Web & Frontend

ndpvt-web Skill

Diagnose and attribute faults in compound AI systems (multi-model pipelines) using SETA's modular robustness testing framework. Applies perturbations, traces execution through each component, computes per-component metamorphic relation scores, and statistically attributes system failures to specific modules. Use when: 'find which model in my pipeline is failing', 'robustness test my multi-model system', 'trace error propagation in my AI pipeline', 'attribute faults in my compound AI system', 'which component is causing my pipeline to break under noise', 'test robustness of my ML pipeline'.

pku-yuangroup Bundle

Orchestrates an end-to-end long-read structural-variant pipeline - basecalling to minimap2 alignment (platform-matched preset) to Sniffles2/cuteSV/pbsv calling to optional assembly-based calling (dipcall/PAV) to two-step .snf cohort merging to Truvari benchmarking - chaining ONT and PacBio HiFi runs while handing the SV signal mechanism off to the component skills. Use when running a long-read SV workflow from reads to a benchmarked callset, choosing the minimap2 preset and SV caller by platform and goal, deciding when long reads are worth it for the insertions and repeat-mediated SVs short reads physically miss, building a joint-genotyped cohort with the two-step .snf design, or parameterizing a Truvari benchmark against GIAB HG002 Tier 1 plus CMRG. Not for the SV signal mechanism itself (see variant-calling/structural-variant-calling) or short-read SV.

pku-yuangroup Bundle

Orchestrates the end-to-end bisulfite/EM-seq methylation pipeline from FASTQ to differentially methylated regions, chaining Trim Galore/fastp QC, Bismark alignment + deduplication, methylation calling, methylKit coverage-filtering/normalization, and selection-aware DMR detection (dmrseq/DSS). Use when gating the run on bisulfite conversion (lambda + pUC19 controls) BEFORE any beta value, committing the genome build + library directionality once, keeping mate-overlap deduplicated (--no_overlap), M-bias-trimming from the plot, filtering coverage before testing, choosing a count model (beta-binomial/DSS) over a bare-beta t-test, or using a region-selection-aware FDR (dmrseq/DSS) rather than raw methylKit tiles. Hands mechanism to the methylation-analysis component skills; not a re-teach of any single step.

pku-yuangroup Bundle

Orchestrates VERTICAL bulk multi-omics integration (RNA + protein + methylation on the SAME samples) from harmonization to a validated result, routing to MOFA2 (shared factors), mixOmics/DIABLO (predictive signature), or SNF (patient subtypes). Use when confirming the correspondence is vertical (not horizontal same-features-different-cohorts), joining on a stable sample primary key rather than cbind on assumed row order, normalizing each omic in its OWN space and equalizing block variance BEFORE stacking (or the widest omic hijacks every shared factor), correcting batch ONCE in one place, and validating in a HELD-OUT cohort because in-cohort CV at n<<p is optimistically biased. Hands mechanism to the multi-omics-integration component skills; not a re-teach of any single step.

pku-yuangroup Bundle

Calls significant loops from protein-directed and targeted 3C assays (HiChIP, PLAC-seq, Capture Hi-C/PCHi-C, ChIA-PET) where the contact background is peak-anchored and coverage-biased, so generic Hi-C loop callers (cooltools dots, Juicer HiCCUPS) use the wrong null. Covers FitHiChIP (config-driven coverage+distance-decay spline regression, peak-to-peak vs peak-to-all foreground, loose vs stringent background, coverage vs ICE bias), MAPS (positive Poisson regression on bias factors for PLAC-seq/HiChIP), hichipper (restriction-site-distance bias model + library QC), CHiCAGO (Delaporte two-component Brownian+technical background for asymmetric bait x other-end Capture Hi-C), the with/without separate-ChIP anchor decision, and differential loops via diffloop. Use when calling loops from HiChIP/PLAC-seq/Capture Hi-C, choosing FitHiChIP/MAPS/CHiCAGO, picking peak-to-all vs peak-to-peak, setting the loop FDR, supplying ChIP peaks as anchors, QCing a HiChIP library, or comparing loops between conditions.

pku-yuangroup Bundle

Orchestrates the untargeted LC-MS metabolomics pipeline end-to-end (xcms 4.x feature extraction, QC/drift/normalization, confidence-stratified annotation, permutation-validated statistics, background-aware pathway mapping), naming what each stage decides and where it silently fails. Use when running a full LC-MS metabolomics study from raw mzML to enriched pathways and needing the honest handoffs between stages. Each stage defers to its component skill for parameters and traps; for stable-isotope flux (a separate branch, not this untargeted flow) see metabolomics/isotope-tracing.

