The Task Extractor is a robust workflow skill that captures, organizes, and verifies multiple instructions from a single prompt to ensure zero task drop.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install task-extractor
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 task-extractor 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 Task Extractor?
The Task Extractor is a critical protocol designed for Openclaw Skills to handle complex, multi-layered user instructions. When an agent receives a message with three or more distinct actions, this skill intervenes to prevent task drop—a common failure in high-context LLM interactions. By standardizing how tasks are identified and tracked, it transforms chaotic prompt dumps into a structured roadmap for Openclaw Skills to follow.
This skill is particularly valuable for developers and power users who provide high-level instructions that touch multiple parts of a codebase or infrastructure. It ensures that every instruction, from a minor configuration change to a heavy-duty sub-agent deployment, is captured in a persistent workspace file and verified before the session is marked as complete.
Task Extractor Use Cases
- Managing feature requests that involve simultaneous frontend, backend, and DevOps changes.
- Processing long lists of research items or data points that require individual verification.
- Coordinating sub-agent spawns for heavy-duty tasks without losing session context.
- Handling complex prompt dumps with mixed technical instructions and "and then" sequences.
How Task Extractor Works
- Identify user messages containing 3 or more distinct actionable items or verbs.
- Extract tasks into a structured Markdown table saved as TASK_QUEUE.md in the workspace.
- Provide an immediate receipt to the user confirming the identified checklist before execution starts.
- Execute tasks based on dependency order, utilizing parallel calls for quick tasks and sub-agents for heavy tasks.
- Update the task queue with artifacts and evidence for every successful completion or failure.
- Reconcile the final status and report back to the user with a comprehensive completion summary.
Task Extractor Setup
To integrate this skill with your Openclaw Skills environment, ensure your agent has file system permissions to manage the workspace.
# Ensure the agent manifest includes task-extractor
# The agent will automatically generate TASK_QUEUE.md upon triggering
Task Extractor Data Schema & Taxonomy
The skill maintains state using a structured file that acts as the single source of truth for all Openclaw Skills tasks:
| Column | Description |
|---|---|
| # | Sequential task number for ordering |
| Task | One-line summary using an imperative verb |
| Type | Classification (BUILD, FIX, RESEARCH, SEND, DEPLOY, CONFIG, OTHER) |
| Effort | Estimated complexity (QUICK, MEDIUM, HEAVY) |
| Status | Visual indicators for progress (Pending, Done, Failed, Partial, or Sub-agent) |
| Artifact | Verifiable evidence such as a file path, URL, or commit hash |
Task Extractor Advanced Features
- Parallel batching of quick tasks to optimize execution speed within Openclaw Skills.
- Automatic sub-agent spawning and lifecycle tracking for heavy workloads.
- Persistent state recovery using the TASK_QUEUE.md file during context overflows or session restarts.
- Checkpoint updates sent to the user after every five completed tasks to maintain transparency.
- Smart dependency mapping to ensure tasks are performed in the correct logical order regardless of their original list position.
SKILL.md
Loading
Related Openclaw Skills
Batch Executor
A high-scale processing engine designed to transform massive dumps of mixed content into executed tasks and structured reports using parallel sub-agents.
Financial Statement Review Skill
A professional AI-driven financial statement review tool for comprehensive compliance auditing and tax risk identification based on Chinese accounting standards.
Spawner
Spawner is a high-performance orchestration skill that automates the hiring, configuration, and monitoring of AI sub-agents to execute complex job board tasks.
Orchestrator v2: Strategic Project Manager
A strategic management agent that transforms vague user requests into comprehensive, multi-wave execution plans by inferring hidden requirements.
Kawaii Art Generator
An AI-powered generator for creating cute characters, chibi illustrations, and Japanese kawaii aesthetics.
Stock-QData
A professional tool for downloading A-share historical market data across multiple timeframes using natural language commands and the QMT quantitative platform.
Featured*
