Product & Planning

revfactory Bundle

A full PM pipeline where an agent team collaborates to generate roadmaps, PRDs, user stories, sprint plans, and retrospectives in one go. Use this skill for 'Write a PRD,' 'Build a roadmap,' 'Decompose user stories,' 'Plan sprints,' 'Help with product planning,' 'PM tasks,' 'feature specifications,' 'product requirements,' 'backlog grooming,' 'sprint planning,' 'OKR setting,' 'product strategy,' and 'retrospective templates' — the full spectrum of PM work. It also supports user story decomposition and sprint planning when existing PRDs or roadmaps are provided. Note: Actual Jira/Linear ticket creation, design mockup production, code development, and stakeholder meeting facilitation are outside the scope of this skill.

revfactory Bundle

A methodology for systematically determining feature priorities using the RICE framework. Used for 'RICE analysis,' 'feature prioritization,' 'backlog prioritization,' 'feature scoring,' and 'prioritization frameworks' when deciding on product feature priorities. Note: Automatic Jira/Linear ticket creation and real-time dashboard building are outside the scope of this skill.

revfactory Bundle

A specialized skill providing industry-specific benchmark data and KPI selection frameworks for KPI dashboard design. Used by the kpi-designer agent when selecting key metrics and setting benchmarks. Automatically applied in contexts such as 'KPI benchmarks', 'key metric selection', 'performance indicators', 'OKR metrics', 'industry KPIs'. However, actual BI tool (Tableau, Power BI) dashboard implementation and real-time data pipeline construction are outside the scope of this skill.

revfactory Bundle

A full pipeline that systematizes an organization's strategy framework through OKR design, BSC mapping, SWOT analysis, vision & mission statement, and strategy execution roadmap. Use this skill for 'build a strategy framework,' 'design OKRs,' 'BSC analysis,' 'SWOT analysis,' 'write vision and mission,' 'strategy roadmap,' 'strategy formulation,' 'mid-to-long-term strategy,' 'business strategy framework,' and 'strategy system design' — across the full spectrum of organizational strategy development. It also supports supplementing and validating existing OKRs or SWOT analyses. Note: Financial statement preparation, ERP system implementation, performance review execution, and real-time KPI dashboard development are outside the scope of this skill.

revfactory Bundle

A methodology for systematically verifying OKR (Objectives and Key Results) quality. Used for 'OKR verification,' 'OKR quality check,' 'KR measurability,' 'OKR alignment check,' and 'Objective quality' when validating OKRs. Note: OKR software configuration and performance review integration are outside the scope of this skill.

ndpvt-web Skill

Automated black-box pipeline for detecting unverbalized biases in LLM decision-making. Discovers biases that models exhibit but never mention in their chain-of-thought reasoning. Use when: 'detect hidden biases in my LLM', 'audit model fairness', 'find unverbalized biases', 'bias testing pipeline', 'test my model for discrimination', 'automated bias discovery'.

ndpvt-web Skill

Apply defensive programming and agent-architecture patterns from SWE-Bench Mobile to tackle production iOS/mobile development tasks. Optimizes how Claude navigates large mixed-language codebases, interprets multi-modal inputs (PRDs + Figma designs), and generates robust patches. Use when: "build this iOS feature from a PRD", "implement this Figma design in Swift", "fix this mobile app issue across multiple files", "generate a patch for this iOS codebase", "help me with production mobile development", "defensive programming for mobile code".

ndpvt-web Skill

Build grounded, declarative agentic architectures using the DALIA pattern: capability descriptors, discovery protocols, federated agent directories, and deterministic task graphs. Use when the user says 'build a multi-agent system', 'create an agent orchestration layer', 'design declarative agent workflows', 'set up agent capability discovery', 'make agent coordination reliable', or 'avoid hallucinated agent plans'.

