Skill collection
PKU-YuanGroup/OpenAI4S agent skills
- skills
- 17
- GitHub stars
- 620
GitHub description: “Open-source AI agent for scientific research. Analyze data in Python/R with Claude, GPT, Gemini, and more.”
- Stars
- 620 (73 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Jul 2026
- Homepage
- arxiv.org/abs/2609.15096
- agent
- ai4science
- claude-science
- mit-license
- open-source
- science-research
Install all skills
npx skills add PKU-YuanGroup/OpenAI4SAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in PKU-YuanGroup/OpenAI4S, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 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… | PKU-YuanGroup/ | 620 | — | ~1.3k | Automated safety check: Pass | MIT | today |
| 2 | 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. | PKU-YuanGroup/ | 620 | — | ~2.3k | Automated safety check: Pass | MIT | today |
| 3 | Map atoms and changed bonds for a complete reaction with RXNMapper. | PKU-YuanGroup/ | 620 | — | ~1.2k | Automated safety check: Pass | MIT | today |
| 4 | Predict ranked products from reactants and reagents with ReactionT5v2-forward; use for outcome prediction or round-trip recovery. | PKU-YuanGroup/ | 620 | — | ~2k | Automated safety check: Pass | MIT | today |
| 5 | Estimate yield for a fully specified reactant/reagent/product record with ReactionT5v2-yield. | PKU-YuanGroup/ | 620 | — | ~2.3k | Automated safety check: Pass | MIT | today |
| 6 | Generate de novo protein backbones with RFdiffusion for protein-target binders, hotspot-conditioned interfaces, motif scaffolding, partial diffusion, or symmetric assemblies. | PKU-YuanGroup/ | 620 | — | ~2.2k | Automated safety check: Pass | MIT | today |
| 7 | Generate ranked one-step precursor sets for a product with RetroChimera; use for disconnection ideas or expansion-policy calls. | PKU-YuanGroup/ | 620 | — | ~1.8k | Automated safety check: Pass | MIT | today |
| 8 | 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. | PKU-YuanGroup/ | 620 | — | ~637 | Automated safety check: Pass | MIT | today |
| 9 | 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… | PKU-YuanGroup/ | 620 | — | ~583 | Automated safety check: Pass | MIT | today |
| 10 | 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. | PKU-YuanGroup/ | 620 | — | ~1.7k | Automated safety check: Pass | MIT | today |
| 11 | Plan reproducible machine-learning experiments with leakage-safe random, grouped, or chronological splits; deterministic configuration fingerprints; dataset checksums; seeds, baselines, ablations… | PKU-YuanGroup/ | 620 | — | ~634 | Automated safety check: Pass | MIT | today |
| 12 | Compose auditable protein-design operations through the configured OpenAI4S protein-design MCP connector: target-conditioned RFdiffusion backbone generation, constrained ProteinMPNN sequence design… | PKU-YuanGroup/ | 620 | — | ~2.3k | Automated safety check: Pass | MIT | today |
| 13 | 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… | PKU-YuanGroup/ | 620 | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 14 | Recommend ranked catalyst, reagent, and solvent labels for a fully specified reaction using the reviewed Parrot USPTO checkpoint. | PKU-YuanGroup/ | 620 | — | ~2k | Automated safety check: Pass | MIT | today |
| 15 | Run GPU jobs on NVIDIA NIM microservices via host.compute.create('byoc:nvidia', ...). | PKU-YuanGroup/ | 620 | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | today |
| 16 | Turn free-text rows into calibrated numeric features with TypeSafe Jev, then model them on a leakage-safe development split. | PKU-YuanGroup/ | 620 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |
| 17 | Discover and call the configured Volcengine DataPro dataProsearch(query:string) MCP tool for professional-dataset queries. | PKU-YuanGroup/ | 620 | — | ~693 | Automated safety check: Pass | MIT | today |
Questions, answered from the data.
What is the best skill in PKU-YuanGroup/OpenAI4S?
Single Cell Rna Analysis from PKU-YuanGroup/OpenAI4S ranks first of the 17 skills in PKU-YuanGroup/OpenAI4S listed here, with the highest score: its repository has 620 GitHub stars, its SKILL.md loads about 1.3k tokens and it passes the automated safety check with no findings. Next come Bioprobench and Reaction Atom Mapping.
Are the skills in PKU-YuanGroup/OpenAI4S official?
None yet. All 17 skills in PKU-YuanGroup/OpenAI4S listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from PKU-YuanGroup/OpenAI4S?
Run npx skills add PKU-YuanGroup/OpenAI4S in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.