Data & Analytics

tuyv Bundle

Query SQL database in Fabric via sqlcmd: interactive exploration, vector similarity, JSON, temporal queries, and security policy inspection on the OLTP and SQL analytics endpoints. For schema changes see the sqldb-authoring-cli skill. Triggers: "sql database in Fabric query sys.tables sqlcmd", "sql database in Fabric system view list user tables sqlcmd", "list user tables sqldb", "sys.tables sqldb", "explore sqldb schema", "vector similarity sqldb", "RAG embedding sqldb", "row level security sqldb inspect", "audit log sqldb inspect", "chat with sqldb", "export sqldb rows", "temporal as of sqldb", "json openrowset sqldb".

tuyv Bundle

Execute read-only T-SQL queries against Fabric Data Warehouse, Lakehouse SQL Endpoints, and Mirrored Databases via the MCP `fabric-sqlendpoint-execute_query` tool. Default skill for any lakehouse data query (row counts, SELECT, filtering, aggregation) unless the user explicitly requests PySpark or Spark DataFrames. Use when the user wants to: (1) query warehouse/lakehouse data, (2) count rows or explore lakehouse tables, (3) discover schemas/columns, (4) generate T-SQL scripts, (5) monitor SQL performance, (6) export results to CSV/JSON. For a Fabric notebook cell (%%sql or other notebook magics), use `spark-authoring-cli`, not this skill. Triggers: "warehouse", "SQL query", "T-SQL", "query warehouse", "show warehouse tables", "show lakehouse tables", "query lakehouse", "lakehouse table", "how many rows", "count rows", "SQL endpoint", "describe warehouse schema", "generate T-SQL script", "warehouse performance", "export SQL data", "connect to warehouse", "lakehouse data", "explore lakehouse".

tuyv Bundle

Create, update, delete, and refresh Fabric Dataflows Gen2 with write-side CLI via Fabric APIs. Build mashup.pq and queryMetadata.json, preview candidate M with executeQuery/customMashupDocument, bind connections, and configure output destinations. For saved query execution or refresh-status reads, use `dataflows-consumption-cli`. If a request explicitly insists on the Dataflows consumption or read-only path for a mutation, do not route here; let consumption refuse before any separately confirmed authoring handoff. Triggers: "create dataflow", "update dataflow", "delete dataflow", "trigger dataflow refresh", "preview Power Query M", "preview before save", "customMashupDocument", "create Fabric data source connection", "create SQL Server source REST", "POST /v1/connections", "supportedConnectionTypes", "passwordReference", "bind connection", "dataflow output destination", "dataflow write to lakehouse", "dataflow write to warehouse", "dataflow write to ADX", "DataDestinations annotation".

tuyv Bundle

Build zero-downtime database migrations — forward SQL, rollback SQL, deployment sequence. Use when asked to "write migration", "schema change", "add column", "rename table", "drop column", or "migrate safely".

withoneai Skill

Google Analytics through One

withoneai Skill

Mixpanel Warehouse Connectors through One

ndpvt-web Skill

Implement the Judge Agent Forest (JAF) pattern: evaluate and refine AI-generated outputs by judging cohorts of related query-response pairs together rather than in isolation, using peer exemplars to surface cross-instance patterns and inconsistencies. Use this skill when the user says: - "Evaluate these outputs together to find inconsistencies" - "Use a judge agent forest to refine these results" - "Cross-check these responses against each other" - "Set up cohort-based evaluation for my agent outputs" - "Find patterns across these related classifications" - "Build a judge that learns from peer examples"

pku-yuangroup Bundle

descriptive-statistics helpers — summary (mean/std/median), quantile, zscore normalization, and Pearson correlation on plain Python number lists (no pandas/numpy).

pku-yuangroup Bundle

Loads mass-spectrometry data into Python/R and strips the search engine's bookkeeping before any number is trusted -- removes decoys (REV__/Reverse), contaminants (CON__/Potential contaminant), Only-identified-by-site groups, and resolves semicolon razor/leading protein-ID ambiguity in MaxQuant proteinGroups.txt, DIA-NN report.parquet, and mzML/mzXML. Distinguishes Intensity (raw) vs LFQ intensity (MaxLFQ) vs iBAQ, treats a MaxQuant zero as missing (NaN, not log2(-inf)), and inherits the acquisition mode's missingness contract (DDA MNAR vs DIA MCAR). Use when starting an analysis from raw spectra or a search engine output. Downstream normalization and stats are differential-abundance; reporter-ion/MaxLFQ quant is quantification; protein grouping is protein-inference.