pku-yuangroup Bundle

Discovers novel miRNAs and quantifies known miRNAs with miRDeep2 by scoring genome-mapped read stacks against the Dicer/Drosha biogenesis signature. Use when deciding whether a study needs de novo discovery at all versus known-miRNA quantification; choosing the species and related-species miRBase references; reading the miRDeep2 score as a signal-to-noise hypothesis rather than a fixed cutoff; or filtering novel candidates against tRNA/rRNA loci to reject the classic false positives.

pku-yuangroup Bundle

Assesses RNA-seq data quality specifically for alternative splicing analysis. QC layers include experimental design audit (library prep, read length, depth, replicates), STAR 2-pass cohort-style alignment, junction saturation curves and discovery plateau detection, novel-vs-known junction ratio diagnostics, junction-overhang distribution, splice-site strength scoring (MaxEntScan intrinsic + SpliceAI context-aware), strandedness verification, GENCODE basic vs comprehensive choice, and rRNA contamination screening. Splicing analysis is more demanding than DGE on read length, depth, library prep, alignment strategy, and annotation choice — failures silently bias PSI estimates and inflate novel-junction false positives. Use when evaluating data suitability for splicing analysis, troubleshooting low event detection, or designing sequencing experiments where AS is a primary endpoint.

pku-yuangroup Bundle

Validates predictive models on omics and biomedical data with nested cross-validation, group/batch/temporal-aware splits, the full data-leakage taxonomy, probability calibration, decision-curve net benefit, optimism correction, sample-size planning, and TRIPOD+AI reporting. Use when estimating model performance honestly, choosing a CV scheme, detecting leakage, or judging whether reported discrimination means the model is actually useful. For feature selection itself see machine-learning/biomarker-discovery; for confirmatory-trial inference see clinical-biostatistics/trial-reporting.

pku-yuangroup Bundle

Decision-grade statistical analysis for metabolomics intensity tables. Covers transformation and scaling (Pareto vs unit-variance as a hidden hypothesis), unsupervised structure (PCA/HCA for QC), permutation-validated PLS-DA/OPLS-DA (R2 vs Q2, double CV, VIP as heuristic), univariate testing (Welch/Mann-Whitney/ANOVA/LMM with covariate adjustment), and dependence-aware multiple testing. Use when testing which metabolites differ, building or validating a discriminant model, choosing a scaling, or correcting many correlated tests. For sample-wise normalization/drift correction see metabolomics/normalization-qc; for ML classifiers and selection-inside-CV leakage see machine-learning/biomarker-discovery and machine-learning/model-validation; for pathway interpretation see metabolomics/pathway-mapping; for design/power/multiplicity regime see experimental-design/multiple-testing.

pku-yuangroup Bundle

Builds diagnostic and prognostic classifiers on omics feature matrices with regularized logistic regression, random forest, and gradient-boosted trees, handling the p>>n regime, batch shortcut learning, class imbalance, and probability calibration. Use when building a classifier from expression, methylation, or variant data, choosing an algorithm for high-dimensional small-n data, or diagnosing a suspiciously perfect AUC. For unbiased evaluation see machine-learning/model-validation; for feature selection see machine-learning/biomarker-discovery; for time-to-event outcomes see machine-learning/survival-analysis.

pku-yuangroup Bundle

Tests and estimates rhythmicity at a PRE-SPECIFIED period (canonically 24h) in time-series omics using cosinor regression (CosinorPy), JTK_CYCLE/ARSER/Lomb-Scargle meta-analysis (MetaCycle meta2d), and non-parametric tests for asymmetric waveforms (RAIN, DiscoRhythm); estimates phase (acrophase), amplitude, and MESOR, and controls FDR with an effect-size (rAMP) filter against over-detection. Use when testing for 24-hour or other known-period oscillations in a single condition (circadian, feeding-fasting, or light-dark experiments) and estimating their phase/amplitude. Not for unknown-period discovery (see temporal-genomics/periodicity-detection) or comparing rhythms between conditions (see temporal-genomics/differential-rhythmicity).

