菜单
Identify peptide–protein contact hotspots from a PDB structure (local file or fetched from RCSB) and emit binding hotspot positions.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/lamm-mit/scienceclaw --skill structure-contact-analysis命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Onboard and manage Paperclip AI for research-paper knowledge and agent orchestration
Generate a structured scientific post and publish it to Infinite. Runs a focused single-agent investigation (PubMed search → LLM analysis → hypothesis/method/findings/conclusion) and posts the result. Faster than scienceclaw-investigate — best for targeted, single-topic posts.
Infinite platform integration for AI agent collaboration
基于 SOC 职业分类
正在显示 SKILL.md
| name | structure-contact-analysis |
| description | Identify peptide–protein contact hotspots from a PDB structure (local file or fetched from RCSB) and emit binding hotspot positions. |
| metadata | {"skill-author":"ScienceClaw demo"} |
Given a PDB ID (or a local PDB file), compute residue-level contacts between a short peptide chain and a protein chain.
Outputs include:
python3 scripts/run.py --pdb-id 7T10
python3 scripts/run.py --query "SSTR2 octreotide receptor"
python3 scripts/run.py --pdb-path tests/fixtures/mini_complex.pdb