UnicomAI

63 mods across 3 repositories, 2.6k stars between them.

chai1

25

UnicomAI/wanwu

Skill Claude CodeCodex

Structure prediction for protein, nucleic-acid, and small-molecule complexes with the Chai-1 foundation model (Chai Discovery 2024, github.com/chaidiscovery/chai-lab). Reach for this skill to predict an antibody-antigen or protein-ligand complex from a single FASTA, to re-fold designed binders as an AlphaFold-multimer…

2.5k 1mo ago A 98 tokens copy · 100% Apache-2.0

compute-env-setup

26

UnicomAI/wanwu

Skill Claude CodeCodex

Set up a compute environment on a remote provider so Claude Science jobs can run there. Covers direct SSH/conda hosts, Slurm clusters, container-via-bridge runners, and managed-API providers (Modal, GCP, RunPod). Use when standing up a new provider, porting an env to a different backend, adding a tool that needs its…

2.5k 1mo ago A 134 tokens original Apache-2.0

customize

27

UnicomAI/wanwu

Skill Claude CodeCodex

Create, configure, and maintain custom agent profiles and author new skills via the repl tool. Use when the user wants to create an agent profile, build a custom agent, modify agent capabilities, attach or detach skills/connectors on a profile, author a skill, or inspect which connectors and tools are available. Also…

2.5k 1mo ago A 88 tokens original Apache-2.0

diffdock

28

UnicomAI/wanwu

Skill Claude CodeCodex

Predict small-molecule binding poses with DiffDock-L (Corso et al. 2023/2024, github.com/gcorso/DiffDock) — blind diffusion docking that places a ligand into a protein pocket without a predefined search box and ranks the samples with a learned confidence model. Reach for this skill to dock a SMILES or SDF against a…

2.5k 1mo ago A 111 tokens copy · 100% Apache-2.0

esmfold2

29

UnicomAI/wanwu

Skill Claude CodeCodex

Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al. 2026, github.com/Biohub/esm). Single-sequence and MSA modes; protein, DNA, RNA, ligand (CCD/SMILES), modified residues. FoldBench Ab-Ag 50-55%, PPI 70-77% DockQ-pass. Also covers the ESMC-{300M,600M,6B} protein language models from the same release…

2.5k 1mo ago A 223 tokens copy · 100% Apache-2.0

evo2

30

UnicomAI/wanwu

Skill Claude CodeCodex

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…

2.5k 1mo ago A 83 tokens copy · 98% Apache-2.0

fair-esm2

31

UnicomAI/wanwu

Skill Claude CodeCodex

Embed proteins with Meta AI's ESM-2 (fair-esm package). Use this skill when: (1) Extracting per-residue or per-sequence embeddings for downstream ML, (2) Masked-LM likelihood / mutation effect scoring, (3) Contact prediction from a sequence.

2.5k 1mo ago A 66 tokens copy · 86% Apache-2.0

figure-composer

32

UnicomAI/wanwu

Skill Claude CodeCodex

Compose one publication-grade multi-panel figure. Entry from a one-line claim + data files, OR from an existing figure via deriveoutlineprompt (you read the PNG). Runs a per-figure loop: outline (12-col grid, per-panel ask + labelbudget) → render each panel with paneltask (loading figure-style), one at a time or…

2.5k 1mo ago A 169 tokens original Apache-2.0

figure-style

33

UnicomAI/wanwu

Skill Claude CodeCodex

Publication-grade figure correctness and legibility rules. Load before drawing any plot and call applyfigurestyle() — sets a role-mapped font-size ladder, outward ticks, frameless legends, and 300-dpi output. The skill is a checklist, not a house look: data fidelity (claim-titles tested against every row, excluded…

2.5k 1mo ago A 167 tokens copy · 83% Apache-2.0

indication-dossier

34

UnicomAI/wanwu

Skill Claude CodeCodex

Generate a therapeutic indication dossier. Covers the patient population, epidemiology, disease biology, standard of care, regulatory precedent, and landmark clinical trials.

2.5k 1mo ago A 34 tokens copy · 100% Apache-2.0

learn

35

UnicomAI/wanwu

Skill Claude CodeCodex

Use this skill when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's judgment. Trigger for: Explicit learning requests: teach, explain, ELI5, walk me through, quiz me, flashcards, "I'm rusty on"; definitions ("what is X") Terse concept…

2.5k 1mo ago A 219 tokens original Apache-2.0

ligandmpnn

36

UnicomAI/wanwu

Skill Claude CodeCodex

Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be…

2.5k 1mo ago A 100 tokens copy · 100% Apache-2.0

literature-review

37

UnicomAI/wanwu

Skill Claude CodeCodex

Find, verify, and synthesize scientific literature — from "what's the seminal paper for X" through full multi-source reviews. Covers grounding claims in real retrieved sources, avoiding fabricated citations, handling retractions, and calibrating confidence to evidence strength.

