internscience
- 642 skills
- 0 followers
- 607 repo stars
- last month last updated
- ▌ Multiomics Integration 3 · internscienceMulti-Omics Integration - Integrate transcriptomics (TCGA), proteomics (UniProt), pathway enrichment (STRING), and metabolic pathway (KEGG) data for a target gene. Outputs a unified JSON report combining expression profiles, protein annotations, enriched pathways, and KEGG pathway details.
- ▌
- ▌
- ▌
- ▌ Planner 3 · internscienceA guideline for how to plan, split, assign tasks, and report back. Governs how the main agent triages user instructions, plans multi-agent work, splits plans into execution blocks, assigns blocks to project agents via route_to_project, tracks progress with beads, and reports outcomes.
- ▌ Local Skill Hub 5 · internscienceManage dormant local skill templates and attach them to project agents or equipment agents.
- ▌ Failure Escalation 3 · internscienceTerminate on unrecoverable external blockers and report precise error details.
- ▌ Nsfc Qc 2 · internscience bundle当用户明确要求"标书QC/质量控制/润色前质检/引用真伪核查/篇幅与结构检查"时使用。对 NSFC 标书进行只读质量控制:并行多线程独立检查文风生硬、引用假引/错引风险、篇幅与章节分布、逻辑清晰度等,最终输出标准化 QC 报告;中间文件默认归档到“交付目录内的隐藏工作区(.nsfc-qc/)”,并兼容 legacy `.nsfc-qc/`。
- ▌ Ssh Essentials 2 · internscience bundleEssential SSH commands for secure remote access, key management, tunneling, and file transfers.
- ▌ Nsfc Code 2 · internscience bundle根据 NSFC 标书正文内容,结合申请代码推荐库,为你给出 5 组申请代码1/2(主/次)推荐与理由;输出到 NSFC-CODE-vYYYYMMDDHHmm.md(只读,不修改标书)
- ▌ Nsfc Budget 2 · internscience bundle当用户明确要求“写/生成 NSFC 预算说明书”“写预算说明”“生成 budget.tex / budget.pdf”“写国自然预算 justification”时使用。基于用户标书正文或补充材料,输出一份可提交的预算说明书 LaTeX 项目并渲染 `budget.pdf`。若用户未指定工作目录,必须暂停并先要求其指定。⚠️ 不适用:用户只是想了解预算原则;用户仅要预算表数字而不写说明书;或用户是 2026 青年 A/B/C 默认包干制且无需预算说明书的场景。
- ▌ Nsfc Roadmap 2 · internscience bundle当用户明确要求"生成 NSFC 技术路线图/技术路线图绘制/roadmap/flowchart"或需要把标书研究内容转成"可打印、A4 可读"的技术路线图时使用。默认输出可编辑源文件(`.drawio`)与可嵌入文档的渲染结果(`.svg`/`.png`/`.pdf`);当用户主动提及 Nano Banana/Gemini 图片模型时,可切换为 PNG-only 模式。⚠️ 不适用:用户只是想修改某张已有图片的格式/尺寸(应使用图片处理技能)、只是想润色技术路线文字描述(应直接改写正文)。
- ▌ Guide Updater 2 · internscience bundle当用户明确要求"更新项目指南""同步指南""沉淀洞见到指南"时使用。将对话中新产生的可复用写作洞见实时沉淀到项目指南文件,保持术语口径一致、结构稳定、可检验与可复现。调用时必须指定指南文件路径。
- ▌ Nsfc Abstract 2 · internscience bundle当用户明确要求"写/润色 NSFC 标书摘要""生成中文摘要和英文摘要""把中文摘要翻译成英文摘要"时使用。输出中文、英文两个版本(英文必须是中文的忠实翻译版),同时输出标题建议(1个推荐标题+5个候选标题及理由)。中文摘要默认≤400字符,英文摘要默认≤4000字符。输出方式:将结果写入工作目录下的 `NSFC-ABSTRACTS.md`。⚠️ 不适用:用户只想翻译一段与标书无关的通用文本(应直接翻译);用户只想写立项依据/研究内容/研究基础正文(应使用对应 nsfc 系列 skill)。
- ▌ Multiomics Integration 2 · internscienceMulti-Omics Integration - Integrate multi-omics: gene expression, protein data, pathway enrichment, and metabolic pathways. Use this skill for multi-omics tasks involving get gene expression across cancers get uniprotkb entry by accession get functional enrichment kegg get. Combines 4 tools from 4 SCP server(s).
