An autonomous background research system that captures and investigates technical, product, and algorithmic questions using structured queues.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install research-queue
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 research-queue 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 Research Queue?
The Research Queue skill provides a disciplined framework for AI agents to handle deep-dive investigations without losing focus on the main task. By utilizing a dedicated QUESTIONS.md file, this addition to Openclaw Skills allows for the capture of unresolved queries and systematic investigation through web searches, local code execution, and experiments. This ensures that every technical hurdle or product unknown is addressed with evidence-based conclusions rather than ad-hoc guessing.
This skill is particularly powerful for developers and researchers who need to maintain a record of why certain technical decisions were made. By moving research tasks into a background queue, Openclaw Skills can operate asynchronously via cron jobs to provide answers without interrupting the primary development workflow.
Research Queue Use Cases
- Investigating unresolved technical or algorithmic questions during a development cycle.
- Conducting bounded web or local experiments to verify a hypothesis.
- Building an autonomous, cron-driven research loop to solve background issues.
- Managing a backlog of product or workflow questions that require deliberate study.
- Tracking evidence and conclusions for complex technical decision-making.
How Research Queue Works
- The agent reads or initializes the QUESTIONS.md file to identify pending research items.
- A high-priority open question is selected for active investigation to maintain focus.
- The agent employs the lightest possible method—such as web searches, browser fetching, or local scripts—to gather evidence.
- Findings are recorded, and the question status is updated within the queue with specific evidence and memory notes.
- Completed or abandoned items are moved from the active section to the completed section in a single edit pass.
- Durable findings are saved to the long-term memory folder as Markdown files for future reference.
Research Queue Setup
To get started with this skill within your environment, ensure you have the necessary reference files and the Openclaw Skills framework installed.
# Initialize the research queue by creating the QUESTIONS.md file
# The agent will automatically use the template from references/queue-format.md
touch QUESTIONS.md
To enable autonomous background processing, configure the internal Openclaw Skills cron tool rather than standard system crontabs to ensure proper environment isolation.
Research Queue Data Schema & Taxonomy
The skill relies on a structured Markdown system to track the lifecycle of research tasks and maintain data integrity:
| Component | Description |
|---|---|
| QUESTIONS.md | The central queue file containing active and completed research tasks. |
| references/ | Directory containing the canonical queue-format.md and automation.md templates. |
| memory/ | Directory where durable findings are stored as YYYY-MM-DD.md files. |
| Statuses | Includes open, investigating, blocked, done, and wontfix. |
| Timestamps | Tracks startedAt and completedAt to monitor research velocity. |
Research Queue Advanced Features
- Support for OpenClaw cron to enable autonomous, scheduled background research without main-session pollution.
- Multi-method investigation including browser automation, web fetching, and sandboxed code execution in Python, Rust, or JavaScript.
- Strict evidence tracking and timestamped completion logs for auditable research results.
- Integration with long-term memory for durable knowledge retention across different sessions.
- Intelligent status modeling to distinguish between verified findings, hypotheses, and blocked work.
SKILL.md
Loading
Related Openclaw Skills
Gate Exchange Internal Transfer
A professional skill for executing and automating internal fund transfers between different account types within the Gate Exchange ecosystem.
Gate Unified Account Assistant
A specialized AI skill for managing Gate.io unified account equity, margin borrowing, and leverage configurations with high-precision data handling.
Gate Coupon Assistant
A specialized tool for querying and managing Gate Exchange coupons, vouchers, and trial funds through an AI agent.
OpenCLI Browser Automation
A lightweight browser automation skill that uses opencli and a Chrome/Chromium bridge to control web pages without expensive APIs.
System Cleanup
A specialized utility to audit and safely remove system junk, caches, and logs on Ubuntu and WSL environments.
OpenClaw Gemini Web Skill
A browser-based automation skill that enables OpenClaw agents to perform deep interactions with the Gemini web interface, including authentication and asset management.
Featured*