pku-yuangroup Bundle

Controls error rates across thousands of simultaneous tests in genomics discovery using false-discovery-rate methods (Benjamini-Hochberg 1995; Benjamini-Yekutieli 2001 for arbitrary dependence; Storey q-value with pi0 estimation; local FDR; independent filtering Bourgon 2010; covariate-weighted FDR via IHW Ignatiadis 2016), plus family-wise error control (Bonferroni, Holm) and the GWAS genome-wide threshold. Covers the FDR-versus-FWER choice as the discovery-versus-confirmatory distinction, the dependence assumptions behind BH (PRDS) versus BY, pi0 estimation, the independent-filtering and false-coverage-rate traps, and reproducibility ranking via IDR (Li 2011). Use when correcting p-values from genome-wide tests, choosing between BH/BY/q-value/Bonferroni, setting an FDR threshold, applying IHW or independent filtering, or interpreting q-values. For confirmatory trials with few pre-specified endpoints (closed testing, graphical/gatekeeping), see clinical-biostatistics/multiplicity-graphical.

pku-yuangroup Bundle

Selects biomarker features from high-dimensional omics data using Boruta all-relevant selection, mRMR, LASSO/elastic-net, and stability selection, while controlling the leakage, irreproducibility, and correlated-feature traps that make most published signatures fail to replicate. Use when identifying candidate biomarkers, deciding between an all-relevant and a minimal-optimal selector, or judging whether a selected gene set is reproducible. For unbiased performance estimation of the resulting model see machine-learning/model-validation; for interpreting a trained model see machine-learning/prediction-explanation.

revfactory Bundle

A specialized skill for designing decision trigger maps and strategy option portfolios within scenario response strategies. Used by the strategy-architect agent when converting robust/hedge/option strategies into concrete execution plans. Automatically applied in contexts such as 'decision triggers', 'strategy options', 'execution roadmap', 'trigger map', 'hedge strategy'. However, actual project management tool (Jira, Asana) integration and budget execution approval are outside the scope of this skill.

revfactory Bundle

crisis stakeholder mapping framework. situation-analyst and message-strategist agent crisis when stakeholderby response strategy establishto do when reference. 'stakeholder analysis', 'crisis etc.grade', 'impact assessment' request when usage. However, rate specialistdocument versus scope outside.

revfactory Bundle

ESG materiality assessment matrix. Referenced by the esg-reporter and improvement-planner agents when evaluating ESG issue materiality and setting priorities. Use for 'materiality assessment', 'importance analysis', or 'Materiality Matrix' requests. Stakeholder surveys and external certification are out of scope.

yigityildiz0 Skill

Route operational work to focused, evidence-based workflows for SOPs, capacity, change, risk, compliance evidence, runbooks, vendor review, stakeholder updates, and process improvement. Use when a task is about repeatable execution, operating cadence, handoffs, or operational decision support.

yigityildiz0 Bundle

Discovers all businesses of a given type in any geography using Nimble WSAs. Two modes: Discovery finds businesses from scratch; Audit compares a user's.

yigityildiz0 Skill

Plan, conduct-support, or analyze ethical user research such as interviews, usability studies, surveys, diary studies, or discovery research. Use for research plan, interview guide, usability test, participant questions, research recruitment, or user insights. Turkish triggers: kullanıcı araştırması, görüşme ve anket planı, içgörü sentezi, araştırma soruları.

yigityildiz0 Bundle

Product management analysis for engineering-informed decision framing. Use when a task needs product framing, feature prioritization based on user impact and engineering reality, scope control to prevent complexity creep, or structured now/next/later sequencing with explicit tradeoffs. Turkish triggers: ürün kararı, PRD ve önceliklendirme, kullanıcı ve iş hedeflerini dengele.

