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 HolobiomicsLab/asb-skill-collections --skill random-matrix-theory-applicationgit clone --depth 1 https://github.com/HolobiomicsLab/asb-skill-collectionsWrote 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/holobiomicslab/asb-skill-collections/random-matrix-theory-application)<a href="https://agentmods.dev/skills/holobiomicslab/asb-skill-collections/random-matrix-theory-application"><img src="https://agentmods.dev/badge/skills/holobiomicslab/asb-skill-collections/random-matrix-theory-application/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/holobiomicslab/asb-skill-collections/random-matrix-theory-application"><img src="https://agentmods.dev/badge/skills/holobiomicslab/asb-skill-collections/random-matrix-theory-application.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 | $0.00045 | $0.01499 |
| Opus 5 | $0.00023 | $0.00749 |
| Sonnet 5 | $0.00009 | $0.00300 |
| Haiku 4.5 | $0.00005 | $0.00150 |
Grade A, and why
random-matrix-theory-application 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 6d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
random-matrix-theory-application
Summary
Apply Random Matrix Theory (RMT) within champ.SVD() to detect and cap the number of latent components in methylation data, limiting reported principal components to a maximum of 20 when RMT identifies more than 20 underlying factors. This skill enables robust batch effect detection by distinguishing true signal structure from noise in high-dimensional methylation arrays.
When to use
When analyzing normalized DNA methylation beta matrices (450K or EPIC arrays) and you need to identify the true number of latent batch or technical factors present in the data. Use this skill when the sample size or biological complexity suggests potential batch structure but the exact dimensionality is unknown; RMT will automatically detect signal rank while preventing overfitting to noise.
When NOT to use
- Input data is already a feature table or dimensionality-reduced representation (e.g., already run through PCA or t-SNE); apply RMT-based SVD to raw or normalized abundance matrices, not derived features.
- Sample size is extremely small (< 5–8 samples) or data contains no clear batch structure; RMT requires sufficient signal-to-noise ratio to reliably detect latent components.
- You require reporting all detected components without capping; if your downstream analysis depends on components >20, this skill's hard maximum of 20 is inappropriate.
Inputs
- normalized beta matrix (numerical matrix of methylation M-values or beta-values)
- HumanMethylation450 or EPIC array data (loaded from .idat files or pre-processed beta-valued matrix)
Outputs
- singular value decomposition (SVD) results with latent component count (maximum 20)
- principal components ranked by variance explained
- component loadings for visualization of batch effects
How to apply
Load a normalized beta matrix (from .idat files or a beta-valued matrix) into R and call champ.SVD() on the data. The function internally applies Random Matrix Theory to estimate the number of true latent components by analyzing the singular value spectrum. When RMT detects more than 20 latent components, champ.SVD() automatically caps the output to the top 20 principal components. Inspect the returned component count to confirm the capping behavior; this threshold of 20 represents a practical limit beyond which components are likely noise or statistical artifacts. Use the resulting component list to visualize and interpret batch structure (e.g., clustering samples by experimental batches or technical factors).
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.
- 6d ago First seen · 94 lines · 45 tokens per session scan A 1473f70e24b3
random-matrix-theory-application is a skill published in the GitHub repository HolobiomicsLab/asb-skill-collections (15 stars, last pushed 2d ago), licensed Apache-2.0. It adds 45 tokens to every session and 1,499 once invoked, about $0.0002 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 2026-09-06.
Other skills, from other repositories
external-model-validation
Use when validating an existing prognostic risk signature on an external bulk expression cohort with survival outcomes, producing risk scores, Kaplan-Meier curves, risk distribution plots, heatmap, and time-dependent ROC curves. NOT for: model training, feature selection, nomogram construction, calibration analysis…
medical-research-literature-reader-pro
A medical-research-native literature reading skill for users with clinical, bioinformatics, translational, and basic experimental backgrounds. Use this skill whenever a user wants to read, analyze, critique, or interpret a medical or scientific paper — whether they provide a PDF, abstract, DOI, PMID, or just a title.…
adverse-event-narrative
Generates CIOMS I-compliant ICSR narratives from adverse event case data for FDA and EMA regulatory submission. Includes temporal analysis, MedDRA coding, causality assessment using WHO-UMC or Naranjo criteria, and multi-format output.
anatomy-quiz-master
Generate interactive anatomy quizzes for medical education with multiple.
decision-curve-analysis
Use when evaluating the clinical utility of a binary prediction model from a single clinical CSV file by fitting a logistic decision-curve model, plotting decision and clinical-impact curves, and exporting summary outputs. NOT for: survival calibration, ROC-only discrimination analysis, nomogram construction, or…
elastic-net-feature-selection
Use when selecting predictive genes or other molecular features from bulk expression matrices for binary case-vs-control classification with elastic net logistic regression, including coefficient path and cross-validation plots. Trigger keywords: elastic net, glmnet, feature selection, binary classification…