DevOps & Infra

pku-yuangroup Bundle

Chains a somatic (tumor-normal) SNV/indel and structural-variant pipeline end to end with GATK Mutect2 (or Strelka2), wiring the somatic-specific machinery - panel-of-normals and gnomAD germline-resource priors, GetPileupSummaries/CalculateContamination, and LearnReadOrientationModel FFPE/oxoG orientation-bias filtering fed into FilterMutectCalls. Use when calling somatic mutations from a tumor-normal pair (or tumor-only with PoN caveats), deciding which artifact filter removes which class of false positive, reasoning about VAF/purity/ploidy and clonal-vs-subclonal detection, adding somatic SV/CNV or TMB/MSI/signatures, or routing variants to AMP/ASCO/CAP tier and oncogenicity interpretation (never germline ACMG).

pku-yuangroup Bundle

Estimates bivariate genetic correlation (rg) between traits from GWAS summary statistics or individual-level genotypes using cross-trait LDSC, HDL, LAVA, rho-HESS, GREML-bivariate, Popcorn, and HDL-L. Use when quantifying shared genetic architecture between two traits, screening MR validity before causal inference, distinguishing global from locus-level rg, estimating trans-ancestry rg, separating partial from full causation via LCV gcp, or producing a STROBE-MR-compliant cross-trait sensitivity battery. Cross-trait LDSC intercept absorbs sample overlap and is NOT a bias; HDL is biased under sample overlap above ~5%. High rg between exposure and outcome motivates CHP-aware MR sensitivity (CAUSE, LHC-MR).

pku-yuangroup Bundle

Analyzes base-editing screens for variant function. Covers library design (Hanna 2021 ClinVar-scale CBE screen benchmarked on BRCA1/2, Cuella-Martin 2021 DDR saturation), CBE vs ABE chemistry choice (BE3/BE4 vs ABE7.10/ABE8.20/ABE8e), editing-window math (positions 4-8 from PAM-distal end; 4-7 for ABE7.10), bystander-edit quantification and the variant-call ambiguity it creates, sgRNA-efficiency filtering before hit calling, indel byproduct interpretation, the substitution-vs-indel diagnostic, variant annotation against ClinVar / COSMIC, and the Broad be-validation-pipeline. Use when designing a BE variant screen, choosing CBE vs ABE for a specific edit, interpreting bystander-confounded hits, distinguishing functional signal from indel artifact, integrating CRISPResso2 output with screen scoring, or deciding BE vs PE for SNV installation.

pku-yuangroup Bundle

Discovers, classifies, filters, and quantifies full-length transcript isoforms from PacBio Iso-Seq/Kinnex (HiFi) and Oxford Nanopore (cDNA/direct-RNA) long reads, using the isoseq+pigeon pipeline, SQANTI3, and ONT tools (IsoQuant, FLAIR, Bambu, StringTie2). Covers why a novel isoform is an artifact until proven otherwise (RT template-switching, intra-priming, and 5' degradation manufacture junctions and truncations), the SQANTI3 structural categories and their trust order, the Kinnex skera-split step, orthogonal CAGE/poly-A/short-read-junction validation, and why long-read isoform quantification needs EM. Use when building a full-length isoform catalog, classifying/filtering long-read transcripts, running Iso-Seq or ONT cDNA/dRNA analysis, or judging novel-isoform reliability.

pku-yuangroup Bundle

Resolve the architecture of focal oncogene amplifications — extrachromosomal DNA (ecDNA), breakage-fusion-bridge (BFB) cycles, homogeneously staining regions (HSR), and linear amplification — from whole-genome sequencing with AmpliconArchitect, the AmpliconSuite pipeline, and AmpliconClassifier. Covers copy-number seed selection, breakpoint-graph reconstruction, balanced-flow optimization, ecDNA classification, and the limits of depth-only amplification calls. Use when a focal amplification needs structural characterization, when distinguishing ecDNA from chromosomal amplification, suspecting ecDNA-driven oncogene amplification or therapy resistance, or selecting copy-number seeds for amplicon reconstruction.

revfactory Bundle

A full pipeline where an agent team collaborates to generate incident postmortem reports. Systematically performs timeline reconstruction, root cause analysis, impact assessment, and remediation planning. Use this skill for requests like 'write an incident postmortem', 'post-incident analysis report', 'create an incident report', 'incident report', 'root cause analysis', 'RCA report', 'organize incident timeline', 'establish remediation measures', and other incident analysis tasks. Note: real-time incident response (on-call), monitoring system setup, and alert configuration are outside the scope of this skill.