yigityildiz0 Skill

Plan a realistic sprint or short delivery cycle with goal, scope, capacity, dependencies, acceptance criteria, risks, and review signals. Use for sprint planning, iteration planning, backlog selection, delivery planning, or team capacity planning. Turkish triggers: sprint planı, kapasite ve iş seçimi, bağımlılık ve risk, gerçekçi taahhüt.

yigityildiz0 Skill

Safely plan and apply a project release version bump with ecosystem-aware file discovery, previewed diffs, changelog evidence, validation, and rollback. Use.

yigityildiz0 Skill

Route product strategy and delivery work to focused workflows for product framing, discovery, competition, metrics, sprint planning, stakeholder communication, and telemetry. Use when a task concerns user problems, scope, prioritization, launch, outcomes, or product decisions. Turkish triggers: ürün yönetimi işi, keşif/strateji/roadmap/teslimat, doğru ürün becerisine yönlendir.

yigityildiz0 Skill

Write a concise, evidence-based stakeholder update for product, engineering, operations, research, or program work. Use for weekly update, status report, executive summary, project update, risk update, or leadership communication. Turkish triggers: paydaş güncellemesi yaz, ilerleme/risk/karar ve sonraki adım, yönetici özeti.

jiayaoqijia Bundle

Discover and manage OKX-aggregated DeFi products and positions across protocols and chains. Use for generic or venue-agnostic yield, APY, or TVL discovery and history; DeFi deposits, staking, liquidity, withdrawals, rewards, lending, CLMM analysis; and DeFi portfolio or position views. Requests targeting a named protocol belong to DApp discovery. Triggers include earn yield, best APY, DeFi product, APY/TVL history, deposit, stake, withdraw, redeem, provide or remove liquidity, claim rewards, borrow or repay, CLMM, V3 liquidity charts, DeFi portfolio, and DeFi holdings.

jiayaoqijia Bundle

Interact with DeFi protocols on MAINNET via the ChainGPT plugin. Aave V3 (supply/borrow/repay/withdraw + health-factor monitoring across 7 chains), Lido stETH staking, EigenLayer restaking. Yield discovery: Pendle yield-trading markets (PT/YT), Morpho Blue lending markets + MetaMorpho vaults. Custody-free — plugin builds unsigned tx, user signs externally. Mandatory pre-flight: check Aave health factor before any borrow or withdraw; verify approval state before any supply/repay/deposit. Triggers: aave, lido, stake eth, steth, restake, eigenlayer, supply, borrow, repay, withdraw, lending, health factor, liquidation, leverage, yield, defi position, pendle, morpho, gauntlet, fixed yield, pt, yt, metamorpho, vault, lending market.

pku-yuangroup Bundle

Infer or annotate TCR antigen specificity by unsupervised clustering (TCRdist/tcrdist3, GLIPH2, clusTCR, GIANA) and database lookup (VDJdb, IEDB, McPAS-TCR), and rank candidates with supervised predictors (ERGO-II, NetTCR-2.x, pMTnet) under explicit caveats. Encodes the central truth that general TCR-epitope prediction for UNSEEN epitopes essentially does not work (collapses to near-random; IMMREP22, Grazioli 2022) because labeled data is dominated by a few immunodominant epitopes and there is no true negative set — so clustering for discovery is the honest task and de-novo binding needs wet-lab validation. Use when annotating TCR specificity or grouping a repertoire. Epitope/MHC context lives in mhc-binding-prediction.

pku-yuangroup Bundle

Analyze spatial cell-cell interactions, neighborhoods, and niches in IMC/MIBI data with squidpy and imcRtools, covering neighborhood-enrichment permutation nulls, the abundance-vs-density confound, inhomogeneous Ripley's K, cellular-neighborhood discovery, graph-construction (contact vs proximity), and edge effects. Use when testing whether cell types co-locate, choosing a spatial null, building a neighbor graph, discovering tissue niches, or deciding whether a spatial pattern is real or a density/segmentation artifact.