pku-yuangroup Bundle

Analyzes data-independent acquisition (DIA) proteomics by scoring reconstructed fragment-chromatogram peak groups against a decoy null with DIA-NN (library-free directDIA, library-based, or deep-learning predicted-library routes), Spectronaut, OpenSWATH, and EncyclopeDIA. Frames the deliverable around q-value LEVEL (precursor/peptide/protein-group) and CONTEXT (run vs experiment-wide/global) rather than a bare "1% FDR", and around the duty-cycle-vs-selectivity acquisition tradeoff (window design, staggered demultiplexing, diaPASEF, narrow-window Astral). Use when identifying and quantifying proteins from DIA mass spectrometry runs and filtering DIA-NN report.parquet/matrix output. Building the spectral library itself is spectral-libraries; normalization and protein roll-up is quantification; statistical testing of the matrix is differential-abundance.

pku-yuangroup Bundle

Generates and interprets per-file and cross-sample QC reports from FASTQ data with FastQC, falco, and MultiQC, covering Phred quality, per-base composition, GC, duplication, overrepresented sequences, and adapter content. Use when performing initial QC on raw sequencing reads, validating preprocessing, or judging a multi-sample cohort for outliers and batch effects. For long reads use NanoPlot; for adapter/quality remediation route to adapter-trimming, quality-filtering, or fastp-workflow.

pku-yuangroup Bundle

Identify recurrent and driver copy number alterations across a tumor cohort with GISTIC2 (G-score, Ziggurat deconstruction, focal vs broad/arm-level analysis, q-values from permutation) and quantify copy-number signatures with the Steele 2022 COSMIC framework and the Drews 2022 CINSignatures framework. Covers driver-gene localization from recurrence peaks, distinguishing focal drivers from arm-level passengers, and the caller-sensitivity caveats of copy-number signatures. Use when finding recurrently amplified or deleted regions in a cohort, localizing driver genes, separating focal from broad events, running GISTIC2, or extracting copy-number mutational signatures.

pku-yuangroup Bundle

Builds publication-ready tables - descriptive Table 1, regression and differential-expression result tables, and supplementary tables - with gtsummary, gt, flextable, and kableExtra (R) or great_tables, pandas, and tableone (Python), choosing the right statistics and the right export format. Use when making a Table 1, exporting a formatted results table for a paper, or writing a gene-symbol-safe supplementary table.

pku-yuangroup Bundle

Visualize copy number profiles, segments, allele-specific tracks, and cohort patterns from CNVkit, GATK, ASCAT, FACETS, Sequenza, and other callers. Covers genome-wide and per-chromosome log2 scatter plots, B-allele-frequency/minor-allele-fraction tracks, ideograms, cohort heatmaps, circos views, and caller-native plots. Use when creating publication CNV figures, choosing which plot answers a given question, diagnosing a wrong diploid baseline visually, displaying loss of heterozygosity, or deciding what depth-only plots cannot reveal.

pku-yuangroup Bundle

Builds and manages DIA spectral libraries as peptide query parameters (precursor m/z, a few fragment m/z plus relative intensities, normalized RT, optional CCS), covering experimental DDA, chromatogram, and in-silico predicted libraries via Koina-served Prosit, AlphaPeptDeep, MS2PIP, and DeepLC, with iRT/CiRT RT calibration, NCE tuning, format conversion (DIA-NN tsv/speclib/parquet, OpenSWATH pqp/TraML, Spectronaut, blib/dlib/elib), and library QC/merge. Use when generating, calibrating, converting, or merging a spectral library to drive a DIA search. Running the actual DIA search is dia-analysis; building from DDA identifications depends on peptide-identification; modified-peptide libraries route to ptm-analysis; quantifying the result is quantification.

