productivity▌

Create and maintain minimal, high-signal agent documentation under 60 lines. \n \n Enforces research-backed best practices for agent-facing docs; instruction quality degrades with length \n Requires three core sections: Package Manager, File-Scoped Commands (per-file test/lint/typecheck), and Commit Attribution with agent identity \n Analyzes project structure (lock files, linter configs, CI commands, monorepo indicators) to determine what belongs in the file \n Uses headers and bullets only; re

Structured guidance for running discovery interviews and extracting actionable customer insights. \n \n Covers interview preparation, question design, participant recruitment, and technique coaching based on principles from 43 product leaders \n Emphasizes collecting behavioral stories over opinions, watching users in context, and avoiding leading questions or solution pitching \n Includes frameworks like the Four Forces for mental structure and guidance on right-sizing sample sizes (7-14 interv

Framework for writing job descriptions that attract the right candidates by defining business impact. \n \n Start with 12-month success: define what changes in the business after the hire, not a list of daily tasks \n Identify the spike: determine one or two areas where the candidate must excel, rather than seeking a generalist \n Replace proxies with outcomes: frame requirements around specific capabilities and progress, not years of experience or tool lists \n Use polarizing language intention

Establish bidirectional links between Figma design components and code implementations using Code Connect. \n \n Requires Figma MCP server connection and published components on Organization or Enterprise plans \n Automatically identifies unmapped components in Figma selections, then scans your codebase for matching code components by name, structure, and props \n Presents matched components to you for review before creating mappings, allowing selective acceptance or rejection \n Supports multip

Real-time search, content extraction, AI-powered answers, and deep research across 25+ specialized data sources. \n \n Four core APIs: Search (web, academic, financial, news), Contents (URL extraction with summarization), Answer (cited synthesis), and DeepResearch (comprehensive reports in fast/standard/heavy modes) \n Supports domain-specific queries across academic papers, SEC filings, clinical trials, stock data, prediction markets, and transportation sources with source filtering \n Official

Swift Concurrency review and remediation for Swift 6.2+ codebases. \n \n Diagnoses and fixes actor isolation, Sendable safety, and data-race warnings through targeted edits that preserve existing behavior \n Applies minimal, concrete fixes: @MainActor annotations, actor isolation, Sendable conformance, and completion-handler-to-async/await migrations \n Triages compiler diagnostics by checking project concurrency settings, actor context, and whether code is UI-bound or background work \n Verifie

Complete App Store Optimization toolkit for researching, optimizing, and tracking mobile app performance across Apple App Store and Google Play Store. \n \n Covers keyword research, competitor analysis, metadata optimization (titles, descriptions, keywords), and visual asset strategies with platform-specific character limit validation \n Includes review sentiment analysis, rating improvement tactics, and A/B testing frameworks for continuous conversion optimization \n Provides ASO health scoring

Automated analysis of market-moving news from the past 10 days with impact-ranked reporting. \n \n Collects news across six categories (monetary policy, inflation, earnings, geopolitical, commodities, corporate) using WebSearch and WebFetch, prioritizing Tier 1 sources \n Ranks events by impact score combining price movement magnitude, breadth across asset classes, and forward-looking significance \n Analyzes multi-asset reactions (equities, bonds, commodities, currencies) and compares actual ma

Write correct, performant SQL across all major data warehouse dialects. \n \n Covers five major dialects: PostgreSQL, Snowflake, BigQuery, Redshift, and Databricks with dialect-specific syntax for date/time, string functions, arrays, and JSON handling \n Includes common analytical patterns: window functions, CTEs, cohort retention, funnel analysis, and deduplication with ready-to-use examples \n Provides performance optimization tips per dialect, such as clustering keys in Snowflake, partition p

Statistical methods for descriptive analysis, trend detection, outlier identification, and hypothesis testing with practical business interpretation. \n \n Covers descriptive statistics (mean, median, percentiles, spread measures), trend analysis with moving averages and period-over-period comparisons, and simple forecasting methods for business analysts \n Includes three outlier detection approaches (z-score, IQR, percentile methods) with guidance on investigating and handling anomalies rather