DevOps & Infra

pku-yuangroup Bundle

Authors reproducible Nextflow DSL2 pipelines built on reactive dataflow, where processes communicate only through channels and execution order is not guaranteed. Use when deciding channel/dataflow (Nextflow) vs rule-based (Snakemake) authoring; wiring queue vs value channels and fixing shared-reference exhaustion with .first(); composing DSL2 modules and subworkflows with take/main/emit; selecting container/conda profiles and pinning images by digest for portability across local/SLURM/LSF/AWS Batch/Google Batch/Kubernetes executors; diagnosing why -resume misses the cache (nondeterministic input order, mtime on network filesystems, mutable :latest tags) with cache 'lenient' and -dump-hashes; managing work/ vs publishDir and dynamic retry escalation; and choosing whether to adopt an nf-core community pipeline or author from scratch.

pku-yuangroup Bundle

Build and analyze pangenomes for prokaryotes (Panaroo, PPanGGOLiN, PEPPAN, GET_HOMOLOGUES, anvi'o pangenomics) and eukaryotes (Minigraph-Cactus, PGGB, vg pangenome graphs). Implement Tettelin core/accessory/cloud genome decomposition (Tettelin 2005), Heap's law open/closed pangenome modeling, gene presence/absence GWAS (Scoary, pyseer), pangenome graph variant calling (vg, PanGenie), and structural-variation graph indexing. Use when assembling species- or genus-level pan-gene catalogs, separating core from accessory/shell/cloud genes, testing gene-content associations with phenotypes, building pangenome graphs from haplotype-resolved assemblies, calling SVs from pangenome graphs, or selecting between bacterial-pangenome and eukaryotic-pangenome workflows.

pku-yuangroup Bundle

Identify tumor neoantigens from somatic variants with pVACtools (pVACseq/pVACfuse/pVACbind/pVACvector/pVACview) for personalized cancer vaccines and checkpoint biomarkers. Encodes the field's hard truth that binding prediction is the easy, near-solved part and single-digit-percent PPV lives downstream — so it centers clonality/CCF, HLA LOH (the silent invalidator), expression, proximal-variant phasing, agretopicity/foreignness quality, and the predicted->presented->immunogenic validation tiers. Use when nominating vaccine targets, ranking neoantigens, or building a tumor-to-candidate pipeline. Binding details in mhc-binding-prediction; ranking in immunogenicity-scoring.

pku-yuangroup Bundle

Authors reproducible bioinformatics pipelines with Snakemake - rules wired by output-file pattern, wildcards and expand() for sample fan-out, checkpoints for runtime-unknown outputs, resource/retry escalation, and conda/container software deployment on HPC and cloud. Use when deciding rule-based (Snakemake) vs channel/dataflow (Nextflow) authoring; wiring rules by OUTPUT-file pattern rather than imperative order; using wildcards + expand() for sample fan-out and constraining them to stop silent mis-routing; adding checkpoints when the set of outputs is unknown until a step runs (dynamic DAG); diagnosing why a job reran (or did not) under the mtime-plus-provenance trigger set; escalating memory on retry for OOM-killed jobs; and porting a Snakemake 7 `--cluster`/remote-provider command to the Snakemake 8+ executor-plugin and storage-plugin model (snakemake-executor-plugin-slurm) with `--software-deployment-method`.

pku-yuangroup Bundle

Creates DE-specific diagnostic and result visualizations using DESeq2/edgeR built-in functions and lightweight ggplot2 wrappers. Covers MA plot (with the shrunken-LFC compression effect), volcano (with the apeglm caveat that p-values are unchanged), PCA on VST/rlog (never raw counts), sample distance heatmaps, top-DE-gene heatmaps with the row-scaling trap, dispersion / BCV plot interpretation, p-value histogram diagnostics, plotCounts for individual genes, blind=TRUE vs FALSE rationale, and the n=3 visualization stake. Use when generating DE diagnostic plots, choosing VST vs rlog for visualization, troubleshooting suspicious plot patterns (shifted MA cloud, batch-dominated PCA, anti-conservative p-value histogram), or building a standard QC figure panel.

