OpenBioMed is an agent platform and toolkit collection for biomedical research and drug discovery, covering areas such as molecular design, protein analysis, and single-cell data analysis. It is intended for researchers and provides the biomedical skills listed in the catalogue as workflows for Claude Code.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add PharMolix/OpenBioMed --skill single-cell-multi-omics-data-harmonizationgit clone --depth 1 https://github.com/PharMolix/OpenBioMedWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pharmolix/openbiomed/single-cell-multi-omics-data-harmonization)<a href="https://agentmods.dev/skills/pharmolix/openbiomed/single-cell-multi-omics-data-harmonization"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/single-cell-multi-omics-data-harmonization/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pharmolix/openbiomed/single-cell-multi-omics-data-harmonization"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/single-cell-multi-omics-data-harmonization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
- medium Excessive Agency · line 35 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02929 |
| Opus 5 | $0.00000 | $0.01465 |
| Sonnet 5 | $0.00000 | $0.00586 |
| Haiku 4.5 | $0.00000 | $0.00293 |
Grade A, and why
single-cell-multi-omics-data-harmonization scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Omics Data Harmonization
Prepare your RNA-seq, proteomics, methylation, and other omics datasets for joint integration by applying per-assay normalization, cross-assay batch correction, feature ID alignment, and missing value handling.
This is Step 1 of the multi-omics integration pipeline — all downstream skills (MOFA, DIABLO, SNF) depend on clean, consistently scaled output from this step.
What it does
- Loads each omics layer into a unified container (MultiAssayExperiment in R; MuData in Python)
- Applies the correct normalization strategy per data type:
- RNA-seq counts → VST (DESeq2)
- Proteomics LFQ intensity → log2 + median centering
- Methylation β-values → M-value transformation: log2(β / 1−β)
- ATAC-seq peaks → log1p(CPM); miRNA → log2(CPM + 1)
- Generates PCA plots before batch correction to visualize batch structure
- Applies ComBat batch correction across assays, preserving biological condition signal
- Generates PCA plots after correction to confirm batch removal
- Maps protein UniProt IDs and methylation probe IDs to HGNC gene symbols via Ensembl BioMart
- Filters features with > 30% missing values, then imputes remaining NAs with MinProb
- Z-scores all features and exports as
.rds,.h5mu, and.csvfor all downstream tools
Why this exists
If you ask a general AI to "prepare my multi-omics data for integration," it will:
- Apply the same normalization to all data types (wrong — RNA counts need VST; methylation needs M-value transformation, not log2)
- Run ComBat without checking for batch–condition confounding, silently removing biological signal
- Skip feature ID alignment, leaving protein UniProt IDs unmapped to gene symbols
- Not generate PCA plots to verify batch correction worked
- Export data in a format incompatible with MOFA, DIABLO, or SNF
This skill encodes the correct methodological decisions:
- Uses VST for RNA, log2+median centering for protein, and M-value for methylation — each chosen for statistical properties of that data type
- Checks
table(Batch, Condition)before ComBat to detect confounding - Aligns all features to HGNC gene symbols via Ensembl BioMart for cross-omics compatibility
- Filters high-missingness features before imputation to avoid noise amplification
- Exports in both R (
.rds) and Python (.h5mu) formats for full downstream flexibility
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 261 lines · 0 tokens per session scan A 9b3a732c427b
single-cell-multi-omics-data-harmonization is a skill published in the GitHub repository PharMolix/OpenBioMed (1,106 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,929 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…