htlin222

依 ticket/issue 產出初版實作 — 解析需求、從最新 develop 切出符合命名規範的分支、寫出實作、跑既有測試與 lint、conventional commit，然後交棒給 /simplify。Use when the user types /develop, or asks to start implementing a ticket, issue, or feature request end-to-end from requirement to first commit.

Put a website behind a Cloudflare Access (Zero Trust) login gate, or remove one, entirely from the CLI — no dashboard GUI. Use when the user wants to password/email-protect a hostname, gate a Cloudflare Pages or Workers site, restrict a site to specific…

Curate a GitHub repository's wiki (the separate repo.wiki.git) into a coherent, tightly written set of pages: Home, Introduction (project + features), Roadmap, Gotchas/Lessons, Tech Debt, and an Architecture page taught through the book *Head First Software…

Build LLM apps, RAG systems, and prompt pipelines. Use for AI-powered features.

Design system architecture and component interfaces. Use for architectural decisions.

Git checkpoint management. Use when starting risky changes or needing recovery points.

Run a comprehensive code review

Analyze Claude Code context efficiency. Use when evaluating session token usage.

Define extraction schema, extract study data from full texts, and store it in a structured database for meta-analysis. Use when moving from full-text collection to statistical analysis.

End-to-end AI-assisted meta-analysis pipeline orchestration from TOPIC.txt to final manuscript and reviewer responses. Use when the user provides a topic and wants the full meta-analysis workflow, tracking, and final paper.

Orchestrate agent team for meta-analysis pipeline. Creates team, spawns teammates, manages task list and handoffs between pipeline stages.

Intake a meta-analysis topic from TOPIC.txt, translate it into a PICO or PECO protocol, and define eligibility, outcomes, and search scope. Use when starting a new meta-analysis project or refining a research question.

Collect and manage full-text PDFs for included studies, track provenance, and prepare documents for extraction. Use when moving from screening to data extraction.

Conduct literature searches for meta-analysis using Python with uv, query PubMed and other databases, deduplicate results, and store round-based bibliographies with notes. Use when building or updating the evidence corpus.

Draft and render a meta-analysis manuscript with Quarto using an IMRaD structure and embedded figures/tables. Use when preparing the final paper from analysis outputs.

Run statistical meta-analysis in R with renv, generate effect estimates, heterogeneity, and publication bias diagnostics, and export figures and tables. Use when analyzing extracted study data.

Orchestrate agent team for meta-analysis pipeline. Creates team, spawns teammates, manages task list and handoffs between pipeline stages.

Define extraction schema, extract study data from full texts, and store it in a structured database for meta-analysis. Use when moving from full-text collection to statistical analysis.

End-to-end AI-assisted meta-analysis pipeline orchestration from TOPIC.txt to final manuscript and reviewer responses. Use when the user provides a topic and wants the full meta-analysis workflow, tracking, and final paper.

Collect and manage full-text PDFs for included studies, track provenance, and prepare documents for extraction. Use when moving from screening to data extraction.

Draft and render a meta-analysis manuscript with Quarto using an IMRaD structure and embedded figures/tables. Use when preparing the final paper from analysis outputs.

Run statistical meta-analysis in R with renv, generate effect estimates, heterogeneity, and publication bias diagnostics, and export figures and tables. Use when analyzing extracted study data.

Perform title and abstract screening, apply inclusion and exclusion criteria, and assess study quality or risk of bias. Use when selecting eligible studies for meta-analysis.

Conduct literature searches for meta-analysis using Python with uv, query PubMed and other databases, deduplicate results, and store round-based bibliographies with notes. Use when building or updating the evidence corpus.

NCCN clinical practice guideline navigation for Colon Cancer. Use when a clinician needs treatment decisions, staging, workup, or evidence for Colon Cancer based on NCCN Guidelines version 2.2026.

Converts NCCN clinical practice guideline PDFs into structured skill packages for cancer treatment navigation. Use when given an NCCN PDF to create a clinical decision-support skill with progressive disclosure from diagnosis to treatment. Handles chunking,…

NCCN clinical practice guideline navigation for Acute Myeloid Leukemia. Use when a clinician needs treatment decisions, staging, workup, or evidence for Acute Myeloid Leukemia based on NCCN Guidelines version 3.2026.

NCCN clinical practice guideline navigation for Non-Small Cell Lung Cancer. Use when a clinician needs treatment decisions, staging, workup, or evidence for Non-Small Cell Lung Cancer based on NCCN Guidelines version 3.2026.

NCCN clinical practice guideline navigation for B-Cell Lymphomas. Use when a clinician needs treatment decisions, staging, workup, or evidence for B-Cell Lymphomas based on NCCN Guidelines version 3.2025.

NCCN clinical practice guideline navigation for Breast Cancer. Use when a clinician needs treatment decisions, staging, workup, or evidence for Breast Cancer based on NCCN Guidelines version 2.2026.