revfactory Bundle

Detailed guide on Terraform module design patterns, directory structures, state management, and environment separation strategies. Use this skill for 'Terraform modules', 'module structure', 'state management', 'remote state', 'environment separation', 'workspace', 'terragrunt', 'module patterns', and other Terraform module design tasks. Enhances the IaC design capabilities of infra-architect and drift-detector. Note: actual terraform apply and infrastructure provisioning execution are outside the scope of this skill.

revfactory Bundle

Methodology for systematically designing a chatbot's intent classification taxonomy. Use this skill for 'intent taxonomy design', 'intent system', 'NLU intent list', 'entity dictionary', 'slot design', and other chatbot intent classification taxonomy design tasks. Note: actual NLU model training and cloud NLU service deployment are outside the scope of this skill.

revfactory Bundle

Full pipeline where an agent team collaborates to perform release management. Use this skill for requests like 'create release notes', 'generate CHANGELOG', 'write changelog', 'prepare version release', 'migration guide', 'release announcement', 'organize changes', 'new version announcement', and other release management tasks. Note: CI/CD pipeline construction, automated deployment configuration, and version management policy establishment are outside the scope of this skill.

revfactory Bundle

Real estate investment analysis pipeline. An agent team collaborates to produce market research, location analysis, profitability analysis, risk assessment, and investment reports. Use this skill for requests such as 'analyze this real estate', 'apartment investment analysis', 'studio apartment yield', 'real estate market research', 'location analysis', 'real estate investment report', 'buy vs lease', 'reconstruction investment analysis', 'commercial property yield analysis', and other general real estate investment analysis tasks. Actual purchase contracts, brokerage services, interior design, and property management are outside the scope of this skill.

revfactory Bundle

Airflow DAG pattern, of , retry strategy, etc. , strategy etc. data pipeline orchestration guide. 'Airflow DAG', 'DAG ', 'of', 'retry strategy', 'etc.', '', 'pipeline orchestration', 'Dagster', 'Prefect' etc. pipeline scheduling this for. scheduler-engineerof DAG -ize. , data rule of monitoring dashboard this of scope .

revfactory Bundle

Text analytics methodology. Referenced by topic-classifier and trend-detector agents when extracting topics and deriving trends from unstructured text. Used for 'topic classification', 'keyword analysis', 'text mining' requests. Note: NLP model training and large-scale data processing pipeline development are out of scope.

revfactory Bundle

A full production pipeline where an agent team collaborates to generate documentary research, treatments, interview questions, and narration scripts all at once. Use this skill for 'plan a documentary,' 'create a documentary treatment,' 'documentary research,' 'create interview questions,' 'write a narration script,' 'investigative reporting plan,' 'documentary scenario,' and all other aspects of documentary production. Also supports treatment writing or narration scripting when existing research materials are provided. Note: actual video filming/editing (Premiere, DaVinci), interview scheduling/conducting, and broadcast transmission are outside the scope of this skill.

revfactory Bundle

open source project launching code , documentation , license , community until inthisbefore teamthis to countlower launching pipeline. 'open source items ', 'project open source-ize', 'GitHub items ', 'open source license ', 'README ', 'CONTRIBUTING guide only', 'open source community ', ' ', 'CI/CD setup', 'code items before ' etc. open source launching beforein this for. READMEonly necessarylower license only necessary inalso supported. , actual creation, GitHub configuration API , package tree deployment execution this of scope .

revfactory Bundle

Full pipeline for auto-generating API client SDKs. An agent team collaborates to parse API specs (OpenAPI/GraphQL/gRPC), generate types, write client code, create tests, and produce usage documentation. Use this skill for requests like 'create an API client', 'SDK generation', 'client from OpenAPI', 'API wrapper', 'REST client', 'GraphQL client', 'API type generation', 'SDK from Swagger', etc. Note: API server implementation, API gateway configuration, and API monitoring dashboard setup are outside the scope of this skill.

revfactory Bundle

Full audit pipeline for ESG/sustainability where an agent team collaborates to generate environmental, social, and governance assessments along with an integrated report and improvement plan. Use this skill for requests such as 'run an ESG audit', 'write a sustainability report', 'ESG assessment', 'carbon emissions calculation', 'ESG rating diagnosis', 'governance review', 'social responsibility assessment', 'GRI report', 'TCFD disclosure', 'ESG improvement plan', and other ESG/sustainability tasks. Also supports assessment of specific pillars (E/S/G) only or improving existing reports. However, actual on-site audit execution, third-party verification certificate issuance, ESG rating agency score changes, and carbon credit trading are outside the scope of this skill.

