An infinite, self-driven research agent that autonomously identifies topics, conducts deep investigations, and documents findings in Feishu.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install autonomous-research-loop
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 autonomous-research-loop 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 Autonomous Research Loop?
The Autonomous Research Loop is a sophisticated self-evolving intelligence system designed for continuous knowledge acquisition. Operating as a core component within the Openclaw Skills ecosystem, it functions on a recursive logic of generation, investigation, and documentation. This skill is engineered to run without human oversight, ensuring a constant stream of high-quality technical and market insights is delivered to your workspace.
By leveraging autonomous agent protocols, the loop identifies gaps in its current knowledge base and proactively fills them. It doesn't just search for information; it synthesizes mechanism breakdowns, actionable strategies, and even functional code frameworks, making it an invaluable asset for teams requiring 24/7 intelligence monitoring and documentation.
Autonomous Research Loop Use Cases
- Building a self-growing corporate knowledge base without manual research labor.
- Tracking emerging technology trends by allowing the agent to branch into derivative topics autonomously.
- Creating high-frequency technical briefings and Python-based proof-of-concepts for R&D teams.
- Automating the population of Feishu or Lark documentation centers with structured industry analysis.
How Autonomous Research Loop Works
- A system-level Cron job triggers the research agent every five minutes.
- The agent parses the research_pool.json file to assess the current queue of pending topics.
- If the queue is empty, the agent uses its internal LLM logic to generate new high-value research subjects.
- A deep research phase is initiated, where the agent explores the selected topic, identifies core mechanisms, and highlights risks.
- The findings are formatted into a structured report and exported to a Feishu document.
- The research pool is updated, marking the topic as completed and generating three new related topics to ensure the loop never ends.
Autonomous Research Loop Setup
To deploy this skill within your Openclaw Skills environment, follow these steps:
# Navigate to the Openclaw workspace directory
cd /root/.openclaw/workspace/
# Create the required research pool tracking file
touch research_pool.json
# Configure your Feishu/Lark API credentials in the environment
# Set up a Cron job to execute the research loop script every 5 minutes
(crontab -l 2>/dev/null; echo "*/5 * * * * /usr/bin/python3 /path/to/research_loop_trigger.py") | crontab -
Autonomous Research Loop Data Schema & Taxonomy
The skill utilizes a centralized JSON schema to maintain state and manage the infinite queue:
| Attribute | Type | Description |
|---|---|---|
completed_topics |
Array | A historical log of all successfully researched and documented subjects. |
pending_topics |
Array | Objects containing the next topics to be processed and their initial descriptions. |
stats |
Object | Metadata including total_completed count and last_completed_at timestamps. |
config |
Object | Operational parameters such as interval_minutes and new_topics_per_completion. |
Autonomous Research Loop Advanced Features
- Infinite Recursive Discovery: Automatically generates three new research branches for every completed task to prevent the loop from stalling.
- Robust Error Recovery: Designed to exit immediately on failure, allowing the system Cron to restart the process and maintain high uptime.
- Structured Insight Templates: Every output is standardized to include core summaries, mechanism chains, actionable points, and risk assessments.
- Zero-Human Intervention: Fully autonomous decision-making from topic selection to document publication.
SKILL.md
Loading
Related Openclaw Skills
QQ Bot Voice Transcribe
An automated speech-to-text skill for QQ Bots that decodes Silk V3 audio and transcribes it using OpenAI Whisper.
Context Compressor
Context Compressor intelligently condenses conversations, source code, and logs to fit more information into limited AI context windows without losing core meaning.
Pixel Art Processing
A comprehensive pixel art and sprite sheet processing pipeline for game developers and digital artists.
Tutoring Video
An AI-powered video assistant that transforms educational expertise and student success stories into compelling enrollment scripts for tutors.
Exhibitor Show History
A specialized research tool that retrieves the complete trade show exhibition history for any company using the Lensmor API.
Pattern Recognition Skill
An intelligent learning system that identifies operational patterns and generates optimized templates to enhance agent performance.
Featured*