pku-yuangroup Bundle

Detects acquired antimicrobial-resistance determinants and chromosomal point-mutation resistance in bacterial assemblies using AMRFinderPlus, ResFinder 4.0 (acquired + PointFinder), CARD-RGI, abritAMR, staramr, and species-specific callers (TB-Profiler, Mykrobe). Harmonises cross-tool output via hAMRonization, contextualises determinants with mobile-genetic-element annotation (MOB-suite, PlasmidFinder, MobileElementFinder, ICEberg), predicts phenotype against EUCAST or CLSI breakpoints, and translates calls into WHO GLASS reporting categories. Use when screening clinical or surveillance isolates for AMR, distinguishing acquired vs intrinsic vs point-mutation resistance, calling rpoB / katG / pncA / gyrA / mgrB mutations, reconciling AMRFinderPlus vs RGI vs ResFinder disagreement, contextualising carbapenemases or mcr alleles on plasmids, predicting susceptibility from genotype against the WHO Mtb 2nd-edition catalogue, or building a hAMRonized multi-lab AMR surveillance pipeline.

pku-yuangroup Bundle

Standardizes molecular structures using the ChEMBL structure pipeline for normalization and parent selection plus RDKit rdMolStandardize for explicit custom steps such as tautomer canonicalization, salt/solvent stripping, charge handling, stereochemistry handling, mixture selection, and isotope normalization. Explicitly compares ChEMBL, canSARchem, RDKit, and PubChem standardization choices. Use when preparing libraries for QSAR training, joining datasets across sources, deduplicating compound collections, or building canonical compound registries.

pku-yuangroup Bundle

Analyzes multiplexed antibody-imaging data (CODEX/PhenoCycler, MIBI-TOF, IMC, CyCIF, Opal/Vectra mIF) as continuous protein intensity rather than transcript counts, using scimap and squidpy. Use when choosing an intensity transform/normalization (arcsinh cofactor vs z-score vs percentile -- NOT log1p-of-counts) and correcting channel spillover and antibody-batch effects; deciding whether to phenotype by gating or by clustering on intensities; recognizing that a bounded antibody panel makes marker absence uninformative; treating whole-cell segmentation (Mesmer) as the dominant error source; and knowing which platform applies and when to defer to the imaging-mass-cytometry skills for the IMC pipeline.

pku-yuangroup Bundle

Build whole-genome alignments using Progressive Cactus (Armstrong 2020 reference-free clade-level WGA), Minigraph-Cactus (Hickey 2024 pangenome-aware), LASTZ chain/net (UCSC pipeline), MUMmer4 (Marçais 2018 pairwise), minimap2 -x asm5/10/20 (Li 2018 fast pairwise), AnchorWave (Song 2022 WGD-aware), and Mauve / progressiveMauve (bacterial). Operates the HAL toolkit (Hickey 2013) for downstream extraction including halSynteny, halLiftover, halBranchMutations, and hal2maf. Use when constructing multi-species alignments for comparative-annotation projection (TOGA), synteny detection, conservation analyses (phyloP / PhastCons), or pangenome graph construction; selecting between reference-free (Cactus) and reference-anchored (LASTZ chains/nets) approaches; tuning sensitivity for closely vs distantly related genomes; or producing HAL files for genome-wide downstream tools.

pku-yuangroup Bundle

Build Sankey, alluvial, river, and CONSORT-style flow diagrams to visualize cohort transitions, cell-state changes, or pipeline filtering using ggalluvial, networkD3, plotly, and consort. Use when showing how entities move between categories across timepoints (cell states, drug response classes, patient flow through a trial) or filtering pipelines (variants filtered through QC stages).

pku-yuangroup Bundle

Predicts protein-coding gene structures (exons, introns, UTRs) in eukaryotic genomes with BRAKER3 (RNA-seq + protein evidence), BRAKER1/BRAKER2, GALBA (protein-only), Funannotate (fungi), GeMoMa (homology projection), or Helixer/Tiberius (deep-learning ab initio). Covers the evidence-first tool decision, mandatory soft-masking, the training-set-quality-dominates principle, OrthoDB clade-partition selection, the one-isoform-per-locus and missing-UTR traps, merge/split errors, and reference bias against orphan genes. Use when annotating a newly assembled eukaryotic genome, choosing a gene-prediction pipeline based on available evidence, or diagnosing a poor annotation.

