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

Bio Single Cell Metabolite Communication

by GPTomics in GPTomics/bioSkills

Infers metabolite-mediated cell-cell communication from scRNA-seq by scoring enzyme-to-sensor pairs (MEBOCOST), with metabolic flux (scFEA), FBA state (Compass), and neurotransmitter (NeuronChat)…

MITAuto-check passedResearch & Science

Install Bio Single Cell Metabolite Communication

skills CLI
$ npx skills add GPTomics/bioSkills --skill bio-single-cell-metabolite-communication -a claude-code

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

GitHub CLI
$ gh skill install GPTomics/bioSkills bio-single-cell-metabolite-communication --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/GPTomics/bioSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/single-cell/metabolite-communication .claude/skills/bio-single-cell-metabolite-communication && 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
bio-single-cell-metabolite-communication
GitHub stars
1.2k
Used in
1 other repo
Token cost
~3.2k tokens
SKILL.md length
1,221 words
Files
3
Skills in repo
559
Repo updated
First seen
Licence
MIT

At a glance

Infers metabolite-mediated cell-cell communication from scRNA-seq by scoring enzyme-to-sensor pairs (MEBOCOST), with metabolic flux (scFEA), FBA state (Compass), and neurotransmitter (NeuronChat)…

  • Studying metabolic crosstalk between cell types
  • SKILL.md covers Version Compatibility, Governing Principle, Method Decision Table and Confounds That Mimic…, plus 7 more sections
  • Runs Python scripts from its folder; calls pip
  • Predicting metabolite secretion and sensing

What it does

Bio Single Cell Metabolite Communication is an agent skill from GPTomics/bioSkills. Infers metabolite-mediated cell-cell communication from scRNA-seq by scoring enzyme-to-sensor pairs (MEBOCOST), with metabolic flux (scFEA), FBA state (Compass), and neurotransmitter (NeuronChat) alternatives. Use when studying metabolic crosstalk between cell types, predicting metabolite secretion and sensing, or deciding which metabolic-communication method fits and how speculative the result is.

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `examples/metabolite_communication.py` and `usage-guide.md`).

It sits in Research & Science, covering Bioinformatics. The repository describes itself as: a set of SKILLS.md for doing bioinformatics with agents like claude code. The licence is MIT.

When your agent uses it

  • Studying metabolic crosstalk between cell types
  • Predicting metabolite secretion and sensing
  • Deciding which metabolic-communication method fits and how speculative the result is

Example prompts

  • “Use the bio-single-cell-metabolite-communication skill to infer metabolite-mediated cell-cell communication from scRNA-seq by scoring…”
  • “/bio-single-cell-metabolite-communication”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit d91ed3d. 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

    Ships script files (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • pip

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

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    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

Bio Single Cell Metabolite Communication loads about 3.2k tokens when it runs. Until then it costs about 111 tokens; SKILL.md has 1,221 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~111
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k

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 GPTomics/bioSkills at commit d91ed3d, republished under its MIT licence (© GPTomics). 1,221 words, ~3,247 tokens.

Download SKILL.mdSave it as .claude/skills/bio-single-cell-metabolite-communication/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
bio-single-cell-metabolite-communication
description
Infers metabolite-mediated cell-cell communication from scRNA-seq by scoring enzyme-to-sensor pairs (MEBOCOST), with metabolic flux (scFEA), FBA state (Compass), and neurotransmitter (NeuronChat) alternatives. Use when studying metabolic crosstalk between cell types, predicting metabolite secretion and sensing, or deciding which metabolic-communication method fits and how speculative the result is.
tool_type
python
primary_tool
MeboCost

Version Compatibility

Reference examples tested with: mebocost 1.0+, scanpy 1.10+, anndata 0.10+

Before using code patterns, verify installed versions match. If versions differ:

  • Python: pip show <package> then help(module.function) to check signatures

If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying.

Metabolite-Mediated Cell Communication

"Find which cell types exchange metabolites" -> Infer a metabolite's presence from the cells expressing its synthesizing enzymes, then score communication to cells expressing its sensor or transporter.

