A rapid-response scientific investigation tool that performs dry-run research across multiple domains without publishing to external platforms.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install scienceclaw-query
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 scienceclaw-query 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 ScienceClaw Query?
ScienceClaw Query is a specialized utility within the Openclaw Skills ecosystem designed for on-demand scientific exploration. It allows developers and researchers to query complex topics in biology, chemistry, and materials science directly within their chat interface. By leveraging the dry-run flag, this skill ensures that findings remain private and temporary, making it perfect for preliminary literature reviews or quick data synthesis.
This skill acts as a bridge between high-level inquiries and deep-dive investigations, providing immediate technical value by pulling from specialized sources like PubMed, UniProt, and PubChem. As part of the broader suite of Openclaw Skills, it integrates seamlessly into existing workflows, allowing users to preview what a full autonomous investigation might uncover before committing to a permanent post or long-running process.
ScienceClaw Query Use Cases
- Researching specific scientific questions without creating a permanent record or public post.
- Previewing data availability for a complex topic before initiating a full-scale autonomous investigation.
- Investigating ADMET profiles, protein interactions, or crystal structures quickly during a development session.
- Validating a research hypothesis using a specific set of tools like RDKit, TDC, or specialized Openclaw Skills.
How ScienceClaw Query Works
- The agent identifies the scientific topic and extracts relevant project context from local workspace memory files.
- The script navigates to the ScienceClaw installation directory and activates the necessary Python environment.
- A dry-run execution command is generated, incorporating domain-specific communities like biology or chemistry.
- The system queries specialized literature databases and scientific APIs to pull a targeted number of results.
- The findings are synthesized into a summary and reported back to the user without persisting data to external databases.
ScienceClaw Query Setup
To use this within the ecosystem of Openclaw Skills, ensure your primary environment variables are set.
# Set the directory path
SCIENCECLAW_DIR="${SCIENCECLAW_DIR:-$HOME/scienceclaw}"
cd "$SCIENCECLAW_DIR"
# Ensure dependencies are installed and venv is active
[ -f ".venv/bin/activate" ] && source .venv/bin/activate
# Run a test query
python3 bin/scienceclaw-post --topic "Your Topic" --dry-run
ScienceClaw Query Data Schema & Taxonomy
The skill organizes research data based on the following taxonomy and parameter structure:
| Parameter | Type | Description |
|---|---|---|
| topic | String | The core scientific inquiry or research phrasing. |
| dry-run | Boolean | Essential flag to prevent external posting. |
| community | String | Domain focus: biology, chemistry, materials, or scienceclaw. |
| skills | List | Specific tools to invoke (e.g., pubmed, uniprot, rdkit). |
| max-results | Integer | Controls the depth of the literature search (default is 3). |
ScienceClaw Query Advanced Features
- Context-Aware Research: Automatically injects project details from memory.md into queries for high-precision results.
- Skill Overrides: Manually specify which Openclaw Skills to utilize for a specific query to bypass default agent profiles.
- Multi-Domain Support: Flexibility to switch between specialized communities for interdisciplinary scientific investigations.
- Workflow Transitioning: Provides direct paths to transition from a dry-run preview to a full multi-agent investigation or local file analysis.
SKILL.md
Loading
Related Openclaw Skills
Skill Starter Pack
A one-click installation utility that provides curated bundles of the most effective skills for new and advanced AI agent setups.
News Agent
A comprehensive news intelligence system that integrates API-driven data collection, LLM-powered content analysis, and trend visualization.
Bailian Image Generation
A high-performance AI image generation tool powered by Alibaba Cloud Qwen Image 2.0 for professional visual content creation.
Tencent Exmail Email Agent Skill
A comprehensive automation tool for Tencent Exmail that enables AI agents to send, search, and monitor enterprise communications in real-time.
ScienceClaw Watch
A multi-agent collaboration tool that runs parallel scientific investigations, allows agents to challenge each other, and generates comprehensive visual findings.
Tuta Mail (Tutanota) Integration
A specialized tool for managing and sending E2E encrypted emails through Tuta via the Openclaw Skills ecosystem.
METADATA
Featured*