pku-yuangroup Bundle

Orchestrates the cell-free DNA / liquid-biopsy pipeline from plasma sequencing to tumor monitoring, forking tumor-naive (screening) vs tumor-informed (MRD), and chaining pre-analytic QC, UMI/duplex error-suppression (fgbio), fragment QC, ichorCNA tumor fraction (sWGS) or VarDict low-VAF calling (panel), CHIP subtraction against matched WBC, optional fragmentomics/methylation, and longitudinal tracking. Use when treating pre-analytics as the irreversible sensitivity ceiling (tube/time-to-plasma/hemolysis), running error-suppression BEFORE calling (single-strand consensus does not remove deamination; only duplex does), reporting a VAF only with input genome-equivalents (TF ~ 2x VAF only for clonal-het-diploid), subtracting CHIP before reporting somatic, or keeping tube/panel/pipeline identical across a longitudinal MRD series. Hands mechanism to the liquid-biopsy component skills; not a re-teach of any single step.

pku-yuangroup Bundle

Creates sashimi-style plots showing RNA-seq read coverage and splice junction counts using ggsashimi (general-purpose, condition-grouped overlays), rmats2sashimiplot (rMATS-output-aware), MAJIQ-VOILA (LSV posteriors interactive HTML), leafviz (leafcutter clusters Shiny), Jutils (tool-agnostic heatmaps and sashimi for rMATS/leafcutter/MntJULiP/MAJIQ output), or pyGenomeTracks (multi-track publication figures). Tool choice depends on the upstream differential-splicing tool's output format and the publication vs interactive use case. Use when visualizing specific splicing events, validating differential splicing calls, or producing publication-quality figures.

pku-yuangroup Bundle

Designs novel molecules using REINVENT 4 (de novo, scaffold decoration, linker design, R-group, molecular optimization), MolMIM, Diffusion-based generators (DiGress, DiffSMol), and JT-VAE with explicit handling of multi-parameter optimization (MPO), goal-directed scoring functions, transfer/reinforcement/curriculum learning, synthetic accessibility scoring, and chemical space exploration vs exploitation. Use when designing new chemical matter against a target, decorating a scaffold, linking fragments, or optimizing a hit for multiple ADMET / activity properties simultaneously.

pku-yuangroup Bundle

Identify differentially accessible chromatin regions across conditions using DiffBind, csaw, DESeq2, or edgeR. Use when comparing ATAC-seq accessibility between treatment groups, choosing between consensus-peak vs sliding-window approaches, picking the correct normalization (full library vs reads-in-peaks), correcting batch with SVA/RUVseq, or interpreting log2FC and FDR thresholds in a chromatin context.

pku-yuangroup Bundle

Orchestrates genome annotation from assembled contigs to functional annotation, forking prokaryotic (Bakta one-step, genetic-code table from GTDB-Tk) vs eukaryotic (RepeatMask -> BRAKER3 -> functional -> ncRNA), then eggNOG/InterProScan functional assignment and Infernal/tRNAscan ncRNA. Use when committing the pro-vs-eukaryotic path and the genetic-code table from taxonomy (never guessing), annotating ONLY a decontaminated QC-passed assembly (CheckM2 before prokaryotic annotation is non-negotiable), committing the evidence set (RNA-seq + protein drives BRAKER3 training), soft-masking with a curated repeat library before gene prediction, or pinning the tool + DB version for any pangenome comparison. Hands mechanism to the genome-annotation component skills; not a re-teach of any single step.

revfactory Bundle

Visual Storytellingof Story Design, Text writing, AI Image (Gemini), HTML Layout, Integration Editing an agent team collaborates to production to line. 'Visual Story ', 'in Planning', 'Image+ combination', 'Visual in', 'Story page production', ' Story', 'Visual Planning', 'Image in', ' Story', 'Visual Narrative' etc. Imageand Text Storytelling productionin . Text Image casein Layout Integration . , video Editing, DTP, (JS ) of .

yigityildiz0 Skill

Read, create, edit, and validate Word DOCX documents while preserving structure, styles, relationships, accessibility, and existing user content. Use when DOCX is the primary input or required deliverable; prefer installed document tooling and make dependency changes only when authorized.

yigityildiz0 Skill

Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix.

yigityildiz0 Bundle

Plan, write, build, and validate strategic presentations and HTML slide decks with clear narrative, responsive layouts, design tokens, data visualization, speaker-ready copy, and accessible exports. Use for pitch decks, research presentations, product narratives, training decks, or slide-system reviews.

yigityildiz0 Skill

Official GSAP skill for React — useGSAP hook, refs, gsap.context(), cleanup. Use when the user wants animation in React or Next.js, or asks about GSAP with.

yigityildiz0 Bundle

Implement and refine accessible, responsive interfaces using an existing component system or utility CSS, with strong state coverage, semantic tokens, dark mode, and framework-aware styling. Use for component styling, Tailwind or shadcn-style workflows, responsive layouts, theme implementation, visual polish, or UI consistency reviews. Turkish triggers: arayüz stilini uygula, CSS ve görsel hiyerarşi, responsive ve erişilebilir görünüm.

