New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Metabolic Study Planner

by aiming-lab in aiming-lab/AutoResearchClaw

Turns a broad metabolic modelling topic into a concrete, paper-shaped plan with organism, model, perturbations, metrics and figures before any FBA code is written.

MITAuto-check passedResearch & Science

Install Metabolic Study Planner

skills CLI
$ npx skills add aiming-lab/AutoResearchClaw --skill metabolic-study-planner -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aiming-lab/AutoResearchClaw metabolic-study-planner --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aiming-lab/AutoResearchClaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/external/agents/Biology-Agent/skills/metabolic-study-planner .claude/skills/metabolic-study-planner && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
metabolic-study-planner
GitHub stars
15k
Token cost
~1.9k tokens
SKILL.md length
760 words
Files
1
Skills in repo
34
Repo updated
First seen
Licence
MIT

At a glance

Turns a broad metabolic modelling topic into a concrete, paper-shaped plan with organism, model, perturbations, metrics and figures before any FBA code is written.

  • Works in 5 steps: Select a product exchange reaction, e.g.… → Run WT FBA and pFBA under a defined… → Screen single reaction/gene knockouts. → …
  • Starting a flux balance analysis paper from only a broad topic
  • SKILL.md covers Overview, Planning Inputs, Study Archetypes and Feasibility Gate, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Used before the gsmm-builder, fba-simulator and flux-analyzer skills when a project starts from a vague prompt such as a metabolic flux analysis paper. It extracts or infers biological scope, organism, model source such as a BiGG ID or SBML file, objective, condition, perturbation, target output and paper type. When no organism is given it falls back to low-risk defaults: E. coli K-12, S. cerevisiae, human Recon3D or M. tuberculosis, preferring E. coli for fully autonomous first runs.

Study archetypes supply ready plans. The first, for metabolic engineering and fermentation topics, selects a product exchange reaction, runs wild-type FBA and pFBA, screens single reaction or gene knockouts, ranks them by product secretion while keeping growth, and validates top candidates with FVA and carbon-source sensitivity. Required metrics include growth rate, mutant growth fraction, secretion flux, yield per glucose uptake and stability across oxygen and carbon-source bounds.

When your agent uses it

  • Starting a flux balance analysis paper from only a broad topic
  • Choosing a feasible BiGG model, objective and perturbation set
  • Planning a knockout screen for product overproduction
  • Defining metrics and figures before generating FBA code

Example prompts

  • “Plan a publishable study on yeast fermentation without a specific dataset.”
  • “Pick an organism and model for a knockout strategy to boost succinate production.”
  • “Turn the idea of a metabolic flux analysis paper into a concrete study plan.”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Select a product exchange reaction, e.g. succinate, lactate, ethanol, acetate.
  2. Run WT FBA and pFBA under a defined medium.
  3. Screen single reaction/gene knockouts.
  4. Rank perturbations by product secretion subject to retaining growth.
  5. Validate top candidates with FVA and carbon-source sensitivity.

What it can do on your machine

Read from SKILL.md and the folder at commit be4ba47. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

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

  • Network

    No URLs in SKILL.md.

    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.

Context cost

Metabolic Study Planner loads about 1.9k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 760 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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

Auto-check passed

The automated check found no risky patterns in SKILL.md.

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 aiming-lab/AutoResearchClaw at commit be4ba47, republished under its MIT licence (© aiming-lab). 760 words, ~1,920 tokens.

Download SKILL.mdSave it as .claude/skills/metabolic-study-planner/SKILL.md (or your agent's skills folder).
name
metabolic-study-planner
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.
metadata.category
domain
metadata.trigger-keywords
metabolic idea,metabolic study,metabolic engineering,FBA,COBRApy,BIGG,no idea,study planner,hypothesis generation,organism selection,target product
metadata.applicable-stages
1,2,7,8,9,10,14,15,16,17
metadata.priority
1

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:

FieldExamples
Biological scopemicrobial metabolism, cancer metabolism, yeast fermentation, tuberculosis
OrganismE. coli, S. cerevisiae, human Recon3D, M. tuberculosis
Model sourceBiGG ID, local SBML/JSON, manually constructed toy model
Objectivebiomass, product secretion, ATP maintenance, dual objective
Conditionaerobic, anaerobic, carbon source, nutrient limitation
Perturbationgene knockout, reaction knockout, medium swap, oxygen sweep
Target outputgrowth, product yield, essential genes, secretion profile
Paper typemechanism hypothesis, metabolic engineering strategy, benchmark, reproduction

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

DefaultModelWhy
E. coli K-12iJO1366 or core modelFast, well curated, standard for FBA papers
S. cerevisiaeiMM904Fermentation and product-yield studies
Human metabolismRecon3DDisease metabolism, but larger and harder
M. tuberculosisiNJ661Essentiality 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.

