Web & Frontend

withoneai Skill

HTML/CSS to Image through One

pku-yuangroup Bundle

ADMET-guided genetic molecule optimization workflow from seed SMILES; use when the agent needs to build or run an RDKit/SA-Score/ADMET-AI GA pipeline for molecule optimization, enforce molecule lineage logs, render optimization-history HTML dashboards, and write candidate triage reports.

pku-yuangroup Bundle

Runs all-in-one FASTQ preprocessing with fastp in a single pass - adapter trimming via paired-end overlap analysis, quality/length filtering, 2-color poly-G removal, base correction, optional dedup/UMI/merge, and HTML/JSON reports. Use when preprocessing bulk Illumina data and wanting one fast tool instead of separate Cutadapt, Trimmomatic, and FastQC steps. For precise small-RNA/amplicon adapters use adapter-trimming; for molecule-accurate UMI dedup use umi-processing.

pku-yuangroup Bundle

Orchestrates gene regulatory network inference from processed single-cell data to regulons and in-silico perturbation, via pySCENIC (RNA-only GRNBoost2 -> cisTarget -> AUCell), SCENIC+ (multiome cisTopic -> pycistarget -> eGRN), and CellOracle perturbation. Use when recognizing that an inferred GRN is UNDIRECTED by default and reporting only the evidence tier delivered (co-expression vs motif-pruned vs enhancer-resolved vs perturbation), matching species/assembly/namespace across the TF-list + cisTarget DB + motif2TF annotation, feeding RAW counts of the cleaned/doublet-free/batch-controlled cells (never imputed/batch-corrected values), running the cisTarget pruning that buys directionality (modules are not regulons without it), or choosing the RNA-only vs multiome path. Hands mechanism to the gene-regulatory-networks component skills; not a re-teach of any single step.

pku-yuangroup Bundle

Orchestrates imaging mass cytometry from raw MCD acquisitions to patient-level spatial analysis, chaining steinbock preprocessing, Mesmer/Cellpose segmentation, single-cell quantification, phenotyping, and squidpy spatial statistics. Use when committing the panel + segmentation frame + pixel size (every per-cell number is a mask-bounded pixel average), compensating channel spillover on PIXELS before segmentation but running REDSEA lateral-spillover on the per-cell table AFTER segmentation, using arcsinh cofactor 1 (not the suspension-CyTOF 5), and aggregating to the PATIENT before any cross-condition test (cells and ROIs from one patient are not independent replicates). Hands mechanism to the imaging-mass-cytometry component skills; not a re-teach of any single step.

pku-yuangroup Bundle

Orchestrates the end-to-end bulk RNA-seq differential-expression pipeline from FASTQ to an annotated DE gene table, chaining fastp QC/trim, Salmon (decoy-aware) or STAR+featureCounts quantification, tximport gene-level collapse, DESeq2/edgeR/limma-voom testing, apeglm shrinkage, and VST-based visualization. Use when committing the reference release and gene-ID namespace once for the whole run, sequencing steps in the defensible order (tximport before DE, raw counts into the model, VST only for viz/clustering), choosing alignment-free vs align-then-count and the DE engine, setting strandedness correctly, keeping batch in the design instead of correcting-then-testing, or handing the signed ranking statistic to downstream enrichment. Hands mechanism to the component skills; not a re-teach of any single step.

pku-yuangroup Bundle

Orchestrates the GWAS pipeline from genotypes to association results, chaining PLINK2 QC (variant-then-sample missingness, controls-only HWE, KING relatedness), panel harmonization + joint phasing/imputation to dosages, long-range-LD-excluded PCA, and an engine chosen by sample structure (PLINK2-GLM / regenie / SAIGE / BOLT-LMM), with LDSC-intercept diagnostics. Use when committing the genome build + ancestry-matched imputation panel once (ancestry match > panel size), running the strand/allele harmonization gate (drop intermediate-frequency palindromes), imputing cases+controls TOGETHER on dosages, excluding long-range-LD regions before PCA, choosing an LMM when relatedness/structure is present (PCs cannot remove a covariance), or separating polygenicity from confounding via the LDSC intercept. Hands mechanism to the population-genetics and phasing-imputation component skills; not a re-teach of any single step.

