To-Do Accelerator is a powerful skill designed for seamless task hand-offs and collaborative project execution between human users and AI agents.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install todo-accelerator
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install todo-accelerator using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
To-Do Accelerator transforms the way humans and AI agents interact by establishing a shared communication channel through an Obsidian Kanban board. It allows agents to function as true teammates, capable of picking up pending tasks, executing workflows, and delivering tangible results without constant manual supervision. By bridging the gap between planning and execution, this entry in the Openclaw Skills library ensures that ideas are captured and processed systematically.
The system relies on a structured workflow where tasks move through different lifecycle stages—from initial ideas to active progress and final review. This ensures that the agent always has context on what to work on next, while the user maintains full visibility into the agent's progress, roadblocks, and completed deliverables.
To get started with this addition to your Openclaw Skills, ensure the configuration is active in your agent's workspace:
todo-accelerator-config.yaml exists in the agent's workspace.initialization.md guide located in the skill directory.# Replace <skill-dir> and <workspace> with your specific absolute paths
python3 <skill-dir>/scripts/todo.py --config <workspace>/todo-accelerator-config.yaml
The To-Do Accelerator manages data through a companion markdown note for every task. This structure ensures that both humans and Openclaw Skills can parse the state of work easily.
| Section | Purpose | Update Method |
|---|---|---|
| Frontmatter | Metadata like priority, assigned agent, and iteration count | Managed by scripts |
| What's More | A checklist of specific requirements (- [ ]) |
Updated via commit command |
| Target | Definition of the final expected results and deliverables | Manual/Agent entry |
| Investigation | Real-time findings, progress logs, and encountered issues | Manual/Agent entry |
commit command enforces exact string matching for requirements to ensure no sub-task is overlooked during the delivery phase.Loading
A high-performance web scraping skill that leverages ScrapeNinja's proxy and headless browser capabilities to extract structured web data via Membrane.

A professional-grade content generation tool designed to create high-impact scripts, titles, and publishing packages specifically for WeChat Channels (Channels IP).

A specialized AI agent skill designed to provide deep technical and fundamental analysis of Chinese A-shares, Hong Kong stocks, and US-listed Chinese companies.

A comprehensive AI-driven code review agent that analyzes PR diffs for structural integrity, data safety, and design consistency while proactively applying auto-fixes.

A specialized technical reference for managing container stripping, cargo breakdown, and cross-dock operations.

A comprehensive TypeScript toolkit for building secure, cross-chain decentralized wallets and signing applications on the Mysten Sui network.








































