Autonomous review-loop workflow for Todokan boards.

This skill is optimized for recurring bot runs:
- pick tasks in `doing`
- process full comment context
- post a high-quality response comment
- move task to `done` (Review) when appropriate

## Prerequisites

- Todokan API key (`kb_live_...`)
- Todokan MCP configured in OpenClaw (`/mcp` planner endpoint)
- OpenClaw runtime with skill loading enabled

## Local Test (without ClawHub)

```bash
mkdir -p ~/.openclaw/skills
cp -r skills/openclaw/todokan-review-loop ~/.openclaw/skills/todokan-review-loop
```

Then restart OpenClaw.

## Beta Publish (recommended first)

Use a beta slug first, test privately, then publish final slug.

```bash
# from repo root
clawhub login
clawhub publish skills/openclaw/todokan-review-loop --slug todokan-review-loop-beta
```

Install for testing:

```bash
clawhub install todokan-review-loop-beta
```

If beta is good, publish final:

```bash
clawhub publish skills/openclaw/todokan-review-loop --slug todokan-review-loop
```

## Suggested MCP Config

```json
{
  "mcpServers": {
    "todokan": {
      "transport": "streamable-http",
      "url": "https://todokan.com/mcp",
      "headers": {
        "Authorization": "Bearer kb_live_YOUR_API_KEY"
      }
    }
  }
}
```

## Scope Guidance

For this review-loop, planner permissions are typically required because it writes comments and status updates.

Minimum practical scopes:
- `boards:read`
- `tasks:read`
- `tasks:write`
- `comments:read`
- `comments:write`

Optional for extended context:
- `docs:read`

## Notes

- Keep this as a separate skill from the general `todokan` skill.
- Publish silently first (no announcement), verify real bot behavior, then announce.