← 返回 Skills 市场
318
总下载
0
收藏
2
当前安装
1
版本数
在 OpenClaw 中安装
/install drug-team
功能描述
Coordinates specialized AI agents to design novel drug candidates with synthesis routes, inventory checks, ADMET/Tox evaluation, pharmacology scoring, and pa...
使用说明 (SKILL.md)
drug-team
Meta-skill that orchestrates a team of specialized AI agents for drug design.
Overview
- Purpose: Designs novel drug candidates for a given target/indication with constraints (e.g., "Design drug for pain relief, logP\x3C3").
- Agents:
- Chem Synth (uses chemistry-query skill): Proposes molecular scaffolds and synthesis routes.
- Synth Notebook (uses synth-notebook skill): Visualizes routes, optimizes yields, checks safety.
- Lab Inventory (uses lab-inventory skill): Checks stock for reagents, estimates costs.
- ADMET: Predicts QED, SA, logP, TPSA, pKa using RDKit/ML proxies.
- Tox: Checks PAINS, Brenk alerts, Ames test.
- Pharm: Evaluates target binding affinity (docking proxy via web/tools).
- Patent Scout (uses patent_scout.py): Scans for prior art patents, computes novelty score, checks for blocking patents via web searches.
- Coordination: Iterative polling and messaging between agents to refine candidates.
- Output: Table of top 3 molecules (SMILES, route, scores) + visualizations (e.g., mol images).
Triggers
- drug design
- design drug
- painkiller
- drug synthesis
- synth pharm
- design molecule
- "low tox" drug
- inventory-aware design
- design with stock check
- check stock for synthesis
- patent
- novelty
- prior art
Usage
When triggered, runs scripts/orchestrate.py \"{user_query}\" .
Integration
- Integrates chemistry-query for initial scaffolds and routes.
- Uses synth-notebook for route visualization, yield optimization, and safety checks.
- Incorporates lab-inventory for reagent stock checking and cost estimation.
- Ranks candidates including feasibility scores based on yield, safety (with SDS scans for route chemicals, risk scores, and alerts), and inventory availability.
- Post-design patent scouting to include novelty scores and blocking status in candidate ranking ("High novelty: no blocking patents").
Dependencies
- RDKit (installed)
- chemistry-query skill (exists)
- synth-notebook skill
- lab-inventory skill
- Matplotlib/Plotly for viz
- OpenClaw subagent spawning
- beautifulsoup4 for patent_scout scraping
安全使用建议
What to consider before installing:
- Provenance: the owner and homepage are unknown. Prefer skills from verified/known sources when dealing with proprietary chemistry.
- External network: this skill will send search terms (SMILES or names) to patents.google.com via patent_scout.py — do not run it on confidential molecules unless you accept that risk or block network access.
- File access: it executes scripts from sibling skill directories and may create or overwrite files there (it will create a stock.csv in lab-inventory if missing). Ensure those other skills are trusted and you are okay with cross-skill file writes.
- Review other skills: because it calls chemistry-query, synth-notebook, and lab-inventory scripts directly, inspect those repos/scripts to confirm they are safe and that calling them via subprocess is intended.
- Environment assumptions: the package contains a venv config but no installer; confirm RDKit and other Python dependencies exist in your environment before running.
- Recommended mitigations: run in an isolated sandbox, disable outbound network during patent-scout if you need confidentiality, back up or sandbox other skill directories to avoid unintended file writes, and review the code of the called sibling scripts. If you need help assessing the other skills (chemistry-query, synth-notebook, lab-inventory), gather their code and provenance and re-run an evaluation.
功能分析
Type: OpenClaw Skill
Name: drug-team
Version: 1.0.0
The drug-team skill bundle is a legitimate orchestration tool for drug discovery, coordinating multiple specialized agents for chemistry, toxicity, and patent analysis. The primary logic in scripts/orchestrate.py uses subprocess.run to execute internal scripts and other skills with well-controlled arguments, while scripts/patent_scout.py performs web scraping on Google Patents to evaluate molecular novelty, which is consistent with its stated purpose. No evidence of data exfiltration, malicious persistence, or intentional harmful behavior was found in the code or the agent instructions.
能力评估
Purpose & Capability
The name/description (orchestrating chemistry, synthesis, inventory, ADMET, patent scouting) aligns with the included code and dependencies (RDKit, BS4, integration hooks). However the code reaches into sibling skill directories (e.g., skills/chemistry-query, skills/synth-notebook, skills/lab-inventory) via relative filesystem traversal — this is a non-obvious design choice that requires those other skills to be present and gives the skill access to other skill files. The presence of a venv/pyvenv.cfg file in the package but no install spec is also unexpected.
Instruction Scope
SKILL.md instructs running scripts/orchestrate.py and the script executes other skills' Python scripts (via subprocess.run), reads/writes files (creates temp, viz, and may write stock.csv into the lab-inventory directory), and performs web scraping (patents.google.com). The script will send candidate identifiers/SMILES to external sites for patent searches, which can leak proprietary molecular structures. It also creates/modifies files inside other skill directories (creating stock.csv if missing), which is scope creep and could corrupt or persist data outside the skill's own sandbox.
Install Mechanism
There is no install specification (instruction-only install), which is low risk. But a venv/pyvenv.cfg file is included in the package — odd for an instruction-only skill and suggests assumptions about environment or bundled virtualenv state. No external download URLs are used.
Credentials
The skill declares no required credentials or env vars (good), but it performs outbound web requests (patent_scout.py uses requests to query patents.google.com) without warning. Sending candidate SMILES, names, or other search queries to external web endpoints can leak IP or sensitive data. The skill also executes other local skill scripts — if those scripts expect credentials or secrets, this skill could indirectly cause exposure. The skill's dependency list mentions beautifulsoup4 but does not explicitly list 'requests' (used in code), a minor mismatch.
Persistence & Privilege
always is false and the skill does not request elevated platform privileges. However it writes files into sibling skill directories (e.g., lab-inventory/stock.csv) and creates temp/viz folders in the working directory, which gives it a degree of persistent footprint across the workspace and could affect other skills' state. It does not modify agent configuration or request permanent inclusion.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install drug-team - 安装完成后，直接呼叫该 Skill 的名称或使用
/drug-team触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release of "drug-team" meta-skill for automated, multi-agent drug design:
- Orchestrates a team of specialized agents for drug candidate generation, synthesis planning, ADMET/tox prediction, and patent analysis.
- Supports design queries with chemical, safety, and novelty constraints.
- Integrates skills: chemistry-query, synth-notebook, lab-inventory, and custom patent scouting.
- Provides outputs including top candidate molecules, feasibility and novelty scores, and visualizations.
- Automatically checks reagent inventory and estimates synthesis costs.
元数据
常见问题
Drug Team 是什么？
Coordinates specialized AI agents to design novel drug candidates with synthesis routes, inventory checks, ADMET/Tox evaluation, pharmacology scoring, and pa... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 318 次。
如何安装 Drug Team？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install drug-team」即可一键安装，无需额外配置。
Drug Team 是免费的吗？
是的，Drug Team 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Drug Team 支持哪些平台？
Drug Team 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Drug Team？
由 Cheminem（@cheminem）开发并维护，当前版本 v1.0.0。
推荐 Skills