Cobrapy

What it does

When your agent uses it

• Research & Science work in your project

Example prompts

• “Use the cobrapy skill to perform constraint-based metabolic modeling with COBRApy, including FBA, pFBA, FVA, gene knockouts, flux sampling, growth…”
• “/cobrapy”

Requirements

• Python 3
• Compatibility (from SKILL.md): Requires Python 3.9+ and cobra; examples tested with Python 3.12 and cobra 0.32.1. GLPK installs via swiglpk; commercial solvers need separate installation/licensing. Remote model downloads need network access; bundled textbook examples run offline.
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1Load, inspect, and validate a model
2. 2Compare FBA, pFBA, and FVA under stated constraints
3. 3Knockouts and media
4. 4Sample the same feasible region as the FVA comparison
5. 5Production envelopes and design hypotheses
6. 6Build and gap-fill carefully

What it can do on your machine

Read from SKILL.md and the folder at commit 92ace75. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Bash

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • uv

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • arxiv.org
  • cobrapy.readthedocs.io
  • github.com
  • doi.org
  • export.arxiv.org

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Requires Python 3.9+ and cobra; examples tested with Python 3.12 and cobra 0.32.1. GLPK installs via swiglpk; commercial solvers need separate installation/licensing. Remote model downloads need network access; bundled textbook examples run offline.

  From compatibility in the SKILL.md frontmatter.

Context cost

Cobrapy loads about 2.9k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 61 tokens; SKILL.md has 944 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~61

When it runs · the whole SKILL.md, loaded when a task matches

~2.9k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Write, Edit, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from K-Dense-AI/scientific-agent-skills at commit 92ace75, republished under its GPL-2.0 licence (© K-Dense-AI). 944 words, ~2,923 tokens.

name

cobrapy

description

Performs constraint-based metabolic modeling with COBRApy, including FBA, pFBA, FVA, gene knockouts, flux sampling, growth media, production envelopes, gap filling, and SBML model validation for systems biology and metabolic engineering.

allowed-tools

Read, Write, Edit, Bash

compatibility

Requires Python 3.9+ and cobra; examples tested with Python 3.12 and cobra 0.32.1. GLPK installs via swiglpk; commercial solvers need separate installation/licensing. Remote model downloads need network access; bundled textbook examples run offline.

license

GPL-2.0 license

metadata.version

1.5

metadata.skill-author

K-Dense Inc.

metadata.last-reviewed

2026-09-30

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"

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

from cobra.flux_analysis import pfba, geometric_fba, flux_variability_analysis

biomass_id = "Biomass_Ecoli_core"  # inspect IDs/objective for each new model
parsimonious = pfba(model)
print(parsimonious.fluxes[biomass_id])
# parsimonious.objective_value is the minimized total flux, not biomass growth.
centered = geometric_fba(model, processes=1)

fva = flux_variability_analysis(
    model, reaction_list=["PFK", "FBA", "PGI"],
    fraction_of_optimum=0.9, processes=1,
)
loopless_fva = flux_variability_analysis(
    model, reaction_list=["PFK", "FBA", "PGI"],
    fraction_of_optimum=0.9, loopless="fastSNP", processes=1,
)
print(fva)  # index: reaction ID; columns: minimum, maximum

from cobra.flux_analysis import single_gene_deletion
from cobra.medium import minimal_medium

results = single_gene_deletion(model, processes=1)
valid = results[results.status.eq("optimal") & results.growth.notna()]
low_growth = valid[valid.growth < 0.01 * baseline]  # declared 1% criterion
unresolved = results[~results.index.isin(valid.index)]
print(low_growth[["ids", "growth"]], unresolved[["ids", "status"]])

with model:
    medium = model.medium
    medium["EX_o2_e"] = 0.0
    model.medium = medium  # editing the returned dict alone does not change model
    anaerobic = model.optimize()
    print(anaerobic.status, anaerobic.objective_value)

min_medium = minimal_medium(model, 0.5 * baseline, minimize_components=True)
if min_medium is None:
    raise RuntimeError("No medium found at the requested growth target")
with model:
    model.medium = min_medium.to_dict()
    assert model.slim_optimize(error_value=None) >= 0.5 * baseline - 1e-6

from cobra.sampling import OptGPSampler

with model:
    model.reactions.get_by_id(biomass_id).lower_bound = 0.9 * baseline
    # The growth floor is already installed. fraction=0 adds no stronger optimum.
    sampled_fva = flux_variability_analysis(
        model, reaction_list=["PFK"], fraction_of_optimum=0.0, processes=1,
    )
    sampler = OptGPSampler(model, processes=1, thinning=100, seed=7)
    samples = sampler.sample(200)
    codes = sampler.validate(samples)
    assert (codes == "v").all(), "Inspect bound/equality violations"
    assert (samples[biomass_id] >= 0.9 * baseline - 1e-6).all()
print(samples["PFK"].describe(), sampled_fva)

from cobra.flux_analysis import production_envelope

with model:
    model.reactions.get_by_id(biomass_id).lower_bound = 0.1 * baseline
    envelope = production_envelope(
        model, reactions=["EX_glc__D_e"], objective="EX_ac_e",
        carbon_sources=["EX_glc__D_e"], points=8,
    )
print(envelope[["EX_glc__D_e", "flux_minimum", "flux_maximum"]])

© K-Dense-AI, GPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in skills/cobrapy of K-Dense-AI/scientific-agent-skills.

• SKILL.md
• references/api_quick_reference.md
• references/workflows.md

Open the folder on GitHubat commit 92ace75

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in K-Dense-AI/scientific-agent-skills, which our catalogue first saw on October 7, 2026.

• lingxling/awesome-skills-cnclaude-scientific-skills/skills/cobrapy