pku-yuangroup Bundle

Explains ML predictions on omics data with SHAP, LIME, and permutation importance, handling the correlated-feature trap, the conditional-vs-interventional Shapley choice, and the attribution-is-not-causation boundary. Use when interpreting an omics classifier, debugging shortcut/batch learning, or deciding whether an attribution ranking can be trusted as biology. For validated feature selection see machine-learning/biomarker-discovery; explanations are not a selection method.

pku-yuangroup Bundle

Nominates and assesses CRISPR off-target sites genome-wide. Enumerates candidate sites by mismatch and bulge tolerance with Cas-OFFinder/CRISPRitz, ranks them with the published CFD score (SpCas9-only, relative ranker) or MIT/CRISTA/energy models, runs variant-aware screening against gnomAD/individual genomes (CRISPRme), and frames the empirical genome-wide discovery assays (GUIDE-seq, CIRCLE-seq, CHANGE-seq, DISCOVER-seq, Digenome-seq) and high-fidelity nuclease choice (HiFi Cas9, Sniper-Cas9, eSpCas9, SpCas9-HF1). Use when assessing guide RNA specificity, choosing among candidate guides, screening a therapeutic guide against population variation, or planning empirical off-target validation. Distinguishes predicted vs detected vs validated. On-target activity scoring and deaminase (Cas-independent) base/prime-editor off-targets are separate skills.

pku-yuangroup Bundle

Estimates SNP heritability and partitions it across functional annotations, cell types, and loci from GWAS summary statistics or individual-level genotypes. Implements LDSC, stratified LDSC with the baseline-LD model, Finucane 2018 cell-type prioritization, LDAK SumHer, HDL, HESS local heritability, BOLT-REML, GCTA-GREML, graphREML, and Popcorn cross-population genetic correlation. Use when computing total h2_SNP from summary stats, partitioning heritability across functional categories, prioritizing trait-relevant tissues or cell types from ENCODE/Roadmap chromatin marks, reconciling LDSC vs LDAK enrichment estimates, computing local heritability with HESS, estimating genetic correlation between traits, or producing publication-grade enrichment with calibrated sensitivity to model assumptions.

pku-yuangroup Bundle

Chooses a bulk multi-omics integration strategy before any tool runs by mapping the biological question (subtype discovery, shared axis of variation, predictive signature, pairwise correlation) to a method class, naming the sample correspondence (paired-vertical, horizontal, mosaic, diagonal), enforcing the n<<p discipline that makes a held-out cohort the endpoint instead of in-cohort cross-validation, and running the per-view variance-imbalance diagnostic. Covers the early/mixed/intermediate/late taxonomy, why vertical and horizontal integration are different problems, and why a shared factor dominated by one omic is not integration. Use when deciding which integration method fits a question, whether data is paired or mosaic, supervised or unsupervised, or how to validate an integrated result. For unsupervised factors see mofa-integration; for supervised signatures see mixomics-analysis; for stratification see similarity-network; for single-cell see single-cell/multimodal-integration.

pku-yuangroup Bundle

Stratifies patients into multi-omics subtypes by building one patient-by-patient similarity network per omic, fusing them with SNF's cross-network diffusion, and spectral-clustering the fused graph - then defending the clusters with stability, survival separation, and replication. Covers why spectral clustering always returns the requested cluster count so a subtype is a claim not a discovery, why the eigengap is a graph property not a biological truth, why fusion is not automatically better than the best single omic, why SNF needs complete data while NEMO handles mosaic cohorts, and the SNFtool API gotchas (dist2 returns squared distance, affinityMatrix width is sigma, spectralClustering K is the cluster count). Use when discovering patient subtypes from multiple omics, choosing a cluster number, validating subtypes, or handling partial multi-omic data. For feature-space factors see mofa-integration; for supervised signatures see mixomics-analysis; for survival see clinical-biostatistics/survival-analysis.