Use when analyzing Xiaohongshu data with Excel, creating spreadsheets for performance tracking, building data dashboards, conducting manual analysis, or learning spreadsheet skills for social media analytics
Analyze marketing performance with key metrics, trend analysis, and optimization recommendations. Use when building performance reports, reviewing campaign results, analyzing channel metrics (email, social, paid, SEO), or identifying what's working and what needs improvement.
Synthesize qualitative and quantitative user research into structured insights and opportunity areas. Use when analyzing interview notes, survey responses, support tickets, or behavioral data to identify themes, build personas, or prioritize opportunities.
Use when creating data reports on Xiaohongshu performance, summarizing analytics findings, presenting insights to stakeholders, documenting marketing results, or building reporting templates
Profile and explore a dataset to understand its shape, quality, and patterns
Build an interactive HTML dashboard with charts, filters, and tables
Create publication-quality visualizations with Python
Use when presenting data insights, creating infographics, or making complex information visual
Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, novel plot types, or publication-quality PNG/PDF/SVG export. For quick statistical plots use seaborn.
Answer data questions -- from quick lookups to full analyses
Consolidate IBRK trade CSV files from a directory into a summary report. Groups trades by symbol, underlying, date, strike, buy/sell, and open/close. Outputs both markdown and CSV.
Update dashboard.yaml with current knowledge base metrics from analysis report
Run a full coherence sweep across the Brain Dependency Graph - computes staleness, lifecycle transitions, structural health, and generates a report
This skill should be used when the user asks to "export matrix data", "backup matrix", "export solutions", "export failures", "export warnings", or needs to export Matrix memory to a portable format.
Multi-model fact-checking. Opus checks independently, spawns a Sonnet sub-agent for a blind second review, then compares and reconciles both results into a consensus report.
Produce calibrated predict and predict_proba outputs, with optional uncertainty intervals, without generating explanations.
Fetch existing triages and untriaged regressions related to a given regression
Complete 9-step Clay enrichment workflow for 90%+ data coverage plus 58 Clay templates across 8 categories. Use when building enrichment workflows, setting up Clay tables, or maximizing data quality.
Expert Clay platform consultant for B2B data enrichment and workflow automation. Use when the user asks about Clay tables, waterfall enrichment, Clay credits, Clay pricing, Claygent, Clayscript formulas, Clay CRM sync, Clay enrichment workflows, Clay integrations, Clay Chrome extension, Clay templates, or building data pipelines in Clay. Also triggers on "Clay workflow", "enrichment waterfall", "Clay credits", "Claygent", "Clayscript", "Clay + HubSpot", "Clay + Salesforce", "Clay table", "Clay providers", "enrich in Clay", "Clay API", "Clay column", "Clay formulas", "find emails", "email waterfall", "phone waterfall", "lead scoring", "Clay debugging". Do NOT use for general CRM questions without Clay context, standalone email tools (Findymail, Hunter), or non-Clay enrichment platforms.
