AI & ML

aradotso-trending-skills Skill

Framework for collective skill evolution in multi-user LLM agent ecosystems — automatically distills session experience into reusable SKILL.md files and shares them across agent clusters.

gptomics Bundle

Builds supervised and unsupervised multivariate integration across bulk omics blocks with mixOmics - sPLS for sparse pairwise correlation, DIABLO (block.splsda) for a multi-block discriminant signature, rCCA for regularized canonical correlation, and MINT for multi-study integration. Covers why these projection methods maximize covariance or correlation and not truth, why DIABLO's design matrix is the central correlation-versus-discrimination decision, why cross-validation must wrap keepX selection or the reported error is leaked, why balanced error rate is required under class imbalance, and why DIABLO needs matched samples while MINT handles multiple cohorts. Use when finding a cross-omic discriminant signature for a known outcome, selecting correlated features between two omics, tuning keepX, or integrating one omic across studies. For unsupervised factors see mofa-integration; for the method decision see integration-design; for cross-validation theory see machine-learning/model-validation.

aradotso-trending-skills Skill

AI-powered penetration testing assistant using local LLM (metatron-qwen via Ollama) on Parrot OS Linux

aradotso-trending-skills Skill

Expert skill for using HY-World 2.0, Tencent's multi-modal world model for reconstructing, generating, and simulating 3D worlds from text, images, and video.

aradotso-trending-skills Skill

AI agent skill for using deepsec, the agent-powered security vulnerability scanner for large codebases

aradotso-trending-skills Skill

Parse HWP, HWPX, and PDF Korean documents to Markdown using kordoc — supports CLI, programmatic API, and MCP server integration.

aradotso-trending-skills Skill

Feed-forward 3D foundation model for streaming scene reconstruction using Geometric Context Transformer

gptomics Bundle

Detects putative ligand-binding pockets and druggable cavities de novo on an apo protein structure with fpocket, P2Rank, CASTp, and DoGSiteScorer, ranking them by druggability/ligandability score. Use when detecting cavities on an apo structure with no bound ligand; choosing geometric pocket enumeration (fpocket alpha-spheres, CASTp) vs ML ligandability scoring (P2Rank, DoGSiteScorer); recognizing that a geometric cavity is a hypothesis, not automatically a functional or druggable site (may be a crystal-additive or non-functional cleft); knowing druggability scores were trained on holo sets and under-detect apo, shallow, and cryptic pockets; detecting cryptic or transient pockets over an MD or conformational ensemble (mdpocket); and detecting on a predicted model whose pocket-lining rotamers are the least reliable atoms. Keywords binding site, pocket, cavity, druggability, ligandability, fpocket, P2Rank, CASTp, DoGSiteScorer, apo, cryptic pocket, alpha sphere, mdpocket.

gptomics Bundle

Detects differential alternative splicing between conditions using rMATS-turbo (binomial LRT on junction counts), leafcutter (Dirichlet-multinomial GLM on intron clusters), MAJIQ V3 deltapsi/HET (Bayesian posterior on LSVs), SUPPA2 (empirical-null on TPM-derived PSI), or Shiba (junction-imbalance-corrected, 2025 SOTA at low coverage). Reports FDR-corrected significance and delta PSI effect sizes. Tools differ in statistical model, annotation dependence, calibration regime, and replicate-count requirements. Use when comparing splicing patterns between treatment groups, tissues, or disease states.

gptomics Bundle

Model gene-family birth-death dynamics across a species tree using CAFE5 (Mendes et al 2020 Bioinformatics 36:5516 gamma-distributed rate categories), CAFE5-error (annotation-error-aware), Count (Csurös 2010 ancestral state reconstruction), BadiRate (Librado 2012 likelihood + parsimony), DupliPHY-Family, and ALE/AleRax (for per-family DTL; see [[gene-tree-species-tree-reconciliation]]). Test lineage-specific gene-family expansions and contractions, distinguish biological dynamics from annotation artifacts, account for assembly fragmentation, identify functional enrichment in expanded / contracted families. Use when correlating gene-family changes with phenotype evolution, ranking lineages by adaptive gene-family-rate shifts, post-WGD dosage-balance analysis, or building Birth-death models from OrthoFinder presence/absence matrices.

