taskmaster
Project manager and task delegation system. Use when you need to break down complex work into smaller tasks, assign appropriate AI models based on complexity, spawn sub-agents for parallel execution, track progress, and manage token budgets. Ideal for research projects, multi-step workflows, or when you want to delegate routine tasks to cheaper models while handling complex coordination yourself.
Why use this skill?
Automate complex projects with TaskMaster for OpenClaw. Streamline task delegation, manage token budgets, and orchestrate AI models for maximum efficiency.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/jlwrow/taskmasterWhat This Skill Does
TaskMaster is a comprehensive project management and task delegation engine designed for the OpenClaw ecosystem. It acts as a primary orchestrator that decomposes high-level objectives into granular, actionable tasks. By intelligently mapping specific tasks to the appropriate AI model based on the complexity of the requirement, TaskMaster optimizes both performance and cost. It manages sub-agent spawning, monitors real-time progress, and enforces token budget constraints, ensuring that resource-heavy models like Opus are reserved for strategic reasoning while faster, cheaper models like Haiku handle routine maintenance and data processing.
Installation
To integrate TaskMaster into your OpenClaw environment, ensure you have the necessary permissions enabled for sub-agent management and external API calls. Execute the following command in your terminal:
clawhub install openclaw/skills/skills/jlwrow/taskmaster
Once installed, verify the installation by calling the help function within the agent console to ensure all dependencies and system prompts are correctly initialized.
Use Cases
- Software Development Lifecycle: Manage an entire codebase evolution, from architectural planning (Opus) to coding tasks (Sonnet) and unit test generation (Haiku).
- Market Intelligence: Execute broad research projects where you need to scrape data, summarize findings, and synthesize a final executive report.
- Automated Workflows: Build repeatable task chains that require parallel processing, such as concurrent security audits and performance testing on different branches of a project.
- Budget-Sensitive Projects: Maintain strict control over development spending by automating the selection of models, preventing unnecessary token burn on simple documentation tasks.
Example Prompts
- "TaskMaster: Research top 5 Python frameworks for AI agents. Split tasks into library search, documentation review, and final comparison. Keep total budget under $1.00."
- "TaskMaster: Build a backend API for my task tracker. Use Sonnet for code, Opus for design, and keep a log of all token usage per task."
- "TaskMaster: Conduct a security audit on the provided directory. Use parallel execution to scan files simultaneously and report findings in a summary table."
Tips & Limitations
- Model Selection: Always prioritize Haiku for data extraction tasks. Over-utilizing Opus for simple tasks will result in rapid budget depletion.
- Constraint Handling: Use the
[FORCE: model]tag if you find the auto-selection is misinterpreting the nuance of a specific technical prompt. - Limitations: TaskMaster operates best with well-defined tasks. Extremely vague instructions may lead to poor sub-agent performance, necessitating manual intervention. Always set a 'Max budget' when spawning parallel sub-agents to prevent unexpected costs.
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-jlwrow-taskmaster": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: external-api, code-execution, file-read, file-write