Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add PKU-YuanGroup/OpenAI4S --skill bio-chemoinformatics-conformer-generationgit clone --depth 1 https://github.com/PKU-YuanGroup/OpenAI4SWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pku-yuangroup/openai4s/bio-chemoinformatics-conformer-generation)<a href="https://agentmods.dev/skills/pku-yuangroup/openai4s/bio-chemoinformatics-conformer-generation"><img src="https://agentmods.dev/badge/skills/pku-yuangroup/openai4s/bio-chemoinformatics-conformer-generation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pku-yuangroup/openai4s/bio-chemoinformatics-conformer-generation"><img src="https://agentmods.dev/badge/skills/pku-yuangroup/openai4s/bio-chemoinformatics-conformer-generation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00119 | $0.05319 |
| Opus 5 | $0.00060 | $0.02660 |
| Sonnet 5 | $0.00024 | $0.01064 |
| Haiku 4.5 | $0.00012 | $0.00532 |
Grade A, and why
bio-conformer-generation scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
subprocess.run(['crest', input_path.name, '--gfn2', '-T', '12'], This is a copy
95% identical to bio-conformer-generation — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Version Compatibility
Reference examples tested with: RDKit 2024.09+, xtb 6.7+, CREST 3.0+, OpenMM 8.1+ for follow-up MD.
Before using code patterns, verify installed versions match. If versions differ:
- Python:
pip show <package>thenhelp(module.function)to check signatures - CLI:
xtb --version;crest --version
If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying.
Conformer Generation
Generate 3D conformer ensembles for molecules from 2D structures. The choice of method depends on molecule size, flexibility, and downstream use: ETKDG (Riniker & Landrum 2015) and its ETKDGv3 macrocycle update (Wang et al. 2020) are modern defaults for drug-like molecules, MMFF94/UFF provide fast energy minimization, and CREST + GFN2-xTB provide higher-cost semi-empirical sampling. A single conformer may be insufficient when the downstream result is conformation-sensitive; determine ensemble size by convergence of the downstream descriptor, alignment, or docking result.
For docking pose validation, see chemoinformatics/pose-validation. For free-energy methods (which require ensemble sampling), see chemoinformatics/free-energy-calculations.
Conformer Method Taxonomy
| Method | Cost / mol | Quality | Use case | Fails when |
|---|---|---|---|---|
| ETKDGv3 + MMFF94 | Benchmark on actual molecules/hardware | Useful for many drug-like organics | Initial docking/descriptors | Difficult macrocycles, peptides, unsupported chemistry |
| ETKDGv3 + UFF | Fast | Different parameter coverage from MMFF94 | Fallback only after checking UFF parameters | Unsupported atom types; coordination chemistry |
| Omega (OpenEye) | Benchmark licensed workflow | Commercial conformer generator | Commercial pipelines | License cost and configured limits |
| Confab (Open Babel) | Benchmark on intended chemistry | Systematic torsion search | Alternative enumeration | Combinatorial growth and force-field dependence |
| RDKit ETKDGv3 + macrocycle preferences | Molecule-dependent | Macrocycle-aware embedding | Macrocyclic starting ensembles | Coverage remains molecule-dependent |
| CREST + GFN2-xTB | Molecule/settings-dependent | Semiempirical conformational sampling | Difficult flexible molecules | Computational cost; special chemistry |
| CREST + GFN-FF | Lower cost than GFN2-xTB | Force-field-level sampling | Exploratory sampling | Validate coverage and ordering for the chemistry |
| GeoMol (Ganea 2021) | Hardware/model-dependent | Learned conformer generation | Large-library research workflow | Training distribution and released-model coverage |
| TorsionNet (Gogineni 2020) | Hardware/model-dependent | Learned torsional search | Research workflow | Training distribution and implementation availability |
| MD sampling (OpenMM) | System/protocol-dependent | Dynamic sampling | Free energy, induced fit | Computational cost and convergence |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 405 lines · 119 tokens per session scan A 51a37945250a
bio-conformer-generation is a skill published in the GitHub repository PKU-YuanGroup/OpenAI4S (403 stars, last pushed yesterday), licensed MIT. It adds 119 tokens to every session and 5,319 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). It is 95% identical to bio-conformer-generation, differing in 12 lines, and is treated as a copy.
Other skills, from other repositories
boltz-structure-prediction
Boltz-1 / Boltz-2 structure prediction for proteins, complexes, and ligand-aware validation. Use this skill when: (1) Predicting protein complex structures, (2) Validating designed binders, (3) Need open-source alternative to AF2, (4) Predicting protein-ligand complexes, (5) Using local GPU resources. For QC…
imaging-data-commons
Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.
flow-cytometry-analysis
Complete flow cytometry analysis pipeline. FCS file handling, compensation, manual/automated gating, immunophenotyping, CFSE proliferation analysis, cell cycle analysis (Dean-Jett-Fox), and apoptosis assays. Extends flowio with analytical workflows. For raw FCS parsing only use flowio.
scientific-critical-thinking
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review…
glycobiology
Glycosylation site prediction and glycobiology analysis. N-glycosylation motif finding, O-glycosylation hotspot prediction, glycan structure resources. Lightweight, pure Python. For protein function queries use uniprot-database; for structure analysis use alphafold-database.
cellxgene-census
Query the CELLxGENE Census (61M+ cells) programmatically. Use when you need expression data across tissues, diseases, or cell types from the largest curated single-cell atlas. Best for population-scale queries, reference atlas comparisons. For analyzing your own data use scanpy or scvi-tools.