todokan-review-loop
Process Todokan task and thought boards with a review-loop workflow. Use when a task enters doing and the agent should pick it up, read latest comments, respond to the newest comment with a high-quality context-aware reply, add an execution update comment, and move the task back to done (Review). Use for recurring polling/cron automation with Todokan MCP.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/banatealab/todokan-review-loopWhat This Skill Does
The todokan-review-loop skill acts as an autonomous Key Account Manager (KAM) for your Todokan workspace. It is specifically designed to manage the lifecycle of tasks that have been delegated to an AI agent. When a user flags a task for AI assistance (assigning it to 'ai' with the 'doing' status), this skill initiates a sophisticated review loop. It parses the complete task context, evaluates the full history of comments to understand the conversation flow, performs cross-task context sweeps to ensure alignment, and provides professional, high-quality responses. Once an update or a question is addressed, the skill systematically moves the task to the 'done' (Review) status, ensuring your workflow remains organized and responsive.
Installation
To integrate this skill into your environment, run the following command within your terminal or OpenClaw interface:
clawhub install openclaw/skills/skills/banatealab/todokan-review-loop
Ensure your Todokan MCP server is correctly configured and authenticated within your agent environment before installation.
Use Cases
- Autonomous Project Management: Ideal for teams that want to offload the tracking of task status updates and common support queries.
- Recurring Review Cycles: Use it as a cron-scheduled job to perform periodic health checks on your active project boards.
- Support Ticketing: Perfect for managing client-facing tasks where clear, consistent communication and status transitions are required.
- Intelligent Triage: Automatically detects blockers and moves tasks to 'Review' only when they are ready for human verification.
Example Prompts
- "Run the todokan-review-loop on all my active boards to catch up on new client feedback and process updates."
- "Check the 'Design' board for any tasks in 'doing' and ensure they are updated with the latest research findings."
- "Initiate the review-loop for the current sprint board to finalize any pending items that have received approval comments."
Tips & Limitations
- Context Awareness: The skill is strictly limited to tasks where
aiEnabled: true. Ensure your tasks are properly tagged, or the agent will ignore them. - Consistency: Because the skill acts as a KAM, avoid manual intervention on tasks currently in the 'doing' state to prevent race conditions.
- Dependencies: This skill relies heavily on the Todokan MCP server. If the server is offline or lacks read/write permissions, the loop will terminate gracefully.
- Transparency: The skill is designed to hide internal orchestration; it only posts relevant progress updates to the user, keeping the thread clean and professional.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-banatealab-todokan-review-loop": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: external-api, file-read, file-write