← Back to Skills Marketplace
309
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install rxn-im
Description
RxnIM 化学反应图像解析技能。当用户需要：(1) 从化学反应图像提取 SMILES 结构， (2) 识别反应条件（试剂/溶剂/温度/产率），(3) 将反应图转化学结构数据时触发。 基于 Chem. Sci. 2025 论文 "Towards Large-scale Chemical Reaction Imag...
Usage Guidance
Before installing or invoking this skill, consider the following:
- Data privacy: The default recommended path posts images to a specific third-party HuggingFace Space (CYF200127-RxnIM). If your images contain proprietary reactions, IP, or sensitive metadata, do not upload them to that external service without confirming the space owner’s data retention and privacy policies.
- Verify sources: If you plan local deployment, inspect the GitHub repo and HuggingFace model/dataset pages (owner identity, recent commits, issues). Prefer checksums/signatures for large model downloads.
- Validate outputs: The model can hallucinate or produce invalid SMILES; use RDKit or other validators (as suggested) before relying on results for downstream decisions.
- Resource needs: Local deployment requires large GPU memory (~16GB+), CUDA, and substantial disk space for weights — ensure your environment can support that.
- Chaining and sharing: The skill suggests passing results to other skills or corporate docs. Confirm permissions and privacy implications of those downstream services.
- Dual‑use / safety: Extracting reaction conditions and SMILES can expose actionable synthesis information; treat outputs as potentially sensitive and follow your organization’s chemical safety and IP policies.
If you need to use this skill with sensitive data, prefer local inference (after verifying repo and model), or request that the skill be configured to a trusted, auditable inference endpoint under your control.
Capability Analysis
Type: OpenClaw Skill
Name: rxn-im
Version: 2.0.0
The RxnIM skill is a legitimate tool for chemical reaction image parsing, providing structured extraction of SMILES and reaction conditions. It offers a clear HuggingFace API integration and standard local deployment instructions consistent with its stated scientific purpose (referencing a 2025 Chemical Science paper). No indicators of data exfiltration, malicious execution, or prompt injection were found in SKILL.md or the associated metadata.
Capability Assessment
Purpose & Capability
Name/description match the instructions: all runtime steps (base64 images, POST to a HuggingFace Space, optional local conda deploy and model weights) are directly relevant to extracting SMILES and reaction conditions. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
Runtime instructions stay within the stated purpose (encode image → call HF space → parse result → format). However, the recommended default is a specific third‑party HuggingFace Space (https://CYF200127-RxnIM.hf.space) — uploading images there may expose sensitive/ proprietary chemical structures or metadata to that space's owner. The skill also suggests chaining outputs to other skills and uploading results to corporate document services, which increases data-sharing scope and should be considered by the user.
Install Mechanism
This is instruction-only (no install spec), which is low-risk. Local-deploy instructions reference cloning a GitHub repo and downloading ~14 GB model weights from HuggingFace — those are standard hosts, but large external artifacts should be verified (checksums, repo owner) before execution. No obscure or shortener URLs are used.
Credentials
No environment variables, secrets, or system config paths are requested. Optional dependencies (RDKit, CUDA, torch, etc.) are appropriate for a local ML inference workload.
Persistence & Privilege
Skill does not request always:true and contains no instructions to modify other skills or system-wide agent settings. Autonomous invocation remains possible (platform default) but is not combined with additional privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install rxn-im - After installation, invoke the skill by name or use
/rxn-im - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.0.0
**v2.0.0: Major skill documentation refactor and localization**
- Completely rewritten skill documentation in Chinese, optimized for users in the chemical and scientific community.
- Clarified multi-modal model capabilities, tasks, and performance with clear tabular presentations.
- Detailed API call examples, workflow, output formatting, and error handling guidelines.
- Outlined triggering phrases and chaining use cases with related chemistry skills.
- Added installation and deployment instructions for both online HuggingFace API and local conda environments.
- Included tables for resources, dependencies, known limitations, and references.
v1.0.0
- Initial release of RxnIM skill for chemical reaction image parsing.
- Supports extraction of reactants, products (as SMILES), and conditions (reagents, solvents, temperature, yield) from reaction images.
- Offers two modes: web API (Hugging Face Spaces) and local inference (GPU required).
- Outputs structured JSON or formatted reaction strings.
- Achieves 84%–92% soft match F1 score on benchmark datasets.
- Includes setup and usage instructions for both modes.
Metadata
Frequently Asked Questions
What is RxnIM?
RxnIM 化学反应图像解析技能。当用户需要：(1) 从化学反应图像提取 SMILES 结构， (2) 识别反应条件（试剂/溶剂/温度/产率），(3) 将反应图转化学结构数据时触发。 基于 Chem. Sci. 2025 论文 "Towards Large-scale Chemical Reaction Imag... It is an AI Agent Skill for Claude Code / OpenClaw, with 309 downloads so far.
How do I install RxnIM?
Run "/install rxn-im" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is RxnIM free?
Yes, RxnIM is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does RxnIM support?
RxnIM is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created RxnIM?
It is built and maintained by fqiangliu (@fqiangliu); the current version is v2.0.0.
More Skills