productivity▌

Role: Portfolio Experience Designer

Real-user dogfooding with emotional friction tracking, click efficiency counting, and resilience testing to produce ranked audit reports. \n \n Supports three operating modes: UX Walkthrough (persona-based task completion), QA Sweep (systematic feature testing), and Targeted Check (focused area validation) \n Tracks emotional friction signals (trust, anxiety, confusion), click efficiency, form resilience (mid-navigation, back button, refresh), and asks \"would I come back?\" \n Three depth level

Creates comprehensive handoff documents that enable fresh AI agents to seamlessly continue work with zero ambiguity. Solves the long-running agent context exhaustion problem.

Automated knowledge site generator for any domain with AI-created content, design system-driven pages, and one-click deployment. \n \n Generates 20-30 core concepts with AI-authored descriptions, examples, and quiz questions tailored to the topic \n Implements four core learning modes: flashcards with keyboard shortcuts, progressive learn pages, knowledge quizzes, and searchable concept index \n Creates topic-specific homepage copy, statistics, and footer text via AI analysis; no template copyin

Query train schedules and remaining tickets from China Railway 12306.

Guided workflows for common git operations that benefit from structured steps.

Search the web for free using DuckDuckGo - no API key or rate limits.

Advanced Git history management with rebasing, cherry-picking, bisect, worktrees, and reflog recovery. \n \n Interactive rebase enables commit squashing, rewording, reordering, and dropping to clean history before merging \n Cherry-pick applies specific commits across branches; bisect uses binary search to find commits that introduced bugs \n Worktrees allow simultaneous work on multiple branches without stashing or switching contexts \n Reflog tracks all ref movements and recovers deleted commi

../../../product-team/agile-product-owner/SKILL.md

Drafts platform-specific social media posts with research-backed content and generated companion images. \n \n Supports LinkedIn posts (1,300 characters with professional tone) and Twitter/X threads (280 characters per tweet with 1/🧵 format) \n Requires delegating research to a subagent before writing, then reading findings to ensure accuracy and relevance \n Generates eye-catching social images automatically using generate_social_image tool with bold, high-contrast compositions optimized for s