yigityildiz0 Skill

Deep Vue 3 expertise for Composition API, component patterns, Pinia state management, Vue Router, performance optimization, and testing. Use when building.

yigityildiz0 Bundle

Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use.

yigityildiz0 Skill

Deep Astro expertise for island architecture, content collections, multi-framework integration, and hybrid rendering. Use when building Astro sites.

yigityildiz0 Bundle

Deep React expertise for component architecture, hooks, state management, performance optimization, and testing. Use when building React applications.

yigityildiz0 Skill

Turn a screenshot, generated design reference, or visual brief into a polished responsive interface through measurable visual analysis, implementation, and screenshot comparison. Use when visual fidelity and art direction matter for a web page or component; generate new references only when they materially improve the result and an image tool is available.

yigityildiz0 Bundle

Deep Next.js expertise for App Router, Server Components, data fetching, middleware, and deployment. Use when building Next.js applications, migrating to.

yigityildiz0 Skill

Deep Svelte 5 and SvelteKit expertise for runes reactivity, component patterns, server-side rendering, form actions, and deployment. Use when building.

yigityildiz0 Skill

CSS animation adapter patterns for HyperFrames. Use when authoring CSS keyframes, animation-delay based timing, animation-fill-mode, animation-play-state.

yigityildiz0 Skill

Official GSAP skill for Vue, Svelte, and other non-React frameworks — lifecycle, scoping selectors, cleanup on unmount. Use when the user wants animation in.

yigityildiz0 Bundle

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a.

yigityildiz0 Skill

Design, implement, critique, or validate charts and quantitative visualizations with correct encodings, annotations, accessibility, and source context. Use for chart, graph, data visualization, visualizing metrics, dashboard chart, or figure review.

yigityildiz0 Bundle

Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization.

yigityildiz0 Skill

Generate beautiful self-contained HTML pages that explain any concept visually

yigityildiz0 Bundle

Create an accessible, self-contained workflow diagram as HTML, Mermaid, or SVG from a process description. Use to map systems, data flows, decisions, ownership, handoffs, or timelines; validate structure and safely escape untrusted text. Turkish triggers: iş akışını görselleştir, Mermaid diyagramı, süreç veya sistem haritası.

yigityildiz0 Skill

Audit a web, mobile, desktop, document, or product flow for practical accessibility issues using current WCAG 2.2 AA-oriented checks, code, screenshots, and interaction evidence. Use for accessibility review, a11y audit, WCAG review, keyboard navigation, screen-reader issues, contrast, or inclusive UX. Turkish triggers: erişilebilirlik denetimi, WCAG kontrolü, klavye veya ekran okuyucu sorunu.

pku-yuangroup Bundle

Orchestrates genome-scale metabolic modeling from a protein FASTA to flux predictions, chaining CarveMe/gapseq reconstruction, memote QC, gap-filling, media-constrained FBA/FVA, gene essentiality, and context-specific models. Use when committing the reconstruction tool (which locks the identifier NAMESPACE forever - BiGG vs ModelSEED vs KEGG, no automatic translation), setting the medium BEFORE FBA (the exchange bounds ARE the medium; essentiality and gap-fill are computed relative to it), curating iteratively (stoichiometric-consistency first, then mass/charge, then directionality, then GPR) with energy-generating-cycle removal, and reading a MEMOTE score as well-formedness NOT correctness. Hands mechanism to the systems-biology component skills; not a re-teach of any single step.

pku-yuangroup Bundle

Detect allele-specific chromatin accessibility from ATAC-seq using WASP, GATK ASEReadCounter, or RASQUAL. Use when mapping cis-regulatory genetic variants from heterozygous SNPs, separating cis from trans regulation, building chromatin QTL (caQTL) maps, validating GWAS variant function with allelic imbalance, or detecting reference allele mapping bias before downstream analysis.

pku-yuangroup Bundle

Build enhancer-driven gene regulatory networks (eGRNs) by integrating single-cell RNA-seq and ATAC-seq using SCENIC+, CellOracle base GRNs, Pando, FigR, DIRECT-NET, TRIPOD, and scMEGA. Covers the accessibility-defines-enhancers principle, peak-to-gene linking and its cell-composition confound, the paired-vs-unpaired decision, and TF-region-gene eRegulon triplets. Use when analyzing 10x multiome or paired/unpaired scRNA+scATAC to infer cis-regulatory GRNs. For RNA-only regulons see scenic-regulons; for in silico TF perturbation see perturbation-simulation.

pku-yuangroup Bundle

Visualize biological networks (PPI, gene-regulatory, co-expression, pathway) with layout algorithm choice (ForceAtlas2, Fruchterman-Reingold, Kamada-Kawai, hive plots), edge bundling, community-based coloring, and reproducible seeds using NetworkX, PyVis, igraph, and Cytoscape automation. Use when rendering biological networks for static publication, interactive HTML exploration, or Cytoscape-format export.