pku-yuangroup Bundle

Analyze TF motif accessibility variability across samples or single cells using chromVAR. Use when identifying TF motifs whose accessibility correlates with conditions, computing per-sample motif z-scores after matched background correction, comparing to ArchR / Signac equivalents, or distinguishing motif-accessibility signal from per-site footprinting.

pku-yuangroup Bundle

Infer cis-regulatory connections (peak-to-peak co-accessibility) from scATAC-seq using Cicero, ArchR getCoAccessibility, or SCENIC+. Use when linking enhancer accessibility to promoter accessibility, identifying enhancer-gene pairs from chromatin alone (without paired RNA), running gene-regulatory inference combining ATAC + RNA, or comparing predicted regulatory contacts against Hi-C/Micro-C ground truth.

pku-yuangroup Bundle

Process and analyze single-cell ATAC-seq data with Signac, ArchR, SnapATAC2, or Cell Ranger ATAC. Use when handling 10X scATAC or 10X Multiome (paired RNA+ATAC) data, performing per-cell QC, choosing between ArchR/Signac/SnapATAC2 ecosystems, building per-cluster consensus peaksets, integrating with paired scRNA-seq, doublet detection (AMULET vs ArchR vs scDblFinder), or running pseudobulk differential accessibility per cluster.

pku-yuangroup Bundle

Runs parameterized Jupyter notebooks as reproducible batch report generators with papermill, renders them to HTML/PDF with nbconvert, aggregates results across samples, and makes notebook outputs trustworthy. Use when generating per-sample analysis reports, executing a notebook template across many datasets, or fixing notebooks that do not reproduce.

pku-yuangroup Bundle

Build a differential-ready consensus peakset from per-replicate ATAC-seq peaks using iterative overlap removal, fixed-width re-centering, and majority-rule overlap. Use when generating a stable peak coordinate system for downstream differential accessibility, ML feature engineering, cross-sample comparison, or fixed-width peak counts; covers Corces 2018 iterative overlap (501 bp), DiffBind summit re-centering, and ENCODE consistency rules.

pku-yuangroup Bundle

Orchestrates the end-to-end bulk ATAC-seq pipeline from FASTQ to differential accessibility and TF footprints, chaining Nextera-aware fastp QC, Bowtie2 alignment, chrM removal, dedup, a single Tn5 +4/-5 shift, MACS3 peak calling, Corces fixed-width consensus, DiffBind/csaw differential accessibility, and TOBIAS footprinting. Use when committing the reference build + blacklist once, recognizing ATAC has NO input control (the shift-extend model IS the background), applying the Tn5 shift exactly once (never combining -f BAMPE with --shift/--extsize), removing chrM before calling, building a fixed-width consensus so per-sample counts are comparable, or choosing MACS3 vs Genrich vs HMMRATAC. Hands mechanism to the atac-seq component skills; not a re-teach of any single step.

pku-yuangroup Bundle

Orchestrates the end-to-end ChIP-seq pipeline from FASTQ to blacklist-filtered, annotated peaks, chaining fastp QC, Bowtie2 alignment, pre-dedup library-complexity QC (NRF/PBC), duplicate removal, chrM + ENCODE-blacklist filtering, MACS3 peak calling against a matched input, IDR/consensus reproducibility, deepTools signal tracks, and ChIPseeker annotation. Use when committing the reference build + blacklist version + effective genome size once, pairing each IP with its matched control, computing complexity metrics BEFORE dedup, choosing narrow vs broad and MACS3 vs SEACR/Genrich, keeping per-replicate peaks for IDR, or avoiding depth-normalization that erases a spike-in global shift. Hands mechanism to the chip-seq component skills; not a re-teach of any single step.

