Interpret and act on Amazon Brand Analytics data. Analyze Search Frequency Rank (SFR), click share, conversion share, market basket analysis, and repeat purchase behavior to optimize your Amazon strategy.

Plan and optimize Amazon promotional deals — Lightning Deals, Best Deals, Coupons, and Prime Exclusive Discounts. Evaluate deal ROI, timing, and strategy for maximum sales impact.

Plan and optimize Amazon Sponsored Display campaigns. Audience targeting, product targeting, retargeting strategy, and creative optimization for awareness and conversion.

Optimize Amazon PPC campaigns by identifying and managing negative keywords. Reduce wasted ad spend by eliminating irrelevant search terms while protecting valuable converting terms.

Amazon sales volume estimator for sellers and product researchers. Estimate monthly sales and revenue from BSR (Best Seller Rank), ASIN, or keyword. Three modes: (A) BSR Calculator — input BSR + marketplace + price + category to get instant sales estimate, (B) ASIN Lookup — input ASIN to auto-fetch data and estimate sales, (C) Keyword Market Analysis — input keyword to analyze total market size and competition. Works on 12 Amazon marketplaces. No API key required. Use when: (1) estimating how many units a product sells per month, (2) sizing a market or niche opportunity, (3) analyzing competitor sales performance, (4) comparing sales across price points, (5) identifying top sellers vs long-tail distribution.

Guide to correctly interpreting BUSCO (Benchmarking Universal Single-Copy Orthologs) completeness statuses. Covers why Duplicated BUSCOs count as complete, how to parse BUSCO output files, how to compute and compare completeness across proteomes and genomes, and common counting mistakes. Relevant when running genome or proteome quality assessments with BUSCO, comparing assemblies, or reporting completeness statistics. See also: prokka-genome-annotation for annotation workflows that feed into BUSCO assessment.

Access TCGA and other cancer genomics datasets via cBioPortal REST API. Retrieve somatic mutations, copy number alterations, gene expression profiles, and clinical data (survival, stage, treatment) for thousands of cancer studies. Use for tumor mutation burden analysis, oncoprint queries, and survival analysis. For population variant frequencies use gnomad-database; for drug-gene interactions use dgidb-database.

GTARS is a Rust-backed Python library for fast genomic token arithmetic and BED file processing. Perform high-performance BED file I/O, genomic interval set operations (intersect, merge, complement, subtract), tokenization of genomic regions against a universe, and universe construction. Use for preprocessing large BED file collections, building token vocabularies for ML pipelines, and computing interval statistics at scale.

Distributed and parallel computing for larger-than-RAM datasets. Five components: DataFrames (parallel pandas), Arrays (parallel NumPy), Bags (unstructured data), Futures (task-based parallelism), Schedulers (threads/processes/distributed). Scales from laptops to HPC clusters. For in-memory speed on single machine use polars; for out-of-core analytics without cluster use vaex.

MATLAB/GNU Octave numerical computing for matrix operations, linear algebra, differential equations, signal processing, optimization, statistics, and scientific visualization. Code examples in MATLAB syntax (runs on both MATLAB and Octave). For Python-based scientific computing use numpy/scipy; for statistical modeling use statsmodels.

>-

Query the IUPHAR/BPS Guide to Pharmacology (GtoPdb) REST API for receptor-ligand interaction data, target pharmacology, and quantitative affinity metrics. Retrieve pKi/pIC50/pEC50 values, ligand classifications (approved drugs, biologics, natural products), target families (GPCRs, ion channels, nuclear receptors, kinases), and selectivity profiles across the pharmacological target space.

>

TorchDrug is a PyTorch-based machine learning platform for drug discovery. Use it for graph-based molecular representation learning, molecular property prediction (ADMET, activity), retrosynthesis prediction, drug-target interaction (DTI) modeling, and pretraining on large molecular datasets. Provides GNN layers (GraphConv, GAT, MPNN), pretrained models, and benchmark datasets in a unified PyTorch-compatible API.

Guide to KEGG pathway enrichment analysis for differential expression results. Covers over-representation analysis (ORA) vs gene set enrichment analysis (GSEA), mandatory directionality splitting, KEGG organism codes, API failure handling with offline fallbacks, cross-condition pathway comparisons, and answer-first reporting. Consult this when running pathway enrichment with clusterProfiler or gseapy on DEG results.

Optimize e-commerce checkout flow to reduce cart abandonment. Friction analysis, payment method optimization, trust signals, and checkout UX best practices.

Increase customer retention and repeat purchases for e-commerce businesses. Email flows, loyalty programs, subscription models, customer segmentation, and win-back strategies.

Optimize e-commerce returns process and reduce return rates. Returns policy design, reverse logistics, root cause analysis, and customer retention through better returns experience.

