← Back to Skills Marketplace
103
Downloads
1
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install virtual-screening
Description
Virtual screening workflows combining protein-sequence lookup, docking box calculation, transformer-based library screening, and docking-based proprietary li...
Usage Guidance
This skill legitimately talks to and relies on SciMiner (https://sciminer.tech) and requires you to set SCIMINER_API_KEY. Before installing: (1) confirm you trust sciminer.tech and its privacy/terms because the skill will upload sequences, receptor PDBs, and any candidate library files to their API; (2) avoid using a highly privileged or long-lived key — prefer a scoped/ephemeral key if possible; (3) if you plan to screen proprietary or confidential molecules/structures, verify that sending them to SciMiner is permitted by your organization; (4) note there is no homepage/source URL in the registry entry and the publisher identity is opaque, so if provenance matters seek additional verification from the skill author or vendor.
Capability Analysis
Type: OpenClaw Skill
Name: virtual-screening
Version: 1.0.2
The virtual-screening skill is a legitimate integration for bioinformatics workflows using the SciMiner API (sciminer.tech). The SKILL.md and sciminer_registry.py files define standard procedures for protein sequence retrieval, docking box calculation, and molecular screening. While the instructions steer the agent to use the SciMiner service exclusively, this behavior is aligned with the skill's stated purpose and lacks any indicators of data exfiltration, malicious execution, or harmful prompt injection.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description (virtual screening) align with the declared dependency (SCIMINER_API_KEY) and the included registry describing transformer- and docking-based screening tools. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md instructs the agent to call SciMiner internal API endpoints and to upload local files (receptor PDBs, ligands). This is coherent for the stated purpose, but it means user-provided sequences, structure files, and library files will be sent to https://sciminer.tech. The docs explicitly forbid falling back to other services and require the SciMiner API path.
Install Mechanism
No install spec or remote downloads; only small local Python registry files are included. Nothing in the install mechanism writes or executes code from unknown URLs.
Credentials
Only a single credential (SCIMINER_API_KEY) is required and is the primaryEnv. That is proportional for a third-party API-based service. There are no other secret env vars or config paths requested.
Persistence & Privilege
always:false and no system-wide config access — no excessive privilege requested. However, the skill allows autonomous model invocation (platform default), meaning an agent could call the SciMiner API and upload files when the skill is invoked without extra manual steps; consider this when granting the API key.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install virtual-screening - After installation, invoke the skill by name or use
/virtual-screening - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
- Clarified that the SciMiner API key is free and updated the prerequisite messaging to reflect this.
- Improved language on API key requirements for user guidance.
- No functional or workflow changes introduced.
v1.0.1
- Added explicit method selection rules to clarify when to use transformer-based or docking-based workflows based on the presence of a protein structure file or PDB ID.
- Updated workflow guidance to route requests according to input type and ensure correct tool invocation order.
- Emphasized that docking-based workflows require docking box calculation before screening.
- Improved clarity and step-by-step instructions for both transformer-based and docking-based screening use cases.
- Made notes and method selection more concise, reducing redundancy.
v1.0.0
- Initial release of the virtual-screening skill, providing end-to-end workflows for protein and small-molecule virtual screening.
- Integrates protein sequence lookup, docking box calculation from natural-language input, transformer- and docking-based library screening using the SciMiner platform.
- Supports file uploads and parameterized tool invocation via the SciMiner API, requiring the `SCIMINER_API_KEY` credential.
- Includes guidance for choosing and chaining tools based on user input (target name, sequence, binding site description, receptor structure).
- Ensures result sharing by including an online `share_url` in all tool outputs.
Metadata
Frequently Asked Questions
What is Virtual Screening?
Virtual screening workflows combining protein-sequence lookup, docking box calculation, transformer-based library screening, and docking-based proprietary li... It is an AI Agent Skill for Claude Code / OpenClaw, with 103 downloads so far.
How do I install Virtual Screening?
Run "/install virtual-screening" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Virtual Screening free?
Yes, Virtual Screening is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Virtual Screening support?
Virtual Screening is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Virtual Screening?
It is built and maintained by SciMiner (@sciminer); the current version is v1.0.2.
More Skills