pku-yuangroup Bundle

Orchestrates the end-to-end spatial transcriptomics pipeline from Space Ranger / vendor output to spatial domains and statistics, branching FIRST on platform class (imaging in-situ Xenium/MERFISH/CosMx vs sequencing/capture Visium/Visium HD/Slide-seq). Use when deciding segmentation-vs-deconvolution and the QC floors from the platform class, committing the coordinate/image-registration frame and panel identity, deconvolving multi-cell spots against an annotated scRNA reference (never relabeling spot clusters as cell types), building the spatial neighbor graph on PHYSICAL not expression space, gating spatially-variable genes on FDR, or using a real domain method (BANKSY/BayesSpace/STAGATE) rather than clustering the spatial graph alone. Hands off deconvolution and cell-cell communication to the component skills; not a re-teach of any single step.

pku-yuangroup Bundle

Sequence-based deep learning for ATAC-seq using chromBPNet, BPNet, scBasset, or Enformer. Use when correcting Tn5 bias with neural networks beyond k-mer models, predicting per-base accessibility profiles, scoring in silico variant effects at GWAS or rare-variant SNPs, discovering motifs via DeepLIFT/TF-MoDISco from a trained model, or generating cell-type-specific accessibility predictions for unobserved cell states.

pku-yuangroup Bundle

Creates reproducible R Markdown analysis reports (HTML, PDF, Word) with knitr, covering the render pipeline, the interactive-vs-knit session trap, cache invalidation, bookdown cross-references, parameterization, and environment pinning. Use when generating an R-based analysis report, debugging a report that knits differently than it runs interactively, or fixing caching or cross-references.

pku-yuangroup Bundle

Analyze single-cell ATAC-seq with Signac/ArchR (R) and SnapATAC2 (Python alternative). Use when processing scATAC fragments, choosing a framework, calling consensus peaks, running TF-IDF/LSI while diagnosing the depth component, scoring chromVAR motif deviations against GC-matched backgrounds, detecting homotypic vs heterotypic doublets, or deciding whether to binarize the count matrix.

pku-yuangroup Bundle

Orchestrates the end-to-end germline short-variant pipeline from FASTQ to a filtered, normalized, benchmarked VCF, chaining QC/trim, BWA-MEM2 alignment, duplicate marking, optional BQSR, calling (bcftools/GATK HaplotypeCaller/DeepVariant/DRAGEN), normalization, site+genotype filtering, annotation, and hap.py/vcfeval benchmarking. Use when deciding the pipeline-wide reference-genome commitment (GRCh38 analysis set vs T2T, ALT/decoy handling), sequencing the steps in the defensible order (normalize BEFORE annotate, filter site- then genotype-level), choosing the calling engine and single-sample vs cohort joint-calling, picking a filtering strategy by cohort size, or benchmarking stratified within GIAB confident regions. Hands off mechanism to the variant-calling and read-alignment component skills; not a re-teach of any single step.

pku-yuangroup Bundle

Orchestrates the end-to-end 10x Multiome (paired scRNA + scATAC) pipeline from Cell Ranger ARC output to a jointly-embedded, annotated object, chaining per-modality QC, AMULET fragment-based ATAC doublet detection, per-modality normalization (RNA SCT/PCA; ATAC TF-IDF/LSI), WNN (or MultiVI) integration, joint clustering, RNA-based annotation, and LinkPeaks peak-to-gene linking. Use when enforcing the shared cell-barcode intersection between modalities (cellranger-ARC not -atac), keeping per-modality QC/doublets before the joint embedding, dropping the depth-correlated LSI component, annotating identity from RNA (ATAC is regulatory state), treating peak-to-gene links as correlational hypotheses, or aggregating to pseudobulk for cross-condition DE. Hands mechanism to the single-cell and atac-seq component skills; not a re-teach of any single step.