- ▌ Nsfc Reviewers 2 · internscience bundle当用户明确要求"评审国自然标书"、"模拟专家评审"、"审阅 NSFC 申请书"时使用。模拟领域专家视角对 NSFC 标书进行多维度评审,输出分级问题与可执行修改建议。⚠️ 不适用:用户只是想写/改标书某个章节(应使用 nsfc-*-writer 系列技能)、只是想了解评审标准(应直接回答)、没有明确"评审/审阅"意图。
- ▌ Nsfc Schematic 2 · internscience bundle当用户明确要求"生成 NSFC 原理图/机制图/schematic diagram/mechanism diagram"或需要把标书中的研究机制、算法架构、模块关系转成"可编辑 + 可嵌入文档"的图示时使用。默认输出可编辑源文件(`.drawio`)与渲染文件(`.pdf`/`.svg`/`.png`);当用户主动提及 Nano Banana/Gemini 图片模型时,可切换为 PNG-only 模式。⚠️ 不适用:用户只是想润色正文文本(应直接改写文本)、只是想改已有图片格式/尺寸(应使用图片处理技能)、没有明确"原理图/机制图"意图。
- ▌ Complete Example 2 · internscience bundle当用户明确要求"填充示例内容""生成示例""补充 LaTeX 示例"时使用。AI 增强版 LaTeX 示例智能生成器,实现 AI 与硬编码的有机融合:AI 做"语义理解"(分析章节主题、推理资源相关性、生成连贯叙述),硬编码做"结构保护"(格式验证、哈希校验、访问控制)。
- ▌ Get Review Theme 2 · internscience bundle当用户明确要求"从文件/图片/网页/描述中提取综述主题"或"生成主题+关键词+核心问题结构化输出"时使用。支持文件(PDF/Word/Markdown/Tex)、文件夹、图片、自然语言描述、网页 URL 等多种输入源,自动识别输入类型并提取内容,生成可直接用于 systematic-literature-review 及其他文献综述技能的结构化输出。
- ▌ Make Latex Model 2 · internscience bundle当用户明确要求"LaTeX 模板优化""样式参数对齐""make_latex_model"时使用。支持任意 LaTeX 模板的样式参数对齐、标题文字对齐、标题格式对比(加粗)、HTML 可视化报告、LaTeX 自动修复建议和像素级 PDF 对比验证。
- ▌ Nsfc Humanization 2 · internscience bundle去除 NSFC 标书中的 AI 机器味,使文本读起来像资深领域专家亲笔撰写(不适用:非标书内容/需修改格式/需补充新内容)
- ▌ Nsfc Ref Alignment 2 · internscience bundle检查 NSFC 标书正文引用与参考文献的一致性与真实性风险(只读):核查 bibkey 是否存在、BibTeX 字段与 DOI 等格式问题,并生成结构化输入供宿主 AI 逐条评估“正文表述是否真的在引用该文献”;默认仅输出审核报告,不直接修改标书或 .bib(除非用户明确要求)。
- ▌
- ▌ Check Review Alignment 2 · internscience bundle当用户明确要求"核查/优化综述 `{主题}_review.tex` 的正文引用"或"运行 check-review-alignment"时使用。通过宿主 AI 的语义理解逐条核查引用是否与文献内容吻合,只在发现致命性引用错误时对"包含引用的句子"做最小化改写,并复用 `systematic-literature-review` 的渲染脚本输出 PDF/Word。核心原则:不为了改而改,无法确定是否为致命性错误时保留原样并在报告中警告。⚠️ 不适用:用户只是想生成系统综述正文(应使用 systematic-literature-review);用户只是想新增/核对 BibTeX 条目(应使用专门的 bib 管理流程)。
- ▌ Nsfc Justification Writer 2 · internscience bundle当用户明确要求"写/改 NSFC 立项依据""立项依据写作/重构"时使用。基于最小信息表输出价值与必要性、现状不足、科学问题/假说与项目切入点,并保持模板结构不被破坏。适用于 NSFC 及各类科研基金申请书的立项依据写作场景。
- ▌ Migrating Latex Templates 2 · internscience bundle当用户明确要求"迁移标书""升级模板""跨版本迁移""旧标书转新模板"时使用。智能迁移NSFC LaTeX标书到新版模板,基于五阶段工作流(分析→映射→规划→执行→验证),自动处理结构变化、内容重组、引用更新;支持AI驱动语义匹配与启发式回退,并提供 runs 输出隔离与一键迁移脚本。
- ▌ Nsfc Research Content Writer 2 · internscience bundle当用户明确要求"写/改研究内容""研究内容+创新+年度计划编排"时使用。为 NSFC 正文"(二)研究内容"写作/重构,并同步编排"特色与创新"和"三年年度研究计划",输出可直接落到 LaTeX 模板的三个 extraTex 文件。
- ▌ Nsfc Research Foundation Writer 2 · internscience bundle当用户明确要求"写/改研究基础""研究基础+工作条件+风险应对编排"时使用。为 NSFC 正文"(三)研究基础"写作/重构,并同步编排"工作条件"和"研究风险应对",用证据链证明项目可行、资源条件对位研究内容、风险预案可执行。
- ▌ Molclaw Admet 2 · internsciencePredict the ADMET (absorption, distribution, metabolism, excretion, and toxicity) properties of the input molecules.