  • Python: mebocost.create_obj() -> infer_commu() (metabolite-sensor scoring)

Governing Principle

Metabolite-mediated communication is a DOUBLE inference and the most speculative layer of cell-cell communication. scRNA-seq never measures metabolites; their levels are inferred from the expression of synthesizing enzymes, then a chain of further assumptions is stacked: enzyme mRNA -> enzyme protein -> enzyme ACTIVITY -> metabolic FLUX -> intracellular metabolite POOL -> SECRETION/export -> extracellular concentration in space -> import/SENSING by the receiver. Every arrow is an assumption and none is measured. On top of this sit all the ligand-receptor caveats (proxy, no spatial geometry in dissociated data, abundance and depth confounds, ambient RNA), so the output is hypothesis-generation ONLY. A defensible claim is never "cell A produces metabolite X" but "cell A expresses the machinery consistent with producing X". Validation is non-optional and means metabolomics (LC-MS), mass-spectrometry imaging (MALDI/DESI), isotope tracing, or perturbation of the enzyme or sensor - not another expression-based method. State the enzyme->flux->level->sensing chain explicitly whenever reporting a result.

Method Decision Table

MethodTests what / nullUse whenFails when
MEBOCOSTMetabolite SENDER->RECEIVER communication; estimates an extracellular metabolite level from producing-enzyme expression, scores enzyme->sensor pairs, permutation FDR over shuffled labelsThe question is metabolite crosstalk between cell types (enzyme-sensor), analogous to CellPhoneDB for L-RSynthase mRNA present but substrate/cofactor absent; transporter "sensor" is bidirectional/promiscuous so sender/receiver direction is wrong; no spatial geometry
scFEAPer-cell metabolic FLUX through modules; graph neural network solver enforcing flux balance (in approximately out)The question is relative flux per cell to FEED metabolite reasoning, not direct communicationRead as absolute mol/s (fluxes are relative); needs the matching module/stoichiometry files for the species; not a CCC tool itself
CompassPer-cell metabolic STATE via flux-balance analysis; reaction penalty inversely proportional to enzyme expression over Recon2, outputs a score per reaction per cellComparing metabolic state between conditions (e.g. pathogenic vs non-pathogenic cells)Used to claim a SECRETED metabolite communicates (output is reaction favorability, not secretion); assumes steady state, questionable for differentiated non-proliferating cells; heavy compute, micropool first
NeuronChatNeurotransmitter/neuromodulator communication; vesicular release machinery and synthesis enzymes vs target receptor abundanceNeural systems specifically (glutamate, GABA, dopamine, serotonin, neuropeptides)Applied outside neural tissue; same expression-proxy and geometry limits

Methods and their curated databases evolve; before committing, verify current best practice, the metabolite-sensor database version, and required config/species files against the installed package docs.

Confounds That Mimic Communication

ConfoundHow it manufactures a fake signalMitigation
Compounded inferenceEnzyme mRNA is a poor proxy for metabolite concentration (post-transcriptional control, substrate availability, allostery, compartmentalization), so a "secreted" metabolite may never be madeState the enzyme->flux->level->sensing chain; require metabolomics/MSI/tracing before any production claim
Bidirectional transportersA transporter labeled a "sensor" may export rather than import, and many move several metabolites, so sender/receiver direction can be invertedTreat transporter-based calls as lower-confidence than dedicated-receptor calls; check transport directionality literature
Ambient RNASoup of highly expressed transcripts inflates enzyme/sensor "expression" in clusters that do not transcribe themDecontaminate (SoupX/DecontX/CellBender) before inference
Cell-type abundance and depthLarger clusters tighten the permutation null and deeper cells detect more genes, inflating significance independent of biologyDown-sample, run on integrated counts, do not compare raw counts across conditions
No spatial geometryMetabolites diffuse and degrade, but dissociated data has no coordinates, so a "communication" may be between cells never co-locatedValidate proximity with spatial metabolomics/MSI; do not claim neighbor exchange from dissociated data

Run MEBOCOST

Goal: Score metabolite sender->receiver communication between cell types with permutation significance.

Approach: Build a MEBOCOST object from a log-normalized AnnData with cell-type labels and a config file pointing at the metabolite-sensor database, then run permutation inference; results carry both the communication score and an FDR.

python
from mebocost import mebocost
import scanpy as sc

adata = sc.read_h5ad('adata_annotated.h5ad')   # log-normalized, gene SYMBOLS not Ensembl IDs

# config_path points to mebocost.conf listing the metabolite-enzyme-sensor database paths
# cutoff_prop=0.15: a gene must be expressed in >=15% of a group to count (dropout floor)
# species MUST match the data: mouse data against the human enzyme/sensor DB returns almost nothing
mebo = mebocost.create_obj(adata=adata, group_col='cell_type', condition_col=None,
                           met_est='mebocost', config_path='./mebocost.conf', species='human',
                           cutoff_exp='auto', cutoff_met='auto', cutoff_prop=0.15,
                           sensor_type='All', thread=8)

# n_shuffle=1000: label-permutation null for FDR; min_cell_number=10 drops tiny groups
commu_res = mebo.infer_commu(n_shuffle=1000, seed=12345, Return=True,
                             min_cell_number=10, pval_method='permutation_test_fdr',
                             pval_cutoff=0.05, thread=None)

Filter and Summarize Results

Goal: Extract the significant, defensible metabolite communications.