2.5k 1mo ago A 54 tokens copy · 100% Apache-2.0

UnicomAI/wanwu

Skill Claude CodeCodex

Register a model service in the managed family — a local model server container the daemon starts/stops on demand, or a remote upstream model API (https). Read the runbook, allocate a port (local only), compose idempotent start/stop scripts (local only), register once. Load when the user wants a model service…

2.5k 1mo ago B 83 tokens original Apache-2.0

openfold3

39

UnicomAI/wanwu

Skill Claude CodeCodex

Structure prediction using OpenFold3, an open-weights PyTorch reproduction of AlphaFold3 from the AlQuraishi Lab. Use this skill when predicting protein/nucleic-acid/ligand complex structures with an Apache-2.0-licensed AF3 reimplementation.

2.5k 1mo ago A 60 tokens copy · 100% Apache-2.0

paper-narrative

40

UnicomAI/wanwu

Skill Claude CodeCodex

Judge and reshape the STORY a paper's figures tell. Input is the work itself — manuscript (or abstract) + figure deck — no hand-written brief. paperbriefprompt(abstract, captions) hands you the prompt to write the brief yourself (pitch/vision/per-figure-claims); then you play a handling editor over the full deck and…

2.5k 1mo ago A 155 tokens original Apache-2.0

pdf-explore

41

UnicomAI/wanwu

Skill Claude CodeCodex

Use this skill when the user has attached a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section, compare sections, find where a topic is discussed, read a value or label off a figure or chart, or find/list/extract every instance…

2.5k 1mo ago A 192 tokens original Apache-2.0

UnicomAI/wanwu

Skill Claude CodeCodex

Stop and consult this skill whenever your response would include specific facts about Anthropic's products. Covers: Claude Code (how to install, Node.js requirements, platform/OS support, MCP server integration, configuration), Claude API (function calling/tool use, batch processing, SDK usage, rate limits, pricing…

2.5k 1mo ago A 138 tokens original Apache-2.0

proteinmpnn

43

UnicomAI/wanwu

Skill Claude CodeCodex

Inverse-fold a protein backbone (PDB structure) into amino-acid sequence with ProteinMPNN (Dauparas et al. 2022, github.com/dauparas/ProteinMPNN). Reach for this skill to run sequence design on RFdiffusion backbones, to redesign one chain of a PDB while holding interface residues fixed, or to generate a…

2.5k 1mo ago A 88 tokens copy · 100% Apache-2.0

UnicomAI/wanwu

Skill Claude CodeCodex

Run GPU jobs on the user's own Modal account via host.compute.create('byoc:modal', ...). Covers the create→submit→waitfornotification flow, the computeprovider kernel for env setup, image/volume resolution, and the two approval cards. Load once you've decided to dispatch to Modal.

2.5k 1mo ago A 65 tokens original Apache-2.0

remote-compute-ssh

45

UnicomAI/wanwu

Skill Claude CodeCodex

Submit→waitfornotification→harvest workflow for the user's SSH/SLURM hosts. Load once you've decided to dispatch remote.

2.5k 1mo ago C 33 tokens original Apache-2.0

scgpt

46

UnicomAI/wanwu

Skill Claude CodeCodex

Embed and annotate single-cell expression data with scGPT, a foundation model for single-cell biology. Use this skill when: (1) Producing cell embeddings from an AnnData for clustering/integration, (2) Zero-shot or fine-tuned cell-type annotation, (3) Gene-level representation for perturbation/GRN tasks. For…

2.5k 1mo ago A 89 tokens copy · 100% Apache-2.0

scvi-tools

47

UnicomAI/wanwu

Skill Claude CodeCodex

Probabilistic single-cell RNA-seq with scvi-tools — scVI for a batch-corrected latent space, scANVI for semi-supervised label transfer, and Bayesian differential expression. Reach for this skill to integrate scRNA-seq batches, embed cells for clustering, transfer annotations from a reference onto a query, or score…

2.5k 1mo ago A 100 tokens copy · 100% Apache-2.0

self-awareness

48

UnicomAI/wanwu

Skill Claude CodeCodex

Claude Science's own session database schema and SDK surface for introspection via host.query(). Load this when you need to query your own conversation history, token usage, cost accounting, execution log, or artifact metadata beyond what host.frames()/host.artifacts() provide — e.g. "how many tokens has this session…

2.5k 1mo ago A 121 tokens original Apache-2.0