Plan:

  1. Select a product exchange reaction, e.g. succinate, lactate, ethanol, acetate.
  2. Run WT FBA and pFBA under a defined medium.
  3. Screen single reaction/gene knockouts.
  4. Rank perturbations by product secretion subject to retaining growth.
  5. Validate top candidates with FVA and carbon-source sensitivity.

Required metrics:

  • WT growth rate
  • mutant growth fraction
  • product secretion flux
  • product yield per glucose uptake
  • robustness across oxygen/carbon-source bounds

Paper claim format:

Constraint-based screening predicts that perturbing <pathway> improves <product> secretion while preserving <growth_fraction> of WT growth.

Archetype B: Nutrient-Condition Phase Map

Use when the topic mentions adaptation, nutrient limitation, aerobic/anaerobic growth, diauxie, or environmental stress.

Plan:

  1. Choose two exchange reactions, usually glucose and oxygen.
  2. Generate a 2D production envelope / phenotype phase plane.
  3. Compare secretion profiles across regimes.
  4. Identify transitions between respiration, overflow metabolism, and no-growth regions.

Required metrics:

  • growth flux_maximum
  • glucose uptake
  • oxygen uptake
  • major byproduct secretion fluxes
  • regime labels

Paper claim format:

A two-axis nutrient envelope reveals distinct feasible metabolic regimes and predicts condition-specific secretion shifts.

Archetype C: Essentiality and Drug-Target Prioritisation

Use when the topic mentions antimicrobial targets, cancer metabolism, essential genes, or robustness.

Plan:

  1. Select an organism/model relevant to the disease.
  2. Run single gene/reaction deletion.
  3. Filter essential genes/reactions.
  4. Remove non-specific housekeeping artifacts where possible.
  5. Prioritise targets by subsystem, growth impact, and flux centrality.

Required metrics:

  • essential gene count
  • essential reaction count
  • subsystem enrichment
  • growth fraction after deletion
  • rescue condition sensitivity

Paper claim format:

FBA essentiality analysis prioritises <subsystem> as a condition-dependent vulnerability under <medium>.

Show full SKILL.md (273 more words)Show less
Archetype D: Method/Protocol Benchmark

Use when the topic is methodological or AutoResearchClaw asks for a benchmark.

Plan:

  1. Compare FBA, pFBA, loopless FBA, and FVA-derived predictions.
  2. Run across multiple models or media.
  3. Evaluate stability of growth, secretion, and essentiality calls.

Required metrics:

  • runtime
  • solver status rate
  • agreement of essential genes/reactions
  • flux sparsity
  • objective consistency

Paper claim format:

A standardised COBRApy protocol improves reproducibility of metabolic phenotype predictions across models and media.

Feasibility Gate

Before committing to a study, score candidate ideas from 1-5:

CriterionReject if
Model availabilityno BiGG/SBML/JSON model or no clear toy model
Runtimerequires exhaustive double knockouts on large models
Interpretabilityno identifiable pathway/subsystem or biological claim
Output richnessfewer than 3 meaningful figures/tables
Reproducibilitydepends on undocumented proprietary data

Proceed only if total score is at least 18/25. Otherwise choose a simpler organism, narrower product, or smaller perturbation space.