pku-yuangroup Bundle

Orchestrates genomic-epidemiology outbreak investigation from pathogen isolates to transmission networks, forking bacterial (snippy -> Gubbins recombination-masking -> IQ-TREE -> TreeTime -> TransPhylo) vs viral (Nextstrain/augur), with parallel MLST typing (cgMLST delegated to epidemiological-genomics/pathogen-typing) and AMR surveillance. Use when committing ONE reference genome for SNP calling (every isolate and distance inherits its coordinates), applying MANDATORY Gubbins recombination-masking on core.full.aln before the tree for recombining bacteria (skipping it inflates the clock 2-5x), gating time-scaling on a temporal-signal test (TempEst R2 >= 0.3), using a pathogen- AND population-specific cluster threshold rather than a universal SNP cutoff, or pinning pangolin-data/Nextclade/Freyja versions for the viral route. Hands mechanism to the epidemiological-genomics component skills; not a re-teach of any single step.

pku-yuangroup Bundle

Orchestrates the end-to-end single-cell RNA-seq pipeline from 10x Cell Ranger output to annotated cell types, chaining ambient-RNA removal, doublet detection, MAD-adaptive QC, normalization, integration, clustering, marker annotation, and (separately) pseudobulk DE + differential abundance. Use when honoring the made-once counting commitments (reference build/Ensembl vintage, --include-introns, cell-calling, feature namespace), ordering correct-then-detect-then-normalize (ambient before doublet before normalize), running per-sample QC before merge, integrating-then-clustering (never testing on integrated values), aggregating to pseudobulk for condition DE instead of cells-as-replicates, or pairing DE with differential abundance. Hands mechanism to the single-cell component skills; not a re-teach of any single step.

pku-yuangroup Bundle

Orchestrates the end-to-end bulk short-read alternative-splicing pipeline from FASTQ to differential splicing, chaining fastp QC, cohort-consistent STAR 2-pass alignment (one shared junction DB), junction QC, event-level differential splicing (rMATS-turbo + leafcutter, optional MAJIQ V3), parallel isoform-level DTU (Salmon -> tximport dtuScaledTPM -> DRIMSeq/DEXSeq -> stageR), and sashimi visualization. Use when committing the annotation GTF and a shared 2-pass junction database for the whole cohort, keeping the analysis at splice-aware resolution (never collapsing to gene), choosing event-level vs isoform-level DTU and reconciling them, applying the stageR two-stage gene->transcript FDR, or off-ramping to splice-variant / outlier / long-read / single-cell splicing. Hands mechanism to the alternative-splicing component skills; not a re-teach of any single step.

pku-yuangroup Bundle

End-to-end flow, spectral, and mass cytometry (CyTOF) pipeline from raw FCS files to differentially abundant/expressed cell populations. Orchestrates the read -> compensate/unmix -> transform -> QC -> doublet-removal -> cluster-or-gate -> annotate -> diffcyt DA/DS chain with flowCore/CATALYST/diffcyt, branching on instrument type and on clustering-vs-gating. Use when processing a cytometry experiment end-to-end, deciding the pipeline path for an instrument, or wiring the flow-cytometry component skills into one analysis with valid sample-level statistics.

pku-yuangroup Bundle

Orchestrates bottom-up proteomics from a search engine's output (MaxQuant/FragPipe/DIA-NN) to differential protein abundance with limma/DEqMS/MSstats. Use when committing the search database + acquisition mode (DDA vs DIA) up front, re-controlling FDR at PSM AND peptide AND protein-group level (not just PSM), removing contaminant/reverse rows and inspecting RAW distributions before normalizing, bridging cross-plex TMT with an IRS reference channel, modeling MNAR missingness rather than downshift-imputing on/off proteins, batching as a covariate (not pre-subtracted), and testing with treat()/DEqMS. Hands mechanism to the proteomics component skills; not a re-teach of any single step.

revfactory Bundle

WCAG 2.1/2.2 accessibility verification checklist and automated audit methodology skill. Use for requests like 'verify accessibility', 'WCAG check', 'check contrast ratio', 'ARIA audit', 'keyboard accessibility', 'screen reader test', etc. Note: running actual assistive technology (JAWS/NVDA), legal consultation, and accessibility certification issuance are outside the scope of this skill.

revfactory Bundle

Checklist and best practices for validating CLI tool user experience. Use this skill for 'CLI UX validation', 'usability check', 'output format verification', 'error message review', 'interaction pattern inspection', and other CLI UX quality checks. Note: GUI usability testing and accessibility certification are outside the scope of this skill.

