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 TianGzlab/OmicsClaw --skill mendelian-randomization-twosamplemrgit clone --depth 1 https://github.com/TianGzlab/OmicsClawWrote 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/tiangzlab/omicsclaw/mendelian-randomization-twosamplemr)<a href="https://agentmods.dev/skills/tiangzlab/omicsclaw/mendelian-randomization-twosamplemr"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/mendelian-randomization-twosamplemr/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/tiangzlab/omicsclaw/mendelian-randomization-twosamplemr"><img src="https://agentmods.dev/badge/skills/tiangzlab/omicsclaw/mendelian-randomization-twosamplemr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00007 | $0.02778 |
| Opus 5 | $0.00003 | $0.01389 |
| Sonnet 5 | $0.00001 | $0.00556 |
| Haiku 4.5 | $0.00001 | $0.00278 |
Grade A, and why
Two-Sample Mendelian Randomization 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 — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Two-Sample Mendelian Randomization
When to Use This Skill
- You have GWAS summary statistics for an exposure and outcome trait
- You want to test causal direction between two traits (not just correlation)
- You need to assess whether an observed association is likely causal or confounded
- You want to use genetic variants as instrumental variables (natural experiment)
- You have OpenGWAS trait IDs or your own GWAS summary statistics files
Not suitable for: One-sample MR (individual-level data), non-linear MR, multivariable MR with >2 exposures
Installation
install.packages(c("remotes", "ggplot2", "ggprism", "dplyr", "rmarkdown"))
remotes::install_github("MRCIEU/TwoSampleMR")
# For PDF report generation (optional but recommended):
# install.packages("tinytex"); tinytex::install_tinytex()
# For MR-PRESSO outlier detection (optional but recommended):
# remotes::install_github("rondolab/MR-PRESSO")
| Software | Version | License | Commercial Use |
|---|---|---|---|
| TwoSampleMR | ≥0.5.6 | GPL-3 | ✅ Permitted |
| ieugwasr | ≥0.2.1 | MIT | ✅ Permitted |
| ggplot2 | ≥3.4.0 | MIT | ✅ Permitted |
| ggprism | ≥1.0.3 | GPL (≥3) | ✅ Permitted |
| dplyr | ≥1.1.0 | MIT | ✅ Permitted |
| rmarkdown | ≥2.20 | GPL-3 | ✅ Permitted |
Inputs
Option A — OpenGWAS IDs (recommended):
- Exposure ID (e.g.,
"ieu-a-300"for LDL cholesterol) - Outcome ID (e.g.,
"ieu-a-7"for coronary heart disease) - Browse available traits at: https://gwas.mrcieu.ac.uk/
Option B — User-provided files (CSV/TSV):
- Exposure GWAS summary statistics
- Outcome GWAS summary statistics
| Required Column | Description | Example |
|---|---|---|
| SNP | rsID | rs1234567 |
| beta | Effect estimate | 0.05 |
| se | Standard error | 0.01 |
| pval | P-value | 5e-10 |
| effect_allele | Effect allele | A |
| other_allele | Other allele | G |
| eaf | Effect allele frequency (optional) | 0.3 |
Outputs
Results (CSV):
mr_results.csv— MR estimates from all 4 methods (beta, SE, p-value, nSNP, F-statistics)heterogeneity_results.csv— Cochran's Q test for instrument heterogeneitypleiotropy_results.csv— MR-Egger intercept test for directional pleiotropydirectionality_results.csv— Steiger test confirming causal directionharmonized_data.csv— SNP-level harmonized exposure-outcome datasingle_snp_results.csv— Per-SNP Wald ratio estimatesleaveoneout_results.csv— Leave-one-out robustness estimates- MR-PRESSO outlier results (if heterogeneity significant and MRPRESSO installed)
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 216 lines · 7 tokens per session scan A 73d677477cc1
Two-Sample Mendelian Randomization is a skill published in the GitHub repository TianGzlab/OmicsClaw (160 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 7 tokens to every session and 2,778 once invoked, about $0.0000 per session on Opus 5. 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
scanpy
Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use…
cellxgene-census-query
Query CZ CELLxGENE Census (61M+ cells). Filter by cell type/tissue/disease, retrieve expression data, and integrate with scanpy/PyTorch for population-scale single-cell analysis. Use this skill when: (1) Querying single-cell expression data by cell type, tissue, or disease, (2) Exploring available single-cell datasets…
single-cell-scrna-seq-analysis-scanpy
Complete single-cell RNA-seq analysis workflow built on Scanpy and AnnData. Use this skill when: (1) Loading diverse single-cell data formats (10X, h5ad, CSV), (2) Performing quality control and filtering, (3) Normalization, dimensionality reduction, and clustering, (4) Marker gene identification and cell type…
single-cell-multi-omics-analysis-scvi
Probabilistic deep learning framework for single-cell multi-omics data analysis. Use this skill when: (1) Analyzing single-cell RNA-seq data with batch correction, (2) Integrating multi-modal data (CITE-seq, ATAC-seq, multi-omics), (3) Performing cell type annotation with scANVI, (4) Spatial transcriptomics…
anndata
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
celltypepilot
Single-cell cell-type annotation with evidence, conservative abstention, and reviewable drafts. Use this whenever the user wants to annotate, label, or identify cell types for pre-clustered single-cell or spatial transcriptomics data (.h5ad), or says things like "annotate my clusters", "what cell types are these?"…