- ▌ Molclaw Dleps 2 · internscienceCalculate disease reversal scores for the provided molecules relative to a specific disease.
- ▌ Molclaw P2rank 2 · internscienceUse P2Rank to locate binding pockets in the input protein. Unless specified by the user, prioritize using fpocket.
- ▌ Molclaw Esmfold 2 · internscienceUse ESMFold model to predict 3D structure of the input protein sequence.
- ▌ Molclaw Fix Pdb 2 · internscienceRepair and clean PDB files with PDBFixer, returning repaired file path and topology counts.
- ▌ Molclaw Fpocket 2 · internscienceUse fpocket to detect binding pockets and output their detailed properties for the input protein. This offers a more concise approach to pocket identification.
- ▌
- ▌ Molclaw Goca Tool 2 · internscienceRun GoCa coarse-grained protein MD pipeline and collect key simulation artifacts from a unified run directory.
- ▌ Molclaw Prolif Md 2 · internscienceProLIF MD trajectory analysis skill for protein-ligand interaction fingerprints with frame slicing and residue controls.
- ▌ Molclaw Hdock Tool 2 · internscienceRun HDOCKlite docking for protein complexes and return run directories with ranked models.
- ▌ Molclaw Prolif Pdb 2 · internscienceProLIF static complex analysis skill for a single protein-ligand structure.
- ▌ Molclaw Run Bioemu 2 · internscienceRun BioEmu sequence sampling and extract ensemble structures for downstream conformation analysis.
- ▌ Molclaw Scp Server 2 · internscienceAll tools utilized within molclaw skills connect via the MCP protocol. This skill serves as a unified guide for using the MCP Server. This skill must be loaded to create the MCP server before invoking any tools.
- ▌ Molclaw Prolif Tool 2 · internscienceUnified ProLIF analysis skill covering MD trajectories, docking poses, single complex structures, and protein-protein interfaces.
- ▌ Molclaw Evobind Tool 2 · internscienceDesign linear or cyclic peptide binders from receptor FASTA sequences using EvoBind2 with structured result outputs.
- ▌ Molclaw Chai1 Predict 2 · internsciencePredict protein structures with Chai-1 from sequence or FASTA input and return model scoring summaries.
- ▌ Molclaw Diffdock Auto 2 · internscienceRun automated DiffDock protein-ligand docking and return confidence-based result summaries.
- ▌ Molclaw Drug Likeness 2 · internscienceCompute the drug-likeness metrics (QED score and Number of violations of Lipinski's Rule of Five) of the input candidate molecules (SMILES format).
- ▌ Molclaw File Transfer 2 · internscienceImplement data transmission between the local computer and the MCP Server using Base64 encoding
- ▌ Molclaw Chroma Toolkit 2 · internscienceChroma toolkit skill covering chroma_monomer for single-chain generation, chroma_complex for multi-chain assembly generation, and chroma_symmetry for symmetry-constrained protein design.
- ▌ Molclaw Equiscore Tool 2 · internscienceUnified EquiScore skill for pocket extraction, pocket scoring, and end-to-end docking-to-score pipeline execution.
- ▌ Molclaw Extract Chains 2 · internscienceExtract protein sequence of each chain from the protein structure file (pdb format).
- ▌ Molclaw Karmadock Tool 2 · internscienceRun KarmaDock graph generation and virtual screening to produce ranked ligand poses and summary metrics.
- ▌ Molclaw Mol Similarity 2 · internscienceCalculate both Tanimoto similarities and the count of shared structural fragments between a target molecule and a list of candidate molecules via Morgan fingerprints.
- ▌ Molclaw Openawsem Tool 2 · internscienceRuns OpenAWSEM simulations and extracts representative trajectory frames for downstream ensemble analysis.
- ▌ Molclaw Prolif Docking 2 · internscienceProLIF docking-pose analysis skill for batch interaction fingerprints and interaction count summaries.
- ▌ Molclaw Protein Openmm 2 · internscienceRun OpenMM protein MD and extract evenly spaced trajectory frames for downstream structural analysis.