revfactory Bundle

A full pipeline for designing, decomposing, communicating, and monitoring microservice architectures. An agent team collaborates to perform domain analysis, service design, communication patterns, and observability. Use this skill for requests like 'design a microservice architecture', 'decompose services', 'MSA design', 'domain analysis', 'event-driven architecture', 'inter-service communication design', 'distributed system design', 'API gateway design', and other microservice design tasks. Also supports transitioning from an existing monolith to MSA. Note: actual infrastructure setup, Kubernetes deployment, and code implementation are outside the scope of this skill.

revfactory Bundle

this performance optimization profiling, bottleneck analysis, optimization , benchmark verificationuntil inthisbefore teamthis to countlower pipeline. 'performance optimization', 'slow API improvement', 'query optimization', 'between ', 'performance profiling', 'bottleneck analysis', 'benchmark test', 'as speed improvement', 'P95 between this', 'throughput ' etc. performance improvement beforein this for. query optimization profilingonly necessary inalso supported. , infrastructure provisioning direct execution, as configuration, CDN setup direct deployment this of scope .

revfactory Bundle

companyproject basis A pipeline where an agent team collaborates for comprehensive planning. 'companyproject basis', 'company project idea', ' project', 'MVP ', ' reporting ', 'service launch', '1person development', 'indie hacking', 'week project', 'tech stack ', 'company ' etc. companyproject basis before skill usage. existing idea case also tech stack MVP design degreeKRW. However, actual code writing, specialistperson whenplan work, person/from versus is outside this skill's scope.

revfactory Bundle

A pipeline where an agent team builds organizational knowledge management systems. Use this skill for requests such as 'build a knowledge base,' 'wiki setup,' 'knowledge management system,' 'internal wiki,' 'organize team documentation,' 'technical documentation wiki,' 'create onboarding docs,' 'organize organizational knowledge,' or 'build documentation system.' Note: CMS server setup, database installation, and search engine deployment are outside the scope of this skill.

yigityildiz0 Bundle

CI/CD pipeline expertise for automated build, test, and deployment workflows. Use when setting up GitHub Actions, GitLab CI, Jenkins, or other CI/CD.

yigityildiz0 Bundle

Multi-cloud architecture expertise for AWS, Azure, and GCP. Use when designing cloud infrastructure, implementing Well-Architected Framework principles.

yigityildiz0 Bundle

Configure test automation in CI/CD pipelines with quality gates, parallel execution, and reporting. Use when setting up GitHub Actions, GitLab CI, Jenkins.

yigityildiz0 Bundle

Automatically design or substantially modify a ComfyUI workflow when the user wants a new image/video pipeline or capability for FLUX, SDXL, SD3, Wan, Hunyuan, LTXV, Mochi, Cosmos, txt2img, img2img, txt2vid, img2vid, LoRA, ControlNet, IPAdapter, PuLID, inpaint, or upscale. Start from the closest validated template, produce valid workflow JSON, and list models/custom nodes. For an existing JSON, runtime error, identity drift, VRAM/performance problem, broken links, or conservative repair of the primary workflow, co-use or route to comfyui-workflow-guardian. Turkish triggers: ComfyUI workflow yap, yeni görsel/video akışı, node ve model bağlantılarını kur.

yigityildiz0 Bundle

Container best practices including Dockerfile optimization, multi-stage builds, image security scanning, and Docker Compose patterns. Use when.

yigityildiz0 Bundle

Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this.

yigityildiz0 Skill

Prepare, preview, deploy, and verify a Cloudflare application with environment-aware configuration, migrations, secrets, domains, observability, and.

yigityildiz0 Bundle

Deep Kubernetes expertise for container orchestration, deployment patterns, and cluster management. Use when deploying to K8s, writing Helm charts.

yigityildiz0 Skill

Deep PowerShell expertise for automation and systems administration. Use when writing PowerShell scripts, building modules, managing Windows/Azure.

yigityildiz0 Bundle

Build or recalibrate a private, evidence-based writing-style profile from text the user explicitly places in scope. Use when the user asks to analyze/capture their voice across future writing, compare samples, or create a reusable style profile; extract observable traits without copying distinctive passages or silently persisting personal data. Do not activate merely to draft one email or WhatsApp message—use message-writer, which may apply an already approved profile. Never scan unrelated conversations, mail, cloud files, or repositories automatically. Turkish triggers: yazım tarzı oluştur, kişisel üslup rehberi, örneklerden ses tonu çıkar.

jiayaoqijia Bundle

Provides digital forensics and signal analysis techniques for CTF challenges. Use when analyzing disk images, memory dumps, event logs, network captures, cryptocurrency transactions, steganography, PDF analysis, Windows registry, Volatility, PCAP, Docker images, coredumps, side-channel power traces, DTMF audio spectrograms, packet timing analysis, CD audio disc images, or recovering deleted files and credentials.