pku-yuangroup Bundle

Detects aberrant splicing in single rare-disease patients vs a control panel using FRASER 2.0 (Bioconductor; Beta-binomial autoencoder on Intron Jaccard Index, default delta cutoff 0.1, q hyperparameter), OUTRIDER (gene-level outlier expression via autoencoder denoising), LeafcutterMD (Dirichlet-multinomial outlier mode of LeafCutter for annotation-free junctions), and DROP (Snakemake pipeline integrating FRASER2 + OUTRIDER + monoallelic expression for clinical diagnostics). The statistical model is fundamentally different from differential splicing — single-sample-vs-cohort outlier detection rather than two-group comparison. Standard tool in EU rare-disease (Solve-RD) and NIH UDN programs. Use when applying RNA-seq to undiagnosed Mendelian disease, validating predicted splice variants in clinical samples, or detecting cryptic splicing in disease tissue.

lgrappag Skill

Initialize ML pipeline with data processing and model architecture

lgrappag Skill

Store player saves in cloud for cross-device access

lgrappag Skill

Deploy and optimize neural networks for real-time inference

lgrappag Skill

Convert assets between different engine formats

withoneai Skill

Docker Hub through One

withoneai Skill

JumpCloud through One

jiayaoqijia Bundle

Deploy Solidity contracts to MAINNET (or testnet) safely via the ChainGPT plugin. End-to-end: generate → audit → compile → estimate → build unsigned tx → user signs → verify on Etherscan. MAINNET is the default; the audit gate is mandatory for mainnet deploys. The plugin never holds private keys — the user signs externally via MetaMask / Rabby / hardware wallet / ERC-4337 smart account. Triggers: deploy contract, ship contract, deploy to mainnet, deploy to ethereum, deploy to base, deploy to bsc, verify contract, mainnet deploy, contract deployment.

jiayaoqijia Bundle

Audit-before-action security workflow for any Web3 interaction the user is about to take. Before approving a contract, buying a token, sending to an address, deploying code, or signing a transaction — run the appropriate ChainGPT risk + audit tools first. Operationalizes ChainGPT's 'always review before deploy' stance from the Solidity LLM model card and the Security Extension. Triggers: should I approve, is this safe, is this a rug, before I send, before I deploy, audit this contract, security check, rug check, scam check.

jiayaoqijia Bundle

Build or edit a Senpi trading strategy — interactively, ONE decision at a time. There is no paper-trading mode: a strategy is tested with `senpi validate` and a $10-floor live run, never with a scanner re-run on a timer (a model call per firing). Use for "build a strategy", "create a strategy from scratch", "design a strategy", "I have a trading idea", or ANY strategy that needs DSL (a runtime-supervised exit: stop-loss, trailing stop, profit-lock ladder) — a runtime.yaml authored here is the ONLY way to carry a DSL; raw MCP strategy_create* / create_position calls cannot, and must never stand up a named or protected strategy. Offers the closest TEMPLATE first (via senpi-strategy-discover) as the quick start to the user's OWN strategy, with fork-before-deploy, bespoke edit and scratch as peers, each with its cost class; never asks for a budget to build (it is asked once, at deploy); exits default to letting winners run, stated in price at leverage; the user names what you build. NOT for installing (senpi-stra

jiayaoqijia Bundle

Help a user choose a Senpi trading strategy to deploy — a conversational, analyst-style picker. Use when the user asks "what should I trade?", "recommend a strategy", "help me pick a strategy", "what's winning?", "set me up", "I have a view on the world (a war, the economy, one coin winning) — trade it", "run a hedge fund / all-weather / tail-risk book", or wants a strategy but has NOT named a specific one — and every discretionary mandate: "deploy whatever you think is profitable", "trade for me", "be aggressive", "put it to work", "you decide". A mandate is a strategy request even when it names no strategy and no coin; it is never answered with hand-picked raw positions. Surface the closest matching TEMPLATE first — the quick start to the user's OWN strategy (every template deploys as `<User>'s <Template>` — or a name of their own — as-is or with levers moved, after ops walks them through it) — passing their worldview as `--theme` to rank the closest fits; offer building one as a peer with its cost class, n

jiayaoqijia Bundle

Pull a complete DeXe DAO report in ONE `dexe_dao_report` call — members, delegations, treasury, proposals, turnout ("who voted"), experts, validators, activity and deadlines — show only what moved with the `since` diff, and put it on a schedule with /schedule (cloud cron) or /loop (this session). Use when the user says "report", "stats", "activity", "who voted", "how is my DAO doing", "weekly digest", "monitor my DAO", "check it every day".