pku-yuangroup Bundle

Joint genotype a cohort of per-sample gVCFs with GATK (HaplotypeCaller -ERC GVCF -> GenomicsDBImport or CombineGVCFs -> GenotypeGVCFs) or GLnexus for DeepVariant gVCFs, producing a squared-off sample-by-site genotype matrix. Use when deciding between joint genotyping and merging single-sample callsets (never bcftools merge as absent==hom-ref), choosing GenomicsDBImport vs CombineGVCFs by cohort size and memory, solving the N+1 problem so a new sample does not force re-calling everyone, understanding cohort rescue of low-coverage het sites, handling the spanning-deletion star allele and GQ/PL recomputation at the joint step, scaling to biobank cohorts by interval sharding, or picking DeepVariant+GLnexus over the GATK path on throughput. Not for single-sample calling (see variant-calling/gatk-variant-calling) or VQSR/hard-filter mechanism (see variant-calling/filtering-best-practices).

revfactory Bundle

A specialized skill providing a Unit Economics analysis framework. Used by the revenue-modeler agent when designing revenue models and calculating LTV, CAC, and contribution margin. Automatically applied in contexts such as 'unit economics', 'LTV/CAC', 'contribution margin', 'cohort analysis', 'payback period'. However, direct CRM data extraction and real-time customer analytics are outside the scope of this skill.

revfactory Bundle

OWASP Top 10 security test methodology, vulnerabilityper attack , detection , modification guide. 'OWASP', 'Top 10', 'XSS', 'SQL Injection', 'CSRF', 'SSRF', 'Injection', 'security test methodology', 'vulnerability test' etc. this security test this for. code-analystand pentest-reporterof security analysis -ize. , actual penetration test executionthis network this of scope .

revfactory Bundle

Code vulnerability pattern database. An extension skill for security-analyst that provides language-specific (Python/JS/Java/Go) vulnerable code patterns, CWE classification, safe alternative code, and severity assessment criteria. Use when performing security reviews involving 'vulnerability patterns', 'CWE', 'SQL Injection', 'XSS', 'security vulnerabilities', 'secure coding', 'vulnerable code', etc. Note: penetration testing execution and WAF configuration are outside the scope of this skill.

ndpvt-web Skill

Explore unfamiliar databases before writing SQL by building a local knowledge base of schema fragments, executable queries, and natural language descriptions. Uses MCTS-inspired schema traversal and dual-agent retrieval+generation. Trigger phrases: 'explore this database then query it', 'build SQL knowledge base', 'generate SQL for unfamiliar schema', 'text-to-SQL with exploration', 'help me understand this database and write queries', 'explore before generating SQL'.

ndpvt-web Skill

Cross-modal data analysis agent that unifies structured sources (SQL, CSV, JSON) with unstructured visual documents (scanned PDFs, invoice images, chart screenshots) using divide-and-conquer sub-agents and iterative code generation. Triggers: 'analyze data from these mixed sources', 'combine CSV with scanned PDF table', 'extract table from image and join with database', 'cross-modal data analysis', 'zombie data activation', 'analyze heterogeneous data files together'

ndpvt-web Skill

Convert natural language questions into SQL queries using MCTS-based modular reasoning inspired by the IESR framework. Decomposes complex Text-to-SQL into information extraction, schema linking, multi-path tree search, and trajectory verification. Use when: 'generate SQL from this question', 'write a query for this database', 'translate this question to SQL', 'help me query this schema', 'complex SQL with calculations', 'text-to-SQL with reasoning'.

ndpvt-web Skill

Build personalized AI tutoring systems with structured onboarding, four-layer prompt architecture, adaptive lesson generation, 3D avatar integration, and learner analytics. Use when: 'build an AI tutor', 'create a personalized learning platform', 'design an educational chatbot with avatars', 'generate adaptive lesson plans', 'build a learner onboarding flow', 'create an intelligent tutoring system'.

ndpvt-web Skill

Build LLM-powered natural language interfaces for data visualization — NL2VIS pipelines, conversational chart analytics, multimodal chart explanation, and visualization recommendation systems. Use when: 'build a chat interface for my dashboard', 'let users query data in plain English', 'generate charts from natural language', 'add conversational analytics to my app', 'explain this chart automatically', 'recommend visualizations for this dataset'.

