An intelligent project management system that breaks down complex goals and orchestrates AI sub-agents using cost-effective model selection.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install taskmaster
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install taskmaster using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is TaskMaster?
TaskMaster is a sophisticated project manager and delegation framework designed to transform high-level objectives into manageable, executed workflows. By serving as an orchestration layer within the Openclaw Skills ecosystem, it intelligently assigns tasks to the most appropriate AI models—ranging from lightweight models for data extraction to high-reasoning models for architectural decisions. This ensures that complex projects are completed efficiently without over-spending on token costs.
The skill focuses on autonomous sub-agent management, allowing users to spawn isolated processes that handle specific parts of a project in parallel. TaskMaster acts as the central brain, monitoring progress, managing budgets, and consolidating disparate outputs into a single, high-quality deliverable.
TaskMaster Use Cases
- Orchestrating multi-step development workflows like building a full-stack MVP.
- Conducting deep market research by running parallel search and analysis tasks.
- Managing token budgets for large-scale AI automation projects.
- Delegating routine tasks like data formatting to cheaper models while reserving complex reasoning for premium models.
- Automating failed task retries and escalation paths in production environments.
How TaskMaster Works
- Task Triage: TaskMaster analyzes the project requirements to identify complexity and specific technical needs.
- Model Selection: It automatically assigns the best-fit model (Haiku, Sonnet, or Opus) based on predefined complexity rules.
- Sub-Agent Orchestration: The system spawns isolated sub-agents with specific constraints and tool access.
- Execution and Tracking: Tasks are executed (optionally in parallel) while the system tracks real-time token spend and status.
- Result Aggregation: TaskMaster collects results from all sub-agents and compiles them into a final report or codebase.
TaskMaster Setup
To get started with TaskMaster, ensure you have the Openclaw Skills environment active. Follow these steps to initialize the delegation engine:
# Install required dependencies for the delegation engine
pip install -r requirements.txt
# Enable the TaskMaster skill within your agent environment
openclaw install taskmaster
# Configure your model API keys and default budget limits
cp config.example.yaml config.yaml
TaskMaster Data Schema & Taxonomy
TaskMaster maintains a structured hierarchy for managing project metadata and sub-agent outputs. Data is organized as follows:
| Component | Format | Description |
|---|---|---|
| Task Manifest | JSON | Tracks task IDs, assigned models, and current status. |
| Session Logs | Plaintext | Isolated logs for each sub-agent to prevent context contamination. |
| Budget Registry | SQLite/JSON | Real-time tracking of token consumption and cost per task. |
| Deliverables | Markdown/Code | The final consolidated output generated by the primary agent. |
TaskMaster Advanced Features
- Parallel execution support for running multiple research or coding tasks simultaneously.
- Automated model escalation: Retries failed Haiku tasks on Sonnet and escalates Sonnet failures to Opus.
- Granular budget controls including hard stops and escalation alerts based on dollar thresholds.
- Custom model overrides using the FORCE tag for specific technical requirements.
- Support for custom task templates to standardize frequent delegation patterns.
SKILL.md
Loading
Related Openclaw Skills
Baidu Baike
A specialized knowledge retrieval tool that enables AI agents to query and extract authoritative encyclopedia data from Baidu Baike.
Scrapling Web Fetch
An intelligent web scraping tool that extracts clean main body content and converts it to Markdown for AI processing.
Scrapling Web Fetch
A high-performance web content extractor that transforms messy HTML into clean, LLM-ready Markdown while removing noise and reducing token usage.
Prepper Survival & Emergency AI Skill
A specialized survival and emergency preparedness skill that leverages the dolphin-llama3 model via Ollama to provide uncensored, practical knowledge.
Gotify Notification Skill
A specialized skill for sending real-time push notifications to a Gotify server upon task completion or system events.
Linkding Bookmark Manager
A comprehensive integration for managing, searching, and organizing bookmarks through the Linkding REST API.
Featured*