- ▌ Molclaw Boltz2 Affinity 2 · internsciencePredict binding affinity between target protein sequence and small molecule SMILES using Boltz-2.
- ▌ Molclaw Denovo Sampling 2 · internscienceGenerate entirely new drug-like molecules from scratch without any starting molecule, using REINVENT4's de novo prior.
- ▌ Molclaw Linker Sampling 2 · internscienceGenerate linker molecules connecting two warhead fragments, for applications such as PROTAC design, bivalent ligands, and fragment merging.
- ▌ Molclaw Pack Sidechains 2 · internsciencePredicts full-atom sidechain conformations from backbone PDBs using AttnPacker for structure preparation workflows.
- ▌ Molclaw Rgroup Sampling 2 · internscienceGenerate new molecules by decorating a scaffold with R-groups at specified attachment points, using LibInvent for scaffold-constrained molecular generation.
- ▌ Molclaw Mol Opt Physchem 2 · internscienceIntegrating molecular property calculation tools with the reasoning capabilities of Large Language Models (LLMs) to optimize key physicochemical properties of drug molecules, such as LogP, QED, and solubility.
- ▌ Molclaw Mol2mol Sampling 2 · internscienceGenerate new molecules by transforming an input molecule using different priors for scaffold-aware, similarity-controlled molecular optimization.
- ▌ Molclaw Peptide Sampling 2 · internscienceGenerate peptide molecules using PepInvent, supporting template-based generation, custom peptide sequence modification, and info queries for available templates and amino acids.
- ▌ Molclaw Proteinmpnn Tool 2 · internscienceDesign or score protein sequences from PDB structures using a ProteinMPNN workflow wrapper.
- ▌ Molclaw Pulchura Rebuild 2 · internscienceRebuilds incomplete protein PDB structures with PULCHRA for downstream docking and simulation preparation.
- ▌
- ▌ Molclaw Compound Retrieve 2 · internscienceRetrieve SMILES strings from PubChem database using compound names.
- ▌ Molclaw Docking Screening 2 · internscienceHigh-level large-scale virtual screening workflow (10+ ligands) combining property filtering, QuickVina docking, EquiScore rescoring, and consensus ranking for target prioritization.
- ▌ Molclaw Equiscore Docking 2 · internscienceEnd-to-end docking-score ranking using EquiScore for candidate molecules against a target protein.
- ▌ Molclaw Mol Basic Metrics 2 · internscienceCompute a set of basic molecular properties for a given list of SMILES strings, returning the molecular formula, exact and average molecular weights, counts of heavy and total atoms, number of bonds, valence electrons, and formal charge for each input molecule.
- ▌ Molclaw Mol Hbond Metrics 2 · internscienceCompute hydrogen bonding-related properties for a list of SMILES strings, specifically determining the number of hydrogen bond donors and acceptors for each input molecule.
- ▌ Molclaw Quickvina Docking 2 · internsciencePerform molecular docking using QuickVina2-GPU between target protein structure and small molecules.
- ▌ Molclaw Mol Charge Metrics 2 · internscienceCompute Gasteiger partial charges and formal charge for a list of SMILES strings, returning the minimum, maximum, average, and range of the Gasteiger charges alongside the formal charge for each molecule.
- ▌
- ▌ Molclaw Fpocket Toolkit Base 2 · internscienceDetect binding pockets with fpocket_toolkit and return parsed pocket descriptors and run artifacts.
- ▌ Molclaw Mol Topology Metrics 2 · internscienceCompute a comprehensive set of topological descriptors for a list of SMILES strings, returning the Topological Polar Surface Area (TPSA), a series of valence and non-valence molecular connectivity indices (Chi0–Chi4), the Hall–Kier alpha value, and Kappa shape indices (Kappa1–Kappa3) for each input molecule.
- ▌
- ▌ Molclaw Mol Structure Metrics 2 · internscienceCompute a set of molecular structure complexity descriptors for a list of SMILES strings, returning detailed metrics for each molecule including the number of rotatable bonds, total/aromatic/aliphatic/saturated rings, heteroatoms, and bridgehead atoms, as well as the fraction of sp³-hybridized carbon atoms (Fsp³).
- ▌ Molclaw Protein Ligand Mmpbsa 2 · internscience bundleExecution-ready protein-ligand MM/GB(PB)SA workflow with explicit MCP handoffs and optional analysis.
- ▌ Molclaw Mol Complexity Metrics 2 · internscienceCompute custom molecular complexity-related descriptors for a given list of SMILES strings, returning the molecular complexity score, aromatic proportion, and asphericity value for each input molecule.