Approach: Filter on the permutation FDR (not the raw p-value), then summarize by metabolite and by sender->receiver pair; column names are capitalized in the result table.

python
sig = commu_res[commu_res['permutation_test_fdr'] < 0.05].copy()

# Result columns: Sender, Receiver, Metabolite_Name, Sensor, Annotation (Transporter/Enzyme),
# Commu_Score, Norm_Commu_Score, met_in_sender, sensor_in_receiver, permutation_test_fdr
sig['pair'] = sig['Sender'] + ' -> ' + sig['Receiver']
top_metabolites = sig['Metabolite_Name'].value_counts().head(10)
top_pairs = sig['pair'].value_counts().head(10)

# Transporter-based sensors are lower-confidence (bidirectional); separate them
transporter_calls = sig[sig['Annotation'] == 'Transporter']
Show full SKILL.md (503 more words)Show less

Compare Conditions

Goal: Find metabolite communications that differ between conditions (e.g. tumor vs normal).

Approach: Either pass condition_col to a single object, or run MEBOCOST separately per condition subset and compare the significant sets; never compare raw interaction counts across conditions without controlling for cell number and depth.

python
results = {}
for cond in adata.obs['condition'].unique():
    sub = adata[adata.obs['condition'] == cond].copy()
    obj = mebocost.create_obj(adata=sub, group_col='cell_type', met_est='mebocost',
                              config_path='./mebocost.conf', species='human',
                              cutoff_prop=0.15, thread=8)
    results[cond] = obj.infer_commu(n_shuffle=1000, seed=12345, Return=True,
                                    min_cell_number=10, pval_cutoff=0.05)
# A "differential" metabolite call (significant in one condition only) is a HYPOTHESIS for metabolomics

Threshold and Permutation Rationale

ParameterValueRationale
cutoff_prop0.15A chosen dropout floor (MEBOCOST tutorials use 0.15-0.25, not a fixed package default): a gene expressed in <15% of a group is mostly dropout, but real low-abundance signaling is also discarded, so tune per dataset
cutoff_exp / cutoff_met'auto'MEBOCOST data-derived thresholds for calling a gene/metabolite present; set manually only with a documented reason
n_shuffle1000Stable label-permutation FDR; the FDR is about label shuffling, not actual metabolite flux
min_cell_number10Groups under ~10 cells give unstable mean expression and inflated scores
permutation_test_fdr cutoff0.05Filter on the FDR, not the raw permutation p-value; significance is statistical, not a measured concentration

Common Errors

SymptomCauseFix
KeyError: 'metabolite' / 'pval'Result columns are capitalized (Sender, Receiver, Metabolite_Name, Commu_Score, permutation_test_fdr)Use the exact column names from commu_res.columns
AttributeError: module 'mebocost' has no attribute 'create_obj'Wrong import; create_obj lives in the submodulefrom mebocost import mebocost then mebocost.create_obj(...)
Almost no metabolites detectedGenes are Ensembl IDs, data is not log-normalized, config_path database is missing, or species does not match the data (mouse data run against the human enzyme/sensor DB)Convert to gene symbols, log-normalize, point config_path at a valid mebocost.conf, set species to match the organism
A cell type "secretes" a metabolite implausiblySynthase mRNA present but substrate/cofactor absent, or ambient RNA inflated the enzymeDecontaminate ambient RNA; treat as "machinery consistent with", validate with metabolomics
Sender/receiver direction looks reversedSensor is a bidirectional/promiscuous transporterCheck Annotation == 'Transporter' calls separately; confirm transport direction
More communications in condition B than ACounts scale with cell number and depthCompare score magnitudes or matched subsets, not raw counts
  • single-cell/cell-communication - Ligand-receptor CCC; the single-inference counterpart this skill mirrors at one extra remove
  • single-cell/cell-annotation - Cell-type labels define metabolite senders and receivers
  • single-cell/preprocessing - Log-normalization, gene-symbol mapping, and ambient-RNA decontamination happen here, before inference
  • metabolomics/pathway-mapping - Places inferred metabolites in pathway context and informs which to prioritize
  • metabolomics/isotope-tracing - Orthogonal flux validation that a producing cell actually makes the metabolite
  • systems-biology/flux-balance-analysis - Genome-scale FBA underlying Compass-style per-cell metabolic state