把官方專科醫師考題 PDF 解析成題庫,推進 hema-2026 的匯入暫存區,供管理員在網站上審閱後發布新年份。當使用者說「加入新年份」「匯入 115 年」「/bank-ingest」或帶著考題 PDF 要建題庫時使用。

血液腫瘤考古題(單題測驗/看答案/關鍵字搜尋/個人筆記,一題可有多則筆記、可讀可寫,可從 HTML 或 OpenEvidence 公開對話匯入圖文)。前綴決定動作,由 mcq_cmd.py 確定性 dispatch。當使用者輸入 /mcq 開頭的指令時使用,例如 /mcq 114-001、/mcq 114-001 answer、/mcq search: CML、/mcq note 114-001: 內容、/mcq note 114-001 #2: 內容。

Fix typos / garbled text in a hema-2026 exam question reported through the in-app feedback button (a GitHub issue). Use when the user says "fix issue N", "fix the feedback", or points at a mcq-bank issue about a question having 錯字 / wrong text. This corrects…

Use when auditing or fixing hema-2026 question answers with OpenEvidence MCP: read the question from D1, ask OpenEvidence for a verdict, report pending answer/explanation changes for user approval, then update D1 with history.

Install, update, clean up, uninstall, or check the status of openevidence-mcp on this machine. Use when the user wants to set up openevidence-mcp, update to the latest release, register/unregister the MCP server with Claude/Codex, reap stray relay daemons, or…

Query OpenEvidence (clinical evidence assistant) without an MCP server. Closely mirrors the openevidence-mcp tool surface - check auth, list question history, fetch an article, or ask a new question (with optional follow-up thread). Use when the user asks…

Implement OpenEvidence rate limiting, backoff, and request optimization. Use when handling rate limit errors, implementing retry logic, or optimizing API request throughput for clinical queries. Trigger with phrases like "openevidence rate limit",…

Appraise a CLAIM (e.g. a popular diet or health product) — decompose into PICO sub-questions, run a Q1/post-2016/CrossRef-verified systematic review per question, GRADE each, cross-check with OpenEvidence, and ship a verdict-style bilingual site to Cloudflare…

World-class automated literature review pipeline - the single entry point for all lit review operations (brainstorm, search, review, render)

Brainstorm and refine research topics with comprehensive search term generation for literature review

Generate lizard-gslide-module compatible pure HTML (gslide-html v1) that maps to the 11 official Google Slides layouts. Use when the user wants slide content authored as HTML for the "HTML to Slides" importer, asks for "gslide html" / "模組相容 HTML" / "轉成 Google…

Insert and style elements (tables, text boxes, shapes) onto Google Slides at exact positions via the Apps Script advanced Slides service. Use when adding/positioning page elements programmatically, or when "object could not be found" / wrong-style /…

Mint the daily CCChange 講義 from the Claude Code CHANGELOG and open a PR. Use when asked to write today's post, run the daily routine, check whether Claude Code shipped a new version, or publish to the CCChange site. Handles the 24-hour freshness check,…

去除文字中的 AI 生成痕跡。適用於編輯或審閱文字，使其聽起來更自然、更像人類書寫。 基於維基百科的「AI 寫作特徵」綜合指南。偵測並修復以下模式：誇大的象徵意義、 宣傳性語言、以 -ing 結尾的膚淺分析、模糊的歸因、破折號過度使用、三段式法則、 AI 詞彙、否定式排比、過多的連接性短語。

台灣護理人員撰寫實證護理報告（實證讀書報告、實證案例分析）的完整教練技能，專為護理進階制度 N1–N4 升等、台灣護理學會與台灣實證護理學會審查格式而設計。當使用者提到「實證護理報告」、「實證案例分析」、「實證讀書報告」、「N2 報告」、「N3 報告」、「N4 報告」、「護理進階報告」、「護理升等」、「PICO」、「5A 步驟」、「CASP 評讀」、「護理 EBP」、「EBN」、「evidence-based…

線上被惡意質疑、人身攻擊、帶風向、截圖喊告恐嚇時的冷靜應對教練。當使用者說自己「被攻擊」「被網友圍剿」「被酸民纏上」「有人帶風向」「被截圖喊告」「對方一直挑語病」「不知道該不該回」「快氣炸了想反擊」「被影響者/網紅針對」,或貼上一段別人攻擊他的留言、私訊、貼文要你幫忙看怎麼辦時,務必觸發此技能。即使使用者只是說「有人在網路上一直煩我」「這留言好過分我該回嗎」也應觸發。此技能是防禦與自保導向:拆解對方在用什麼操弄招數、預判下一步、分流哪些該理哪些不該理、攔住使用者別發出事後後悔的話、提供不升級衝突的回應。此技能不產出…

Create decks and add cards/flashcards to the user's AnkiWeb account from the command line. Bundles a self-contained Python CLI plus the user's AnkiWeb credentials, so no setup is required. Use whenever the user wants to add a flashcard or note to…