ndpvt-web Skill

Perform unified multi-language taint analysis across Java, JavaScript, Python, and Go codebases using YASA's UAST-based approach. Detects SQL injection, command injection, SSRF, XSS, deserialization, and privilege escalation vulnerabilities by tracing data flow from sources to sinks. Trigger phrases: 'find taint vulnerabilities across languages', 'multi-language security audit', 'trace user input to dangerous sinks', 'run taint analysis on this project', 'check for injection vulnerabilities', 'find data flow security issues'.

pku-yuangroup Bundle

Compute and interpret VCF quality-control metrics (Ti/Tv, het/hom, novel/known, missingness, HWE, contamination, relatedness) with bcftools stats, vcftools, plot-vcfstats, and identity tools (somalier, peddy, KING). Use when judging whether a callset is trustworthy, diagnosing a low Ti/Tv or outlier het/hom sample, deciding whether an HWE deviation is error or biology, screening a cohort for sample swaps/contamination/wrong-sex before analysis, or comparing call sets before and after filtering. Not for applying filters (see variant-calling/filtering-best-practices) or normalizing representation (see variant-calling/variant-normalization).

pku-yuangroup Bundle

Batch effect correction for CRISPR screens covering ComBat empirical-Bayes, RUV, SVA, control-sgRNA normalization, and the model-based alternative of including batch as a covariate in MAGeCK MLE or Chronos. Covers screen-specific batch sources (passage cohort, library lot, infection day, sequencing run, Cas9 lot, FBS lot), PCA + variance-decomposition diagnostic to decide if correction is needed, when correction harms biology by over-correcting condition into batch, limma removeBatchEffect for visualization-only correction, and relationship to multi-condition design matrices. Use when combining screens for joint analysis, when passage cohort confounds biology, when DepMap-style panels need Chronos with batch covariates, when picking ComBat vs RUV, or when correction harms biology and should be replaced with explicit covariate modeling.

pku-yuangroup Bundle

Estimates the minimum biological replicates (or cells/events) for a target power at a target FDR in genomics experiments using ssizeRNA, PROPER, powsimR for scRNA-seq, and pilot-data dispersion estimation from DESeq2/edgeR. Covers the biological-versus-technical replication distinction (technical replicates do not add degrees of freedom for biological inference), replicate-number-versus-sequencing-depth budgeting, scRNA-seq sample-versus-cell allocation under a pseudobulk model, and the critique that "n=3" is a publication convention rather than a power calculation. Use when budgeting a sequencing experiment, writing the sample-size justification in a grant, estimating replicates from pilot data, allocating a fixed budget between samples and depth, or planning scRNA-seq cohort size. For clinical-trial sample size see clinical-biostatistics/power-and-sample-size; for the power-given-n direction see experimental-design/power-analysis.

pku-yuangroup Bundle

Call germline SNPs and indels from a BAM/CRAM with bcftools mpileup and call, and select the right calling engine for the job. Use when generating a VCF from aligned reads, choosing between bcftools, GATK HaplotypeCaller, DeepVariant, and DRAGEN, setting ploidy for haploid/organelle/polyploid/sex-chromosome calling, or deciding whether pileup-based calling is good enough versus a local-reassembly caller for indels and difficult regions. Not for cohort joint genotyping (see variant-calling/joint-calling), GATK-specific workflows (see variant-calling/gatk-variant-calling), deep-learning calling (see variant-calling/deepvariant), or somatic/low-VAF detection.

pku-yuangroup Bundle

Handles BED-format genomic intervals (BED3 through BED12, narrowPeak/broadPeak) and the coordinate-system substrate the whole interval category rests on, with bedtools (CLI) and pybedtools/pyranges/pandas (Python). Covers the 0-based half-open vs 1-based-closed convention boundary and the start-1/end-unchanged conversion, the silent failures (chrom-name mismatch, CRLF, lexicographic-vs-version sort under -sorted), genome/chrom.sizes generation, sorting contracts, BED12 block invariants, validation, makewindows, cross-assembly liftover (liftOver/CrossMap), and BED<->VCF/BAM/FASTA conversion. Use when reading, creating, validating, sorting, lifting between genome builds, or converting interval files, preparing inputs for bedtools/tabix/bigBed, or debugging an off-by-one or empty-overlap result.