Required Study Card

Write a study_card.md before code generation:

markdown
# Metabolic Study Card

## Research Question
One sentence.

## Hypothesis
One falsifiable claim.

## Model
- Organism:
- Model ID / source:
- Objective reaction:

## Conditions
- Medium:
- Carbon source:
- Oxygen bounds:

## Analyses
- FBA:
- pFBA:
- FVA:
- Knockout screen:
- Production envelope:

## Metrics
- Growth rate:
- Product flux:
- Yield:
- Essentiality:
- Robustness:

## Figures
1. WT vs perturbation flux summary
2. Product yield ranking
3. Production envelope / phase map
4. Essentiality or subsystem enrichment plot

## Risks
- Model curation risk:
- Solver/runtime risk:
- Biological interpretation risk:

AutoResearchClaw Guidance

When this skill is matched in AutoResearchClaw:

  • In hypothesis_gen, propose hypotheses tied to a named model and analysis.
  • In experiment_design, include a concrete model ID, objective reaction, perturbation set, and metrics.
  • In code_generation, generate a self-contained COBRApy script that can run either on a local model file or on a minimal fallback toy model if the full model is unavailable.
  • In result_analysis, do not overclaim experimental validation. Phrase results as model-based predictions.
  • In paper writing, explicitly state that conclusions are constraint-based computational predictions requiring wet-lab validation.

If the user has no idea, start with:

text
Predict robust reaction knockout strategies for succinate overproduction in
E. coli using COBRApy FBA, pFBA, FVA, and oxygen/glucose production envelopes.

This topic is computationally feasible, uses a standard organism, produces multiple figures, and has an interpretable metabolic-engineering narrative.

© aiming-lab, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in external/agents/Biology-Agent/skills/metabolic-study-planner of aiming-lab/AutoResearchClaw.

Open the folder on GitHubat commit be4ba47

Compare with similar skills

Metabolic Study Planner next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Metabolic Study Planner compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Metabolic Study Planner this skillaiming-lab/AutoResearchClaw15k—~1.9kAutomated safety check: PassMIT
Claim-Driven Experiment PlannerzjYao36/Auto-Research-Refine1287 repos~2.3kAutomated safety check: NotesNone
Research RefinezjYao36/Auto-Research-Refine1287 repos~6.9kAutomated safety check: NotesNone
Scientific BrainstormingOleafly/Oleafly2062 repos~3.5kAutomated safety check: PassMIT
Academic GrillExekiel179/psyclaw103—~2kAutomated safety check: PassMIT
Denariodavila7/claude-code-templates32k9 repos~1.5kAutomated safety check: NotesMIT

Similar skills

  • Claim-Driven Experiment Planner

    zjYao36/Auto-Research-Refine

    Turns a refined research proposal into a claim-to-evidence-to-run-order roadmap instead of a sprawling benchmark wishlist.

    128 GitHub starsUsed in 7 repos~2.3k tokens
    Research & ScienceAuto-check: notes

  • Research Refine

    zjYao36/Auto-Research-Refine

    Turns a vague research direction into a focused, problem-anchored method plan through up to five review rounds with a second model.

    128 GitHub starsUsed in 7 repos~6.9k tokens
    Research & ScienceAuto-check: notes

  • Scientific Brainstorming

    Oleafly/Oleafly

    Facilitates evidence-aware scientific ideation with independent generation, structured discussion, explicit assumptions, transparent evaluation, adversarial review, and decision logs.

    206 GitHub starsUsed in 2 repos~3.5k tokens
    Research & ScienceAuto-check passed

  • Academic Grill

    Exekiel179/psyclaw

    Stress-test an academic research question, proposal, study design, analysis plan, manuscript claim, review protocol, or AI research project through a one-question-at-a-time interview until its…

    103 GitHub stars~2k tokensUpdated 10 days ago
    Research & ScienceAuto-check passed

  • Denario

    davila7/claude-code-templates

    Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication.

    32k GitHub starsUsed in 9 repos~1.5k tokens
    Research & ScienceAuto-check: notes

  • Aviv Regev

    K-Dense-AI/mimeographs

    Applies the computational biology and AI-driven reasoning of Aviv Regev (computational biologist, Genentech, single-cell genomics).

    129 GitHub stars~1.4k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

More from aiming-lab/AutoResearchClaw

All 34 skills in this repo

  • A-Evolve Agent Improvement

    aiming-lab/AutoResearchClaw

    Diagnoses where an agent failed across runs and turns the findings into new skills, system prompt patches and knowledge entries, using the A-Evolve loop.

