Skip to content
Get packs

Tellurium Kinetic Experiments

Run and verify biochemical reaction-network simulations from SBML or Antimony models, with reproducible archives.

Source Download skill
Repository
K-Dense-AI/scientific-agent-skills
Stars
55,780
Licence
MIT
Files
4 files

What it does

This skill teaches the agent to simulate chemical reaction networks, such as how drug or metabolite concentrations change over time, using the Tellurium and libRoadRunner simulation tools. It checks the model's units and consistency, runs baseline and altered-parameter scenarios, and exports the exact model files and a standard COMBINE archive that can be replayed later to confirm the results match. It is meant for deterministic kinetic models, not for steady-state metabolic flux analysis.

Great for

  • Researchers or students modelling reaction kinetics from a local SBML or Antimony model file
  • Computational biologists who need reproducible parameter sweeps with exported SBML and SED-ML archives
  • Anyone who wants concentration time courses and CSV output checked against a stored replay

Skip it if

  • Steady-state constraint-based metabolic flux analysis, which the skill itself says belongs to cobrapy
  • Stochastic, event-driven, delayed or rate-rule models, which the skill explicitly does not cover in its tests; results could be misleading
  • Clinical or safety decisions based on a model's output, since the skill notes that a smooth curve does not establish model validity

Try asking

  • “Simulate the reaction A to B with k=0.2 and then with k=0.4 over 0 to 10 seconds and export the results”
  • “Check the units and consistency of my SBML model file before running a time course”
  • “Run a parameter sweep on a kinetic model I have locally and package the results as a COMBINE archive”
Step-by-step guide: how to use Tellurium Kinetic ExperimentsInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 4 original files, the MIT licence and an attribution note.

    tellurium.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip tellurium.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip tellurium.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Create a fresh output directory for each run, since the helper refuses to overwrite existing output folders.
  • Use the model's own time units in the experiment JSON and confirm species are concentration-based, since amount-only species are rejected.
  • Re-run at stricter solver tolerances when small differences matter, and treat the replay check as evidence of consistency rather than proof of model validity.

What's inside

  • assets/experiment.json
  • references/experiments.md
  • scripts/kinetic_experiment.py
  • SKILL.md

Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.