# Metabolic Study Planner

Plan publishable constraint-based metabolic modelling studies when the user has a broad...

- Repository: https://github.com/aiming-lab/AutoResearchClaw (14798 stars)
- Category: Data and ML
- License: MIT
- Last updated: 2026-08-19
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add aiming-lab/AutoResearchClaw --skill metabolic-study-planner -g -a claude-code -y`
Codex: `npx skills add aiming-lab/AutoResearchClaw --skill metabolic-study-planner -g -a codex -y`
Cursor: `npx skills add aiming-lab/AutoResearchClaw --skill metabolic-study-planner -g -a cursor -y`
Gemini CLI: `npx skills add aiming-lab/AutoResearchClaw --skill metabolic-study-planner -g -a gemini-cli -y`

## Description

Plan publishable constraint-based metabolic modelling studies when the user has a broad biological or metabolic-engineering topic but no concrete dataset, organism, model, or hypothesis. Selects feasible BiGG/COBRA models, objectives, perturbations, analyses, metrics, figures, and risk controls before FBA code is generated.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Metabolic Study Planner

## Overview

Use this skill before `gsmm-builder`, `fba-simulator`, and `flux-analyzer` when
the project starts from a broad prompt such as "do a metabolic flux analysis
paper" or "find a publishable idea in microbial metabolism".

The goal is to turn a vague topic into a concrete, executable, paper-shaped
study plan:

```text
organism + model + condition + perturbation + metric + figure set + claim
```

This is the MFA analogue of choosing a collider process and parameter scan
before generating events.

## Planning Inputs

Extract or infer the following:

| Field | Examples |
|---|---|
| Biological scope | microbial metabolism, cancer metabolism, yeast fermentation, tuberculosis |
| Organism | E. coli, S. cerevisiae, human Recon3D, M. tuberculosis |
| Model source | BiGG ID, local SBML/JSON, manually constructed toy model |
| Objective | biomass, product secretion, ATP maintenance, dual objective |
| Condition | aerobic, anaerobic, carbon source, nutrient limitation |
| Perturbation | gene knockout, reaction knockout, medium swap, oxygen sweep |
| Target output | growth, product yield, essential genes, secretion profile |
| Paper type | mechanism hypothesis, metabolic engineering strategy, benchmark, reproduction |

If the user provides no organism, start with one of these low-risk defaults:

| Default | Model | Why |
|---|---|---|
| *E. coli* K-12 | `iJO1366` or core model | Fast, well curated, standard for FBA papers |
| *S. cerevisiae* | `iMM904` | Fermentation and product-yield studies |
| Human metabolism | `Recon3D` | Disease metabolism, but larger and harder |
| *M. tuberculosis* | `iNJ661` | Essentiality and drug-target hypotheses |

Prefer *E. coli* for fully autonomous first runs because it is fast and
interpretable.

## Study Archetypes

### Archetype A: Knockout Strategy for Product Overproduction

Use when the topic mentions metabolic engineering, bio-production, yield, or
fermentation.

The rest: https://github.com/aiming-lab/AutoResearchClaw/blob/HEAD/external/agents/Biology-Agent/skills/metabolic-study-planner/SKILL.md