jiayaoqijia Bundle

Deploy / monitor / close a NAMED Senpi trading strategy. Monitoring is on demand: never an agent-turn cron to watch a strategy (a model call per firing) — the runtime supervises it at zero model cost, and there is no paper-trading mode ($10 floor = the test). Use when the user names a strategy to run — "install spider", "deploy polar", "set up kodiak", "run the spider strategy", "is my strategy live?", "what am I running", "list my strategies" (→ status.py), "are my positions protected? / do they have a stop-loss (DSL)?", "stop/close/uninstall polar" — and for teardown like "close all strategies", "return funds to main", "tear everything down" (→ close.py --all). ALWAYS tear down via close.py, never a raw strategy_close (that strands the runtime). ops deploys / closes / monitors; it does NOT author or edit strategy files — an edit ("make my live strategy more aggressive", change leverage/sizing/DSL) is authored in senpi-strategy-author, the only skill that knows the scanner / yaml / DSL schema. A strategy is

pku-yuangroup Bundle

Runs and configures curated nf-core community Nextflow pipelines (rnaseq, sarek, atacseq, methylseq, ampliseq, taxprofiler, fetchngs) reproducibly, pinning the pipeline revision with -r and selecting a container engine and institutional config via -profile. Use when deciding to adopt a community pipeline versus author one from scratch; picking a pipeline and pinning its -r revision; selecting -profile test/docker/singularity/conda plus an institutional config from nf-core/configs; building and validating a samplesheet CSV against the pipeline schema (nf-schema); choosing --genome/iGenomes versus custom references; configuring resources and max_memory for SLURM/AWS Batch; using -resume and -stub; and reading MultiQC outputs.

pku-yuangroup Bundle

Analyzes differential transcript usage (DTU) and isoform switches with functional consequence prediction (NMD via 50nt rule, ORF disruption, protein domain loss/gain, signal peptide changes, IDR alterations, coding-potential shifts). Tools include IsoformSwitchAnalyzeR v2 (auto-selects satuRn for >5 reps else DEXSeq), the manual DRIMSeq -> DEXSeq/satuRn -> stageR DTU pipeline, and fishpond/swish for inferential-uncertainty-aware DTE. Distinguishes DTU from DGE and DTE; integrates external annotators (CPC2, Pfam, SignalP, IUPred2A or DeepTMHMM). Use when investigating how splicing differences alter protein function or trigger NMD-mediated degradation.

pku-yuangroup Bundle

Processes eDNA metabarcoding from raw paired-end reads to species tables, navigating ASV (DADA2, UNOISE3) vs OTU (swarm v2) decision (Callahan 2017 vs Schloss multi-copy-16S critique), marker/primer choice (Leray COI, MiFish 12S, 515F/806R 16S, ITS2) with primer-specific bias, OBITools3 v3 command-name break (obi stats plural; .tar.gz taxonomy), tag-jumping with dual-indexing (Schnell 2015; NovaSeq 10x MiSeq), decontam as screening-not-classifier (Davis 2018), read-counts-not-abundance critique (Lamb 2019), site-occupancy modeling (Ficetola 2015), Naive-Bayes calibration limits (Bokulich 2018), and eDNA decay (Strickler 2015). Use when going from raw eDNA FASTQ to species tables, picking marker + denoising pipeline, deciding whether read counts represent abundance, applying occupancy modeling, configuring OBITools3 v3, or interpreting decontam output. Not for clinical 16S microbiome (see microbiome/amplicon-processing).

pku-yuangroup Bundle

Imputes untyped genotypes against a phased reference panel with Beagle, Minimac4, or IMPUTE5 (array data) or from genotype likelihoods with GLIMPSE2, QUILT2, or STITCH (low-coverage WGS), producing per-variant dosages (DS) with a self-estimated quality (Beagle DR2, Minimac R2, IMPUTE INFO). Covers why the honest output is a dosage posterior not a hard call, why GWAS regresses on DS, why the quality metric is an ESTIMATE of r2 from posterior spread (not validation against truth), the DS/GP/HDS fields, the phasing prerequisite, chunking, chrX ploidy, the Michigan/TOPMed servers (the only access to HRC/TOPMed), and low-coverage WGS as the modern array replacement. Use when increasing variant density for GWAS, harmonizing arrays, inferring untyped variants, or imputing low-coverage sequence. Phase first with haplotype-phasing; prepare the panel with reference-panels; filter with imputation-qc; the GWAS test is population-genetics/association-testing; end-to-end orchestration is workflows/gwas-pipeline.