jiayaoqijia Bundle

Set up DeXe DAO staking end-to-end: resolve/deploy the StakingProposal contract, pass a `create_staking_tier` proposal via `dexe_proposal_create`, then holders stake/claim/reclaim. Covers the two traps that silently eat tiers — a PAST deadline is rejected on-chain with a SUCCESSFUL execute (StakingRejected, no tier), and staking does not exist on BSC testnet (97) at all. Use when the user says "staking", "stake", "staking tier", "staking rewards", "let holders stake".

jiayaoqijia Bundle

Deploy a new DeXe DAO with the one-call `dexe_dao_create` composite. Use SIMPLE mode (symbol + totalSupply) and let the tool synthesize a coherent, governance- safe config — it previews the resolved config + a safety proof and only broadcasts on confirm. Covers the quorum turnout rule (quorum ≤ 0.8 × votable share) and the ≥50% floor, the implicit-treasury pattern, and the deploy gotchas. Use when the user says "create/deploy a DAO".

jiayaoqijia Bundle

Scaffold for assembling on-chain copy-trading strategies on Binance Agentic Wallet. Wires the existing capabilities — address monitoring, signal subscription, address scoring, token audit, order placement, on-chain take-profit/stop-loss — into one runnable pipeline, and exposes every strategy decision as a hook. Ships no strategy of its own. Trigger on: copy trade, copy trading, follow smart money, follow a wallet, mirror trades, copy-trade bot, auto-buy on signal, monitor a wallet and trade, smart money copy trading, signal-driven trading, pick addresses to copy, copy-trade strategy, copy-trade status, copy-trade post-mortem. NOT for: single manual trades (use binance-agentic-wallet), signal queries alone (binance-trading-signal), address analysis alone (binance-wallet-tracker / binance-leaderboard).

rudironsoni Skill

Converts VitePress wiki to Azure DevOps Wiki-compatible format

yigityildiz0 Skill

Azure-specific infrastructure expertise for designing and managing cloud environments. Use when provisioning Azure resources with Bicep or Terraform.

yigityildiz0 Bundle

Data pipeline design for ETL/ELT workflows, streaming architectures, data validation, and orchestration. Use when building data pipelines, choosing batch vs.

yigityildiz0 Bundle

Run nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data. Use when analyzing RNA-seq, WGS/WES, or ATAC-seq data—either local FASTQs or public datasets from GEO/SRA. Triggers on nf-core, Nextflow, FASTQ analysis, variant calling, gene expression, differential expression, GEO reanalysis, GSE/GSM/SRR accessions, or samplesheet creation. Turkish triggers: Nextflow veya nf-core pipeline geliştir, süreç ve kanal hatası, biyoinformatik iş akışı.

yigityildiz0 Bundle

Infrastructure as Code expertise with Terraform/OpenTofu for cloud provisioning. Use when writing Terraform modules, managing state, configuring.

yigityildiz0 Bundle

Generates continuous deployment pipelines for GitHub Actions, GitLab CI, Jenkins, and ArgoCD with deployment strategies, environment promotion, and rollback.

yigityildiz0 Bundle

Automatically audit, repair, refactor, and stabilize an existing ComfyUI workflow or Windows runtime when the user shares workflow JSON, an error/screenshot, or reports startup/queue failure, `Failed to fetch`, missing nodes/models, broken links, overlap, identity drift, LoRA/model-order problems, VRAM/speed instability, or wants to integrate identity/refiner/post-processing modules without breaking the primary workflow. Validate before and after, preserve backups and working branches, and prefer one evidence-based change at a time. Use comfyui-workflow to design a new pipeline from scratch. Turkish triggers: ComfyUI workflow düzelt, JSON veya node hatası, VRAM/kimlik/bağlantı sorunu, güvenli onarım.

yigityildiz0 Bundle

Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance.

yigityildiz0 Skill

Design and verify Claude API access across Anthropic direct and supported cloud/platform integrations without hard-coded model IDs or silent failover. Use.

yigityildiz0 Skill

Design bounded OpenCode CLI loops and multi-stage pipelines with explicit artifacts, stop conditions, time/cost budgets, permissions, validation gates, and recovery. Use for repeat-until-pass, batch pipeline, CI audit, or Turkish intents such as “OpenCode döngüsü”, “otonom ama sınırlı çalış”, “başarana kadar dene”, “çok aşamalı pipeline”. Do not use for unbounded autonomy, ambiguous goals, credentials, payments, publishing, or irreversible external actions.