revfactory Bundle

A skill for systematically generating and validating CSS/XPath selectors for web page data extraction. Use for requests like 'create selectors', 'CSS selectors', 'write XPath', 'data extraction patterns', 'parsing rules', etc. Note: directly operating browser DevTools is outside the scope of this skill.

revfactory Bundle

A full development pipeline where an agent team collaborates to develop fullstack web apps through requirements analysis, design, frontend, backend, testing, and deployment. Use this skill for requests like 'build me a web app', 'web service development', 'SaaS development', 'CRUD app', 'build a dashboard', 'admin page', 'signup/login feature', 'REST API development', 'fullstack project', 'Next.js app', and other general web application development. Also supports feature additions and refactoring for existing codebases. However, mobile apps (React Native/Flutter), desktop apps (Electron), game development, and ML/AI model training are outside this skill's scope.

revfactory Bundle

React/Next.js component design pattern library. Provides Compound/Render Props/HOC/Custom Hooks patterns, state management strategies (Zustand/React Query/Context), and folder structure conventions as a frontend-dev extension skill. Use for requests like 'component patterns', 'React patterns', 'state management', 'folder structure', 'Custom Hook', 'component separation', and other frontend architecture design tasks. However, actual code implementation or backend logic is outside this skill's scope.

revfactory Bundle

Full mobile app development pipeline. An agent team collaborates to perform UI/UX design, native/cross-platform code generation, API integration, and store deployment preparation. Use this skill for requests like 'build me a mobile app', 'app development', 'iOS app', 'Android app', 'Flutter app', 'React Native app', 'app UI design', 'app store deployment', 'app API integration', and other general mobile app development. Also supports API integration and store deployment for existing codebases. However, actual build/compilation (Xcode, Gradle), actual store submission, and CI/CD pipeline setup are outside this skill's scope.

revfactory Bundle

Mobile UX design pattern library. Provides iOS HIG/Material Design 3 guidelines, navigation patterns, gesture interactions, responsive layouts, and accessibility checklists as a ux-designer extension skill. Use for requests like 'mobile UX', 'iOS guidelines', 'Material Design', 'navigation patterns', 'gestures', 'design tokens', 'mobile accessibility', and other mobile UI/UX design tasks. However, actual design file creation or code implementation is outside this skill's scope.

ndpvt-web Skill

Boost Android app test coverage beyond the 30% activity ceiling using agentic static analysis of Smali code, component transition graphs, activation condition inference, and Frida dynamic instrumentation script generation. Use when: 'increase Android app test coverage', 'generate Frida scripts for unreachable activities', 'analyze APK activation conditions', 'break through coverage barriers in mobile testing', 'instrument Android app for GUI fuzzing', 'find unreachable activities in Android app'.

ndpvt-web Skill

Predict and simulate GUI state transitions by generating renderable HTML/CSS/SVG code from screenshots and user actions. Use when asked to: 'simulate what happens when I click this button', 'predict the next UI state', 'generate HTML that reproduces this screenshot', 'build a GUI world model', 'create a visual sandbox for UI testing', 'convert a mobile screenshot to interactive HTML'.

ndpvt-web Skill

Build agentic LLM-driven robotic manipulation pipelines using the ALRM framework pattern: a ReAct-style reasoning loop with dual execution modes (Code-as-Policy for direct code generation, Tool-as-Policy for iterative tool-based execution). Generates modular robot control code with closed-loop planning, observation, and replanning. Trigger phrases: "robot manipulation agent", "agentic robot control", "ReAct robot planner", "code-as-policy generation", "tool-as-policy robot", "LLM robotic pipeline"

ndpvt-web Skill

Build semantic component interfaces that expose UI components as structured tool primitives for AI agent automation. Use when: 'make my UI agent-friendly', 'add CI4A interfaces to components', 'create semantic wrappers for web components', 'build agent-accessible UI toolkit', 'expose component actions as tools', 'wrap Ant Design components for agent use'.