- ▌ Molclaw Prolif Protein Protein 2 · internscienceProLIF protein-protein trajectory analysis skill for interface interaction fingerprints and stability profiling.
- ▌ Molclaw Protein Protein Mmpbsa 2 · internscience bundleExecution-ready protein-protein MM/GB(PB)SA workflow with MCP-exposed tool names, strict file validation, and failure guards.
- ▌ Molclaw Protein Sequence Retrieve 2 · internscienceSearch the target protein sequence information from the input gene name or uniprot id.
- ▌ Molclaw Mol Hydrophobicity Metrics 2 · internscienceComputes hydrophobicity-related molecular descriptors for a given list of SMILES strings, returning the octanol-water partition coefficient (logP) and molar refractivity for each input molecule.
- ▌ Molclaw Protein Structure Retrieve 2 · internscienceRetrieve and download protein structure file (pdb format) using gene name, Uniprot ID or PDB ID.
- ▌
- ▌ Drugsda Linker Sampling 2 · internscienceGenerate new molecules sampling from the input two warhead fragments.
- ▌
- ▌ Drugsda Target Retrieve 2 · internscienceSearch the protein information from the input gene name and downloads the optimal PDB or AlphaFold structures.
- ▌ Enzyme Inhibitor Design 2 · internscienceEnzyme Inhibitor Design - Design enzyme inhibitor: target structure, pocket prediction, compound screening, and ADMET assessment. Use this skill for enzyme pharmacology tasks involving retrieve protein data by pdbcode pred pocket prank quick molecule docking pred molecule admet calculate mol drug chemistry. Combines 5 tools from 2 SCP server(s).
- ▌ Gene Variant Drug Nexus 2 · internscienceGene-Variant-Drug Nexus - Connect gene variants to drugs: variant effect, gene-disease link, drug associations, and clinical evidence. Use this skill for translational genomics tasks involving get vep hgvs get associated targets by disease efoId get associated drugs by target name clinvar search. Combines 4 tools from 3 SCP server(s).
- ▌ Electromagnetic Analysis 2 · internscienceElectromagnetic Field Analysis - Analyze EM fields: vacuum permittivity, total charge, radiation pressure, and photon calculations. Use this skill for electromagnetics tasks involving calculate vacuum permittivity calculate total charge calculate radiation pressure calculate total power. Combines 4 tools from 2 SCP server(s).
- ▌ Metabolomics Pathway 2 · internscienceMetabolomics Pathway Analysis - Analyze metabolomics: compound identification, KEGG pathway mapping, enzyme links, and PubChem data. Use this skill for metabolomics tasks involving search pubchem by name kegg find kegg link kegg get. Combines 4 tools from 2 SCP server(s).
- ▌ Protein Blast Search 2 · internscienceSearch for similar protein sequences in UniProt Swiss-Prot database using BLAST to identify homologous proteins and functional relationships.
- ▌ Aliphatic Ring Analysis 2 · internscienceRing System Analysis - Analyze ring systems: count aliphatic carbocycles, analyze aromaticity, compute topology, and structure complexity. Use this skill for organic chemistry tasks involving GetAliphaticCarbocyclesNum AromaticityAnalyzer calculate mol topology calculate mol structure complexity. Combines 4 tools from 3 SCP server(s).
- ▌ Compound Name Retrieval 2 · internscienceRetrieve SMILES strings from PubChem database using compound names to obtain molecular structures from common chemical names.
- ▌ Gene Disease Association 2 · internscienceGene-Disease Association Analysis - Analyze gene-disease associations: NCBI gene metadata, OpenTargets disease associations, TCGA expression, and Monarch phenotypes. Use this skill for medical genetics tasks involving get gene metadata by gene name get associated targets by disease efoId get gene expression across cancers get joint associated diseases by HPO ID list. Combines 4 tools from 4 SCP server(s).
- ▌ Tissue Specific Analysis 2 · internscienceTissue-Specific Expression Analysis - Analyze tissue-specific expression: ChEMBL tissue data, TCGA cancer expression, Ensembl gene info, and NCBI gene data. Use this skill for tissue biology tasks involving get tissue by id get gene expression across cancers get lookup symbol get gene metadata by gene name. Combines 4 tools from 4 SCP server(s).
- ▌ Drug Interaction Checker 2 · internscienceDrug-Drug Interaction Checker - Check interactions between multiple drugs using FDA interaction data, PubChem compound info, and ChEMBL target overlap analysis. Use this skill for clinical pharmacology tasks involving get drug interactions by drug name get compound by name get target by name. Combines 3 tools from 3 SCP server(s).
- ▌