pku-yuangroup Bundle

Combine, split, sort, intersect, and subset VCF/BCF files with bcftools merge, concat, isec, sort, view, and reheader. Use when merging different samples into a cohort VCF, concatenating per-chromosome or per-region call sets for the same samples, intersecting or complementing call sets from different callers, subsetting samples/regions, harmonizing sample names and

pku-yuangroup Bundle

Maps between gene identifier systems (Ensembl, Entrez, HGNC symbol, UniProt, RefSeq, MANE) using AnnotationDbi, biomaRt, mygene, pyensembl, and Ensembl REST. Encodes Ensembl version stripping with GENCODE _PAR_Y preservation, the Ziemann 2016 Excel autocorrect debacle and Bruford 2020 HGNC renames (SEPT*->SEPTIN*, MARCH*->MARCHF*, MARC*->MTARC*, DEC1->DELEC1), OCT4/POU5F1 alias resolution, biomaRt archive endpoints for release pinning, the `filters` (plural) gotcha, MANE Select for clinical reporting, cross-species orthology via Ensembl Compara / OMA / OrthoDB, and tx2gene construction for tximport. Use when converting gene IDs across systems, handling renamed symbols, building tx2gene, pinning to a specific Ensembl release for reproducibility, or mapping cross-species orthologs.

pku-yuangroup Bundle

Assign cell types from marker expression in IMC/MIBI data using clustering (PhenoGraph/FlowSOM/Leiden/Pixie), marker-based probabilistic classifiers (Astir), or image-context CNNs (CellSighter), covering the double-positive segmentation artifact, lineage-vs-state markers, the two spillover types, and why a "cell type" in imaging is conditioned on a segmentation guess. Use when phenotyping segmented IMC cells, choosing clustering vs classification, diagnosing implausible double-positive populations, separating lineage from functional markers, or transferring labels across a cohort.

pku-yuangroup Bundle

Estimates haplotype phase from population linkage disequilibrium with SHAPEIT5, SHAPEIT4, Eagle2, or Beagle - turning unphased genotypes (0/1) into phased haplotypes (0|1) for imputation input, compound-heterozygote calls, HLA typing, or population genetics. Covers why statistical phase is an INFERENCE (not a measurement) whose error concentrates at rare variants, why a genome-wide switch-error rate hides catastrophic rare-variant error and must be reported MAC-stratified, the SHAPEIT5 common-scaffold-then-rare design (phase_common, ligate, phase_rare, switch), reference-based vs within-cohort phasing, the build-matched genetic map, chrX male-haploid handling, and the switch-vs-flip-vs-Hamming distinction. Use when phasing genotypes before imputation, for compound-het/ASE/HLA, or benchmarking against trios. Read-backed / molecular phasing (long reads, Hi-C) is long-read-sequencing/haplotype-phasing; panel choice is reference-panels; imputation is genotype-imputation.

pku-yuangroup Bundle

Call germline SNPs and indels with GATK HaplotypeCaller and the GVCF joint-genotyping workflow. Covers the local-reassembly + PairHMM mechanism (why HC beats pileup callers on indels), the -ERC GVCF reference-confidence model and <NON_REF> allele, BQSR-vs-DRAGSTR and --dragen-mode error modeling, allele-specific (AS_) annotations, and edge cases (ploidy, Mutect2 mitochondria mode, sex chromosomes/PAR, contamination gating). Use when deciding whether to use HaplotypeCaller vs a pileup or DRAGEN caller, whether BQSR still earns its place, whether to call per-sample GVCFs for a cohort, or how to handle non-diploid, mitochondrial, sex-chromosome, or contaminated samples. Not for post-calling filtering depth (see variant-calling/filtering-best-practices) or cohort joint-genotyping scaling (see variant-calling/joint-calling).

pku-yuangroup Bundle

Extracts and assigns COSMIC v3.4 mutational signatures (86 SBS / 11 DBS / 18 ID / 21 CN / 16 SV) from somatic VCFs using SigProfilerSuite, MutationalPatterns, MuSiCal mvNMF, SigNet, or HRDetect. Use when characterizing DNA-damage etiology (BRCA1/2 HRD, MMR-D, POLE, APOBEC3A, UV, tobacco, aflatoxin, 5-FU/SBS17b, platinum, colibactin SBS88), routing PARP inhibitor decisions, or auditing de novo extraction vs refit choice for cohort size.