PKU-YuanGroup/OpenAI4S

volcengine-datapro

Discover and call the configured Volcengine DataPro dataPro_search(query:string) MCP tool for professional-dataset queries.

admet-genetic

ADMET-guided genetic molecule optimization workflow from seed SMILES; use when the agent needs to build or run an RDKit/SA-Score/ADMET-AI GA pipeline for molecule optimization, enforce molecule lineage logs, render optimization-history HTML dashboards, and…

alphafold2

Predict protein structure for monomers and multimers with AlphaFold2 via the ColabFold runner (Mirdita et al. 2022, github.com/sokrypton/ColabFold; AlphaFold2 Jumper et al. 2021). Reach for this skill to fold a sequence or complex with the AF2/AF2-Multimer…

audit-dataset

Audit tabular datasets before analysis or training for schema drift, missing values, duplicate rows or IDs, target imbalance, and entity or group leakage across splits using pure-stdlib helpers.

bioprobench

Score an LLM's biological-protocol reasoning on the BioProBench benchmark: protocol QA, step ordering, error detection, protocol generation, and LLM-judged error reasoning; or generate the responses.

boltz

Structure prediction for protein, nucleic-acid, and small-molecule complexes with Boltz-2 (Passaro & Wohlwend et al. 2025, github.com/jwohlwend/boltz). Reach for this skill to validate designed binders against a target, to co-fold a protein with a SMILES or…

borzoi

Predict genome-wide functional tracks (RNA-seq, CAGE, DNase, ChIP) from DNA sequence with Borzoi. Use this skill when: (1) Scoring the regulatory effect of a variant on expression/accessibility, (2) Generating predicted coverage tracks for a locus, (3)…

catalyst-sar-screening

HARD-LOCKED Catalyst-Design-Agent FAIRChem UMA (uma-s-1p1, oc20) SAC SAR screening for dissolution potential / adsorption / overpotential. Always call run_pipeline with the user's metals/metrics into a fresh workdir and present ONLY that run's…

chai1

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…

diffdock

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…

esmfold2

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…

evaluate-model

Evaluate binary classification or regression models with confusion-matrix metrics, tie-aware ROC AUC, regression errors, and deterministic bootstrap confidence intervals; emphasizes held-out data, uncertainty, baselines, and subgroup checks.

evidence-walkthrough

Run the reference end-to-end research pass — fixed database query, local analysis, versioned artifacts with lineage, then an exported evidence package that verifies in a clean environment. Use as the first-run demonstration, as a benchmark case, or when a…

evo2

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…

example-stats

descriptive-statistics helpers — summary (mean/std/median), quantile, zscore normalization, and Pearson correlation on plain Python number lists (no pandas/numpy).

fair-esm2

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.

figure-composer

Compose one publication-grade multi-panel figure. Entry from a one-line claim + data refs, OR from an existing figure via `derive_outline(png)`. Runs a per-figure loop: outline (12-col grid, per-panel ask + label_budget) → fan-out one sub-agent per panel…

figure-style

Publication-grade figure correctness and legibility rules. Load before drawing any plot and call `apply_figure_style()` — sets a role-mapped font-size ladder, outward ticks, frameless legends, and 300-dpi output. The skill is a checklist, not a house look:…

indication-dossier

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

ligandmpnn

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…

literature-review

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…

mineral-spectra-analysis

Raman mineral mixture spectra analysis pipeline for unknown mixed-mineral spectra; preprocess noisy spectra once, iteratively match residual peaks against a reference spectral library, unmix components with NNLS, diagnose reliability, write reports, and…

openfold3

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.

paper-narrative

Judge and reshape the STORY a paper's figures tell. Input is the work itself — manuscript (or abstract) + figure deck — no hand-written brief. `derive_paper_brief(abstract, captions)` extracts pitch/vision/per-figure-claims; a handling-editor reviewer on the…

pdf-explore

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…

plan-ml-experiment

Plan reproducible machine-learning experiments with leakage-safe random, grouped, or chronological splits; deterministic configuration fingerprints; dataset checksums; seeds, baselines, ablations, and artifact manifests.

protein-design-mcp

Compose auditable protein-design operations through the configured OpenAI4S protein-design MCP connector: target-conditioned RFdiffusion backbone generation, constrained ProteinMPNN sequence design, monomer or complex structure prediction, Rosetta scoring and…

protein-mutation-enhancement

Deterministic protein gain-of-function mutation workflow: build single, double, and higher-order mutant libraries; merge ESM sequence-effect scores, structure metrics from ESMFold-class models, property/function scores; rank candidates; and decide whether to…

proteinmpnn

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…

reaction-atom-mapping

Map atoms and changed bonds for a complete reaction with RXNMapper. Use for reactant/product correspondence and reaction-centre audits, not target-only retrosynthesis or feasibility.

reaction-condition-recommendation

Recommend ranked catalyst, reagent, and solvent labels for a fully specified reaction using the reviewed Parrot USPTO checkpoint. Not for unknown reactions or lab procedures.

reaction-forward-prediction

Predict ranked products from reactants and reagents with ReactionT5v2-forward; use for outcome prediction or round-trip recovery. Product rank is not reaction feasibility.

reaction-yield-estimation

Estimate yield for a fully specified reactant/reagent/product record with ReactionT5v2-yield. Use for in-domain screening, not route success; flag domain shift and uncalibrated uncertainty.

remote-compute-nvidia

Run GPU jobs on NVIDIA NIM microservices via host.compute.create('byoc:nvidia', ...). Covers both forms — self_hosted (an nvcr.io NIM container on a local GPU with --gpus all) and hosted (the fully-managed integrate.api.nvidia.com gateway, no local GPU) —…

remote-compute-ssh

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

retrosynthesis-planning

Search multi-step retrosynthesis routes from a target to stock with AiZynthFinder, then audit and rank route trees. Use for recursive planning, not mapping, forward prediction, conditions, or yield.

rfdiffusion

Generate de novo protein backbones with RFdiffusion for protein-target binders, hotspot-conditioned interfaces, motif scaffolding, partial diffusion, or symmetric assemblies. Use this skill when a design workflow needs reproducible RFdiffusion contigs,…

scgpt

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)…

scvi-tools

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,…

single-cell-rna-analysis

Reproducible Scanpy workflow for human or mouse 10x scRNA-seq and snRNA-seq count matrices: single-sample descriptive QC, clustering and annotation, or comparative donor-aware pseudobulk DE and Milo DA; plus preflight validation, optional explicitly requested…