Skill collection

xuzhougeng/wisp-science

43 agent skills across 10 categories, read straight from the repository tree.

Zhougeng Xu584★ across the radarProfile →
43
Skills published
10
Categories
7
Ship scripts
895
Stars on the repo
Tracked on the radar · 895★ · +311 this weekRepository facts and velocity →
AI & Agents · 11
All in category →
scvi-toolsProbabilistic single-cell RNA-seq with scvi-tools — scVI for a batch-corrected latent space, scANVI for…scriptsesmfold2Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm).…diffdockPredict small-molecule binding poses with DiffDock-L (Corso et al. 2023/2024, github.com/gcorso/DiffDock) —…openfold3Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi…solublempnnInverse-fold a backbone with SolubleMPNN — ProteinMPNN retrained on a soluble-PDB subset (Dauparas et al.…remote-compute-sshSubmit recoverable SSH-direct research Runs with live progress cards and model-free monitoring.evo2Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill…boltzStructure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend…chai1Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model…
customizefair-esm2
Backend & API · 5
All in category →
probe-compute-environmentInspect a registered execution server before compute planning and interpret its persisted capability profile.…managed-model-endpointsExplain Wisp's current managed-model endpoint boundary and plan a safe integration. Use when the user asks to…product-self-knowledgeStop and consult this skill whenever your response would include specific facts about Anthropic's products.…using-model-endpointInvoke an already configured model endpoint from a supported Wisp execution context and capture the bounded…alphafold2Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al.…
Workflow & Productivity · 4
All in category →
skill-creatorCreate, update, validate, and evaluate Wisp skills. Use when authoring a project-local or installable skill…scriptsbear-map给一个概念，从真实检索到的论文摘要里挖出它的邻近概念，画出以该概念为中心的知识地图——每个节点都锚定真实文献，不从记忆里补节点。同时输出 Mermaid 概念图（可在 Claude Code / GitHub /…remote-compute-modalExplain Wisp's current Modal boundary and migrate a requested Modal workload to a supported direct SSH Run…self-awarenessWisp-science's actual agent tool surface and runtime boundaries. Load this when deciding which Wisp tool can…
Design & Presentation · 4
All in category →
paper-narrativeJudge and reshape the story told by a manuscript and its figure deck. Use when revising paper structure…scriptsproteinmpnnInverse-fold a protein backbone (PDB structure) into amino-acid sequence with ProteinMPNN (Dauparas et al.…journal-club-pptUse this skill whenever the user provides a scientific paper PDF and asks for a group-meeting literature…ligandmpnnInverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023…
Data & Analytics · 3
All in category →
figure-composerCompose or improve a publication-grade multi-panel scientific figure from a claim, concrete data paths, or an…scriptsscgptEmbed and annotate single-cell expression data with scGPT, a foundation model for single-cell biology. Use…browser-useUse this skill to drive the user's real, persistent Chrome/Chromium session — open pages, read them, click…
Testing & QA · 3
All in category →
figure-stylePublication-grade figure correctness and legibility rules. Load before drawing any plot and call…scriptscompute-env-setupSet up and validate a reproducible Python or R environment on a Wisp execution context. Use for a selected…borzoiPredict genome-wide functional tracks (RNA-seq, CAGE, DNase, ChIP) from DNA sequence with Borzoi. Use this…
Code Review & Quality · 2
All in category →
literature-reviewFind, verify, and synthesize scientific literature — from "what's the seminal paper for X" through full…scriptsbear-review给一个观点，同时检索支持它的文献和反对它的文献，在一份综合报告里呈现正反两侧的证据格局——支持侧最强证据是什么、反对侧最危险的挑战是什么、哪些角度有支持但无反对、哪些角度有反对但无支持。底层走真实检索（scimaster…
Databases · 2
All in category →
agent-infiniUse the InfiniSynapse CLI (`agent_infini`) for multi-turn AI data-analysis tasks, database/RAG context, and…analysis-workflowOrganize multi-step scientific analyses into reproducible, self-contained modules. Use for workflows such as…
Content & Marketing · 1
All in category →
pdf-exploreUse this skill when the user has attached a PDF, paper, report, or other document and the answer needs its…scripts
Other · 8
indication-dossierGenerate a therapeutic indication dossier. Covers the patient population, epidemiology, disease biology…bear-support给一句话或一段话，找出真实学术文献来支持它，每篇文献附一行"它如何支撑这个观点"的说明。底层走真实检索（scimaster-cli），绝不从记忆编造引用——搜不到就如实说搜不到。…bear-trace给一个主题或一篇种子论文，向前挖掘它建立在哪些前驱工作上（逐层回溯），再向后补充最新进展，讲清楚这个问题从源头到现在是怎么演化的。底层走真实检索（scimaster-cli），每个节点都锚定真实检索到的论文。…bear-counter给一句话或一段话，找出真实学术文献来反对它——相反结论、边界条件、替代解释、方法批评、复制失败。按威胁程度排序，每篇附一行"它如何威胁这个观点"和"怎么回应它"。底层走真实检索（scimaster-cli），绝不编造反例…bear-onboard给一个概念或领域，同时画出它的概念版图（空间：现在这个领域长什么样）和演化脉络（时间：这个领域是怎么走到今天的），在一份综合报告里帮你快速建立对一个陌生领域的立体认知。底层走真实检索（scimaster-cli），绝不编…bear-propose给一个研究 idea，依次执行撞车检测、安静区支撑检索、潜在挑战检索，在一份综合报告里呈现这个 idea…bear-scoop在你投入一个研究方向之前，先看看有谁已经在做同样的事。把 idea 拆成多个不同角度分别去检索，返回一张"邻近程度地图"，重点标出最危险的撞车候选。底层走真实检索（scimaster-cli），不做主观新颖性判断。…local-env-setupConfigure the local wisp-science runtime — uv/Python bootstrap, Node+scimaster-cli for bear-* literature…
About this collection
How many skills does xuzhougeng/wisp-science publish?

43 that pass our gate — each has a real description and a SKILL.md we could read.

How do I install one?

Every skill page carries its own command — `npx skills add xuzhougeng/wisp-science --skill <name> --agent claude-code`. Swap the agent for codex, cursor or copilot.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these collections come from.
More from xuzhougeng →
Everything this maker publishes.