Compare and optimize shipping rates across carriers and fulfillment methods. UPS, FedEx, USPS, DHL rate comparison, zone optimization, and shipping strategy to maximize margins.

Shipping strategy — free shipping vs markup, shipping profiles, international shipping, tracking

Shop analytics — traffic sources, conversion rates, search terms, top listings performance

Optimize Google Shopping campaigns and product feeds for maximum visibility and ROAS. Feed optimization, bidding strategy, campaign structure, and Performance Max integration.

Track and analyze e-commerce sales performance across platforms. Set up KPI dashboards, trend analysis, and performance alerts to catch issues and opportunities early.

App stack advisor — essential apps by business stage, cost optimization, performance impact analysis

Google integration — Shopping feed, Performance Max, free listings, Merchant Center optimization

Comprehensive Shopify SEO optimization guide. Technical SEO, on-page optimization, collection pages, blog strategy, site architecture, and link building for Shopify stores.

Store speed audit — lazy loading, image compression, app bloat removal, theme code optimization

Theme speed and UX optimization — Core Web Vitals, Liquid code, image loading, mobile responsiveness

Supply Chain Bottleneck Analyzer for Shopify/DTC stores. Diagnose cash flow, inventory, shipping costs, and customer acquisition efficiency. Includes CAC/LTV analysis, 3PL cost optimization, and ad spend benchmarks. No API key required for basic analysis.

Creator Marketplace strategy — finding creators, negotiation, campaign management, performance metrics

Master TikTok live selling for e-commerce. Plan live sessions, engage audiences, pin products, handle real-time sales, and optimize GPM (GMV per mille) for maximum live revenue.

Affiliate collaboration — commission structure, creator selection, sample management, performance tracking

Master TikTok Shop analytics and data-driven selling. Track shop performance, video analytics, live selling metrics, creator affiliate ROI, and advertising performance.

Optimize WooCommerce stores for search engines. Covers technical SEO, product page optimization, schema markup, site speed, URL structure, and content strategy for organic traffic growth.

>

Memory management system for Claude Code — Student Loop, Smart Context, Auto Learn, Session Handoff, Correction Cycle. Triggered by memory commands (/save, /reflect, /handoff, /check) or memory-related questions. Not for general programming tasks.

Profile app performance while browsing, collecting Web Vitals and React rerender data via react-scan. Orchestrates parallel profiler subagents via playwright-cli to capture navigation timing, long tasks, layout shifts, LCP, React commit counts, render bursts, and per-component render data. Use when profiling browsing performance, finding bottlenecks, diagnosing excessive rerenders, or auditing page performance.

本技能负责分析多条笔记或想法之间的关系，发现隐含连接和长期模式。

Constructs technical Suno V5 style prompts, selects genres, and optimizes generation settings. Use when creating or refining Suno prompts for track generation.

Create markdown indexes of GitHub repositories optimized for Claude project knowledge. Indexes enable retrieval via GitHub API with semantic descriptions for effective matching.

Produce zero-shot univariate time series forecasts using the Reverso foundation model family (arXiv:2602.17634), implemented in NumPy/Numba for CPU-only container execution.

Advanced memory operations reference. Basic patterns (profile loading, simple recall/remember) are in project instructions. Consult this skill for background writes, memory versioning, complex queries, edge cases, session scoping, retention management, type-safe results, proactive memory hints, GitHub access detection, autonomous curation, episodic scoring, and decision traces.

Maintain a single structured markdown document that tracks what is happening

Sort grocery lists by aisle order using store aisle sign photos. Build aisle maps from uploaded images, match items to aisles, and output optimized shopping routes. Use when users upload aisle sign photos, request grocery list sorting, want shopping trip optimization, need store layout mapping, or mention grocery list organization.

AST-powered code navigation using tree-sitter. Each invocation auto-scans

Prepare a MemoryLane release by updating the version and release notes, then creating and pushing the tagged release commit that triggers CI. Use when the user asks to release, ship, publish, bump version, or cut a stable or prerelease version.

Get historical price data (OHLCV) for a stock. Use when user asks about price history, historical data, past performance, price over time, or needs data for chart analysis.

Configure serverless PostgreSQL databases on Neon with connection pooling, branching, and Edge Function integration. Apply when setting up serverless databases, connecting from Edge Functions, or managing database branches.

Build Next.js 15 applications using App Router, Server Components, Client Components, Server Actions, and streaming. Apply when creating pages, handling data fetching, implementing routes, or optimizing performance.

Optimize Next.js bundle size with code splitting, tree shaking, lazy loading, and build configuration. Apply when improving performance, reducing bundle size, analyzing dependencies, or optimizing load times.