Scientific Agent Skills is a collection of reusable procedures that give AI agents capabilities for scientific research across areas such as biology, chemistry, medicine, and drug discovery. It is used by researchers and by people building AI scientist workflows with compatible coding agents. The catalogue contains many of the project's skills and supporting instructions.
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 K-Dense-AI/scientific-agent-skills --skill cobrapygit clone --depth 1 https://github.com/K-Dense-AI/scientific-agent-skillsWrote 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/k-dense-ai/scientific-agent-skills/cobrapy)<a href="https://agentmods.dev/skills/k-dense-ai/scientific-agent-skills/cobrapy"><img src="https://agentmods.dev/badge/skills/k-dense-ai/scientific-agent-skills/cobrapy/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/k-dense-ai/scientific-agent-skills/cobrapy"><img src="https://agentmods.dev/badge/skills/k-dense-ai/scientific-agent-skills/cobrapy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00055 | $0.02735 |
| Opus 5.5 | $0.00022 | $0.01094 |
| Sonnet 5.5 | $0.00011 | $0.00547 |
| Haiku 4.5 | $0.00006 | $0.00274 |
Grade A, and why
cobrapy scanned grade A with 0 findings 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 14d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
COBRApy - Constraint-Based Reconstruction and Analysis
When to use
Use for loading/building metabolic networks, optimizing their steady-state fluxes, knockout screens, medium design, feasible-space sampling, and gap-filling hypotheses. FBA is a constraint-based prediction; it does not infer kinetic rates or establish experimental growth, thermodynamic feasibility, or flux identifiability.
Setup and reproducibility
Targets cobra 0.32.1 (import cobra), checked against its released source and
current documentation.
uv pip install "cobra==0.32.1"
# Optional SciPy support for MATLAB I/O and array operations:
uv pip install "cobra[array]==0.32.1"
Plotting examples additionally require matplotlib, pandas, and seaborn. The
cobra[chrr] extra supplies hopsy for the new CHRR sampler; that optional backend
was documentation-reviewed, not executed in this refresh. In 0.32.1, sample()
defaults to method="auto" (CHRR when hopsy is installed, otherwise OptGP).
Choose the method explicitly to avoid environment-dependent changes.
Record model source/version/checksum, cobra and solver versions, objective,
medium, bounds, tolerances, and any random seed with each analysis. GLPK handles
the examples below; inspect cobra.util.solver.solvers before choosing an
optional solver. Use "hybrid" for its HiGHS/OSQP interface when installed;
the legacy "osqp" alias is deprecated. QP methods require a suitable backend.
Start with processes=1; scripts using multiprocessing need a guarded entry point.
Workflow
1. Load, inspect, and validate a model
from cobra.io import load_model
# These names are bundled: textbook, iJO1366, salmonella.
model = load_model("textbook") # model.id is e_coli_core; 95 reactions
model.solver = "glpk"
print(model.id, len(model.reactions), len(model.metabolites), len(model.genes))
print(model.reactions.get_by_id("PFK").reaction)
print(model.reactions.PFK.gene_reaction_rule)
print(model.medium)
solution = model.optimize(raise_error=True)
assert solution.status == "optimal"
print(solution.objective_value, solution.fluxes["PFK"])
# error_value=None raises on a failed solve; the default instead returns NaN.
baseline = model.slim_optimize(error_value=None)
assert baseline > 0
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.
- 14d ago Changed · -238 lines · +17 tokens per session b11365507e18
- 15d ago Changed · +1 lines 4ea6f62cd123
- 1mo ago Changed · -34 lines dae7cdddfa3c
- 1mo ago Changed · +16 lines 1035a644835d
- 1mo ago First seen · 497 lines · 38 tokens per session scan A bb99605b1a4e
cobrapy is a skill published in the GitHub repository K-Dense-AI/scientific-agent-skills (50,453 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 2,735 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…
geopandas-spatial
Geospatial and climate data analysis with geopandas and xarray. Use when: (1) geographic vector data analysis, (2) climate and weather NetCDF data, (3) spatial joins and overlay operations, (4) map visualization, (5) CRS transformations and area calculations. NOT for: satellite imagery ML (use rasterio/torchgeo)…
pymatgen-materials
Materials science computation with pymatgen. Use when: (1) crystal structure creation and manipulation, (2) phase diagram construction, (3) electronic structure analysis, (4) symmetry and space group operations, (5) VASP input/output parsing. NOT for: molecular chemistry (use rdkit-chemistry), protein structure (use…
rdkit-chemistry
Molecular chemistry operations via RDKit. Use when: user asks about molecular structures, SMILES, chemical properties, or fingerprints. NOT for: reaction databases or wet lab protocols.
nanoresearch-experiment
Generate a Python code skeleton from an experiment blueprint.
alterlab-anndata
Build, slice, concatenate, read, and write AnnData annotated data matrices (obs, var, X, layers, obsm, uns) — the scverse data STRUCTURE, not an analysis pipeline. Use when creating or wrangling .h5ad/zarr files, managing cell and gene annotations, concatenating batches, or handling layers/obsm/backed-mode; for the…