References

  • Zheng R, et al. MEBOCOST maps metabolite-mediated intercellular communications using single-cell RNA-seq. Nucleic Acids Res 53(12):gkaf569 (2025). PMID 40568942.
  • Alghamdi N, et al. A graph neural network model to estimate cell-wise metabolic flux using single-cell RNA-seq data [scFEA]. Genome Res 31(10):1867-1884 (2021).
  • Wagner A, et al. Metabolic modeling of single Th17 cells reveals regulators of autoimmunity [Compass]. Cell 184(16):4168-4185 (2021).
  • Zhao W, et al. Inferring neuron-neuron communications from single-cell transcriptomics through NeuronChat. Nat Commun 14(1):1128 (2023).
  • Dimitrov D, et al. Comparison of methods and resources for cell-cell communication inference from single-cell RNA-Seq data. Nat Commun 13:3224 (2022). [discordance framing]
  • Young MD, Behjati S. SoupX removes ambient RNA contamination from droplet-based single-cell RNA sequencing data. GigaScience 9(12):giaa151 (2020).

© GPTomics, MIT. 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 in single-cell/metabolite-communication of GPTomics/bioSkills.

  • SKILL.md
  • examples/metabolite_communication.py
  • usage-guide.md

Open the folder on GitHubat commit d91ed3d

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 GPTomics/bioSkills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Bio Single Cell Metabolite Communication 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.

Bio Single Cell Metabolite Communication compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bio Single Cell Metabolite Communication this skillGPTomics/bioSkills1.2k1 repos~3.2kAutomated safety check: PassMIT
Alphagenome Single Variant Analysisgoogle-deepmind/science-skills3.2k2 repos~3kAutomated safety check: NotesApache-2.0
13C Metabolic Flux AnalysisK-Dense-AI/scientific-agent-skills48k1 repos~3.2kAutomated safety check: PassMIT
Clinvar Databasegoogle-deepmind/science-skills3.2k2 repos~3.9kAutomated safety check: NotesApache-2.0
Metabolic Study Planneraiming-lab/AutoResearchClaw15k—~1.9kAutomated safety check: PassMIT
Dbsnp Databasegoogle-deepmind/science-skills3.2k2 repos~3.4kAutomated safety check: NotesApache-2.0

Similar skills

  • Alphagenome Single Variant Analysis

    google-deepmind/science-skills

    Analyzes genetic variant effects on gene expression (RNA-seq), chromatin accessibility (DNASE), histone marks (ChIP), and transcription factors using the AlphaGenome API.

    3.2k GitHub starsUsed in 2 repos~3k tokens
    Research & ScienceAuto-check: notes

  • 13C Metabolic Flux Analysis

    K-Dense-AI/scientific-agent-skills

    Estimates reaction fluxes inside cells from steady-state carbon-13 labeling data with a bundled mfapy-based solver, and reports which fluxes the data pin down.

    48k GitHub starsUsed in 1 repo~3.2k tokens
    Research & ScienceAuto-check passed

  • Clinvar Database

    google-deepmind/science-skills

    A skill your agent uses when needing clinical significance, pathogenicity classifications (e.g., Pathogenic, Benign, VUS), clinical evidence rationales, or finding "hard positive" benchmark controls…

    3.2k GitHub starsUsed in 2 repos~3.9k tokens
    Research & ScienceAuto-check: notes

  • Metabolic Study Planner

    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.

    15k GitHub stars~1.9k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

  • Dbsnp Database

    google-deepmind/science-skills

    A skill your agent uses when you want to look up, map, and search for short genetic variants (SNPs, indels) in NCBI's dbSNP database.

    3.2k GitHub starsUsed in 2 repos~3.4k tokens
    Research & ScienceAuto-check: notes

  • 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
    Research & ScienceAuto-check passed

More from GPTomics/bioSkills

All 559 skills in this repo

  • Bio Alignment Io

    GPTomics/bioSkills

    Read, write, and convert multiple sequence alignment files using Biopython Bio.AlignIO.

    1.2k GitHub starsUsed in 3 repos~4.9k tokens
    Auto-check passed

  • bioSkills Installer

    GPTomics/bioSkills

    Installs the bioSkills collection of 425 bioinformatics skills in one step, or only chosen categories, so sequencing, RNA-seq, single-cell and variant tasks get specialized help.