    15k GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

  • MFA Pipeline Orchestrator

    aiming-lab/AutoResearchClaw

    Runs a metabolic flux analysis from model loading to phenotype prediction and figures by handing work to four sub-agents in sequence.

    15k GitHub stars~923 tokensUpdated 1 mo ago
    Auto-check passed

  • Qiskit 2.x Quantum ML Reference

    aiming-lab/AutoResearchClaw

    Reference patterns for writing qiskit 2.x code for variational quantum machine learning: feature maps, VQC training, VQE for chemistry, MPS circuits and noise models.

    15k GitHub stars~4.7k tokensUpdated 1 mo ago
    Auto-check passed

  • Genome-Scale Metabolic Model Builder

    aiming-lab/AutoResearchClaw

    Builds or loads a genome-scale metabolic model in COBRApy, sets its growth medium and objective, and exports it as a validated JSON file for flux analysis.

    15k GitHub stars~1.4k tokensUpdated 1 mo ago
    Auto-check passed

  • Biopython Bioinformatics

    aiming-lab/AutoResearchClaw

    Quick reference for Biopython work: sequence operations, SeqIO file parsing, BLAST searches, Entrez queries, phylogenetic trees and PDB structure analysis.

    15k GitHub stars~810 tokensUpdated 1 mo ago
    Auto-check passed

  • RDKit Cheminformatics Practices

    aiming-lab/AutoResearchClaw

    Reference guide for working with molecules in RDKit: reading SMILES and SDF files, computing descriptors and fingerprints, and searching substructures.

    15k GitHub stars~708 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Metabolic Study Planner

What does Metabolic Study Planner do?

Turns a broad metabolic modelling topic into a concrete, paper-shaped plan with organism, model, perturbations, metrics and figures before any FBA code is written. Used before the gsmm-builder, fba-simulator and flux-analyzer skills when a project starts from a vague prompt such as a metabolic flux analysis paper. It extracts or infers biological scope, organism, model source such as a BiGG ID or SBML file, objective, condition, perturbation, target output and paper type.

When should I use Metabolic Study Planner?

Metabolic Study Planner fits situations like: starting a flux balance analysis paper from only a broad topic; choosing a feasible BiGG model, objective and perturbation set; planning a knockout screen for product overproduction; defining metrics and figures before generating FBA code.

How do I install Metabolic Study Planner in Claude Code?

Run `npx skills add aiming-lab/AutoResearchClaw --skill metabolic-study-planner -a claude-code`. Or copy the skill folder (external/agents/Biology-Agent/skills/metabolic-study-planner in aiming-lab/AutoResearchClaw) into .claude/skills/metabolic-study-planner in your project. Claude Code loads it when a task matches its description.

How do I install Metabolic Study Planner in Codex?

Run `npx skills add aiming-lab/AutoResearchClaw --skill metabolic-study-planner -a codex`. Or copy the skill folder (external/agents/Biology-Agent/skills/metabolic-study-planner in aiming-lab/AutoResearchClaw) into .agents/skills/metabolic-study-planner in your project. Codex loads it when a task matches its description.

Can I use Metabolic Study Planner in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aiming-lab/AutoResearchClaw --skill metabolic-study-planner -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/metabolic-study-planner, .gemini/skills/metabolic-study-planner, .github/skills/metabolic-study-planner and .opencode/skills/metabolic-study-planner in your project.

What does Metabolic Study Planner need to run?

SKILL.md names no scripts, command-line tools or credentials: Metabolic Study Planner is instructions for the agent only.

Does Metabolic Study Planner access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Metabolic Study Planner safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Metabolic Study Planner use?

Metabolic Study Planner is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Metabolic Study Planner use?

About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Metabolic Study Planner?

Skills that share tags, products or a category with Metabolic Study Planner: Claim-Driven Experiment Planner (zjYao36/Auto-Research-Refine, 128 stars), Research Refine (zjYao36/Auto-Research-Refine, 128 stars), Scientific Brainstorming (Oleafly/Oleafly, 206 stars) and Academic Grill (Exekiel179/psyclaw, 103 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Metabolic Study Planner?

aiming-lab (a GitHub organization) maintains it in aiming-lab/AutoResearchClaw, which has 14,595 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on August 19, 2026.

Source: aiming-lab/AutoResearchClaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.