gptomics Bundle

Build publication-quality figures with matplotlib using the object-oriented Figure/Axes API, constrained_layout, rcParams customization, TrueType (Type-42) font embedding for journal submission, and CVD-safe palettes. Covers seaborn integration, common chart types, axis formatting, and the small gotchas that distinguish reproducible matplotlib from notebook scratch. Use when producing publication figures in Python — RNA-seq scatter, single-cell embeddings, generic biological plotting.

gptomics Bundle

Structures biological experiments so inference is valid by construction, covering Fisher's principles (randomization, replication, local control), the experimental-vs-observational unit distinction and pseudoreplication (Hurlbert 1984; Lazic 2018), randomization mechanics (complete, restricted, stratified, rerandomization, run-order), blocking layouts (randomized complete block, Latin square, incomplete block), factorial designs and interactions, and the split-plot/nested error strata hidden inside multi-batch genomics. Use when deciding the experimental unit and what counts as a replicate, planning randomization and run order, choosing a blocked/factorial/split-plot/nested layout, avoiding pseudoreplication in cell-culture or animal studies, or specifying the random-effects structure of the analysis model. For assigning samples to sequencing batches/lanes/plates and batch-effect correction see experimental-design/batch-design; for regulated clinical-trial randomization see clinical-biostatistics.

oimiragieo Bundle

Multiagent AI system for scientific research assistance that automates research workflows from data analysis to publication. This skill should be used when generating research ideas from datasets, developing research methodologies, executing computational experiments, performing literature searches, or generating publication-ready papers in LaTeX format. Supports end-to-end research pipelines with customizable agent orchestration.

aradotso-trending-skills Skill

Extract structured PII spans from text using the OpenAI Privacy Filter 1.5B model reversed — returns what, where, and which type instead of masking.

aradotso-trending-skills Skill

Interactive TUI dashboard for visualizing Claude Code token usage, costs, and task breakdowns by project, model, and activity type.

aradotso-trending-skills Skill

Read-only observability dashboard plugin for Hermes Agent — journeys, crossings, guideposts, and reports.

aradotso-trending-skills Skill

Expertise in using open-multi-agent, a TypeScript framework for building production-grade multi-agent AI teams with task scheduling, dependency graphs, and inter-agent communication.

aradotso-trending-skills Skill

OpenGame is an open-source agentic framework for end-to-end web game creation from a single text prompt, using LLMs, Game Skill (Template + Debug), and headless browser evaluation.

aradotso-trending-skills Skill

Lossless DFlash speculative decoding for MLX on Apple Silicon — 1.7–4x faster LLM inference using block diffusion drafting with target model verification.

aradotso-trending-skills Skill

Agent skill to convert any arxiv paper into a citation-anchored, working Python implementation with ambiguity auditing

gptomics Bundle

Compares how a rhythm CHANGES between conditions, genotypes, treatments, tissues, or ages (differential rhythmicity), classifying each feature as gain-of-rhythm, loss-of-rhythm, phase change, amplitude change, unchanged-rhythmic, or arrhythmic-in-both, and distinguishing differential EXPRESSION (condition main effect) from differential RHYTHMICITY (condition x time interaction). Uses model-based approaches that borrow strength across conditions - LimoRhyde (sin/cos interaction terms in a limma/edgeR/DESeq2 design), dryR (BIC model selection across >=2 conditions), compareRhythms (direct gain/loss/change/same classification), DODR, CircaCompare - instead of the detect-then-Venn anti-pattern that overestimates reprogramming. Use when testing whether rhythms differ between conditions/genotypes/tissues/ages, classifying gain/loss/phase/amplitude change, or separating differential expression from differential rhythmicity. Not for detecting rhythms in one condition (see temporal-genomics/circadian-rhythms).