    1.2k GitHub starsUsed in 1 repo~789 tokens
    Auto-check passed

  • Bio Write Sequences

    GPTomics/bioSkills

    Write biological sequences to files (FASTA, FASTQ, GenBank, EMBL) using Biopython Bio.SeqIO.

    1.2k GitHub starsUsed in 3 repos~2.1k tokens
    Auto-check passed

  • Amplicon Primer Clipping

    GPTomics/bioSkills

    Soft- or hard-clips PCR primer footprints from aligned amplicon BAMs so primer bases stop masquerading as confirmed reference sequence.

    1.2k GitHub starsUsed in 2 repos~2.2k tokens
    Auto-check passed

  • Alignment Filtering with samtools and pysam

    GPTomics/bioSkills

    Filters BAM alignments by FLAG bits, mapping quality and regions with samtools view or pysam, with recipes for common keep and drop cases.

    1.2k GitHub starsUsed in 2 repos~3.6k tokens
    Auto-check passed

  • Bio Alignment Indexing

    GPTomics/bioSkills

    Create and use BAI/CSI indices for BAM/CRAM files using samtools and pysam.

    1.2k GitHub starsUsed in 2 repos~2.4k tokens
    Auto-check passed

Categories

Questions about Bio Single Cell Metabolite Communication

What does Bio Single Cell Metabolite Communication do?

Infers metabolite-mediated cell-cell communication from scRNA-seq by scoring enzyme-to-sensor pairs (MEBOCOST), with metabolic flux (scFEA), FBA state (Compass), and neurotransmitter (NeuronChat)…. Bio Single Cell Metabolite Communication is an agent skill from GPTomics/bioSkills. Infers metabolite-mediated cell-cell communication from scRNA-seq by scoring enzyme-to-sensor pairs (MEBOCOST), with metabolic flux (scFEA), FBA state (Compass), and neurotransmitter (NeuronChat) alternatives.

When should I use Bio Single Cell Metabolite Communication?

Bio Single Cell Metabolite Communication fits situations like: studying metabolic crosstalk between cell types; predicting metabolite secretion and sensing; deciding which metabolic-communication method fits and how speculative the result is.

How do I install Bio Single Cell Metabolite Communication in Claude Code?

Run `npx skills add GPTomics/bioSkills --skill bio-single-cell-metabolite-communication -a claude-code`. Or copy the skill folder (single-cell/metabolite-communication in GPTomics/bioSkills) into .claude/skills/bio-single-cell-metabolite-communication in your project. Claude Code loads it when a task matches its description.

How do I install Bio Single Cell Metabolite Communication in Codex?

Run `npx skills add GPTomics/bioSkills --skill bio-single-cell-metabolite-communication -a codex`. Or copy the skill folder (single-cell/metabolite-communication in GPTomics/bioSkills) into .agents/skills/bio-single-cell-metabolite-communication in your project. Codex loads it when a task matches its description.

Can I use Bio Single Cell Metabolite Communication 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 GPTomics/bioSkills --skill bio-single-cell-metabolite-communication -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bio-single-cell-metabolite-communication, .gemini/skills/bio-single-cell-metabolite-communication, .github/skills/bio-single-cell-metabolite-communication and .opencode/skills/bio-single-cell-metabolite-communication in your project.

What does Bio Single Cell Metabolite Communication need to run?

Going by SKILL.md and its folder, Bio Single Cell Metabolite Communication needs Python for the scripts in its folder and the command-line tools its instructions call (pip). Our summary lists: Python 3.

Does Bio Single Cell Metabolite Communication access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Bio Single Cell Metabolite Communication 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 Bio Single Cell Metabolite Communication use?

Bio Single Cell Metabolite Communication 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 Bio Single Cell Metabolite Communication use?

About 3.2k tokens (SKILL.md is roughly 13k 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 Bio Single Cell Metabolite Communication?

Skills that share tags, products or a category with Bio Single Cell Metabolite Communication: Alphagenome Single Variant Analysis (google-deepmind/science-skills, 3.2k stars), 13C Metabolic Flux Analysis (K-Dense-AI/scientific-agent-skills, 48k stars), Clinvar Database (google-deepmind/science-skills, 3.2k stars) and Metabolic Study Planner (aiming-lab/AutoResearchClaw, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bio Single Cell Metabolite Communication?

GPTomics (a GitHub organization) maintains it in GPTomics/bioSkills, which has 1,218 GitHub stars. The repository holds 559 skills in this directory. The repository was last updated on August 15, 2026.

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