A Traditional Chinese analysis workflow that creates a detailed report about an article's language, structure, style, references, themes, and emotional progression. It combines measured text statistics with written interpretation tied to lines or paragraphs.
End-to-end clinical diagnostic reasoning skill. Takes a patient case (SCENARIO.md), runs multi-persona Bayesian reasoning rounds with textbook evidence and literature search, outputs structured DDx with likelihood ratios. Use when solving clinical cases, generating differential diagnoses, discussing clinical…
Claude Code instructions for htlin222/cps-skills, covering cps skills project, project structure, key commands, subagent file writing and known issues.
Use when building a curated video course website from YouTube — picking and verifying videos, organising them into chapters/units, attaching evidence or references, and shipping a static site with good SEO. Topic-agnostic; works for anatomy, cooking, guitar, statistics, welding, anything with good YouTube coverage.
A research-quality checking system for AI agents. It verifies facts, compares literature, checks experiment designs, and reviews claims about new findings.
Use when the user asks to batch-draft replies to outstanding Hahow student questions in this project — phrases like "batch draft", "draft 全部還沒回的", "處理一輪 Q&A", "幫我把待回問題草稿一下". Orchestrates: refresh snapshot → read images → parallel WebSearch → write findings → make draft → status report. Drafts only — never posts.
MCP server "hahow-watcher" as configured in htlin222/hahow-mentor-agent. Launched with bun ./channels/hahow-watcher/hahow-watcher.ts. Needs 2 environment variables to run.