oimiragieo Bundle

Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.

oimiragieo Bundle

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

oimiragieo Bundle

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).

g1joshi Skill

LangChain LLM application framework with chains and agents. Use for LLM orchestration.

aradotso-trending-skills Skill

Expertise in See-through, a framework for single-image layer decomposition of anime characters into manipulatable 2.5D PSD files using diffusion models.

oimiragieo Bundle

Decision matrix for selecting multi-agent topologies (Supervisor, Swarm, Hierarchical, Conductor) with token economics, failure modes, and escalation paths

g1joshi Skill

OCaml functional programming with type inference. Use for .ml files.

g1joshi Skill

LlamaIndex data framework for LLMs. Use for RAG applications.

gptomics Bundle

Assigns pathogen lineages (SARS-CoV-2 Pangolin UShER mode; Nextclade clade + QC; pango-designation alias resolution) and tracks variant frequencies over time using Nextstrain (Augur + Auspice), wastewater deconvolution (Freyja, COJAC, alcov, lineagespot), lineage-fitness modelling (multinomial logistic), and recombinant detection (3SEQ, RDP4, Bolotie). Covers Pangolin pangolin-data and Nextclade dataset version pinning (mandatory; lineage-defining mutations change with dataset), Freyja barcode forward-only date constraint, ARTIC primer scheme churn (V3/V4/V4.1/V5.3.2/Midnight) with dropout regions, and recombinant X-prefix designation lag. Use when assigning Pango lineages and Nextclade clades to viral consensus sequences, building Nextstrain Augur surveillance pipelines, deconvolving wastewater into lineage frequencies with Freyja, tracking lineage frequencies over time, handling ARTIC primer dropouts, or running surveillance for SARS-CoV-2/influenza/Mpox/RSV/H5N1/measles.

gptomics Bundle

Tests individual CpG sites for differential methylation (DMC/DMP) from bisulfite sequencing counts or array/continuous beta-value matrices. Covers the count-vs-continuous fork that dictates the model, beta-value vs M-value logit (Du 2010), beta-binomial overdispersion count models (DSS, methylKit, MOABS, RADMeth) for sequencing, limma moderated-t on M-values (eBayes trend/robust) for arrays, the bare-beta Welch t-test caveat, coverage-as-precision coupling, delta-beta effect size, BH-FDR with the neighboring-CpG dependence problem, EWAS genome-wide thresholds, and differential variability (DiffVar/iEVORA). Use when comparing per-CpG methylation between groups from WGBS/RRBS/targeted bisulfite or 450K/EPIC arrays, choosing a per-site test, or scanning for variance (not just mean) differences. For region-level aggregation see dmr-detection; for covariate/cell-fraction strategy and genomic inflation see ewas-design.

oimiragieo Bundle

Search and retrieve academic papers from arXiv.org using WebFetch and Exa. No MCP server required - uses existing tools to access arXiv API directly.

oimiragieo Bundle

Automated LLM-driven hypothesis generation and testing on tabular datasets. Use when you want to systematically explore hypotheses about patterns in empirical data (e.g., deception detection, content analysis). Combines literature insights with data-driven hypothesis testing. For manual hypothesis formulation use hypothesis-generation; for creative ideation use scientific-brainstorming.

oimiragieo Bundle

High-performance reinforcement learning framework optimized for speed and scale. Use when you need fast parallel training, vectorized environments, multi-agent systems, or integration with game environments (Atari, Procgen, NetHack). Achieves 2-10x speedups over standard implementations. For quick prototyping or standard algorithm implementations with extensive documentation, use stable-baselines3 instead.

oimiragieo Bundle

Start and manage the full heartbeat ecosystem for agent-studio. Registers all 7 heartbeat loops plus auto-reschedule task via CronCreate to keep the agent ecosystem healthy, indexed, informed, and connected.

oimiragieo Bundle

Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general programming, or ML/data-science tasks.