htlin222

Kimi WebBridge lets AI control the user's real browser — navigate, click, type, read, screenshot, and interact with any website using the user's actual login sessions. Use this skill whenever the user wants to interact with websites, automate browser tasks, scrape web content, or perform any action requiring a real browser. Also use when the user mentions "browser", "webpage", "open URL", "screenshot", or asks to read/interact with any website. Use even for simple-sounding browser requests — the daemon handles all complexity.

Record demo GIFs/MP4s of agent TUI sessions (Claude Code, Codex CLI, other agent CLIs), synchronized via a Stop-hook sentinel so the recording knows exactly when each response finishes. Two modes - scripted (VHS tape, repeatable) and live/adaptive (tmux + asciinema, where the outer Claude reads each inner response and decides the next prompt). Use when the user wants to record, capture, or make a demo/GIF/video of a Claude Code or Codex session, create a .tape file, drive a nested agent session interactively, or asks about VHS/asciinema recording of an agent CLI.

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 emails, set up Zero Trust Access, or asks about "cf-gate". Manages Access applications and allow-email policies via the Cloudflare API using a token in the skill's .env. Note: wrangler does NOT manage Access — this uses the Cloudflare REST API directly.

Defer execution of a slash-command or prompt until a timer elapses. Starts a background polling timer that prints "TIMER DONE" on stdout, then executes the deferred prompt.

Generate an image via Codex CLI (OpenAI gpt-image-1) and save to a local path. Use when user asks to create/draw/generate an image AND save it (e.g. "draw X, save to images/y.png", "用 codex 生圖"). Requires `codex login` + `$OPENAI_API_KEY`.

DeepSeek client via the private chat.deepseek.com API (browser-exported userToken), not the official platform.deepseek.com API. Use for personal webgui automation, `x-ds-pow-response` / DeepSeekHashV1 POW solving, or SSE THINK/TOOL_SEARCH stream parsing.

End-to-end data-first research pipeline — find an underutilised public dataset, pick the publishable claim, target a journal, ship LaTeX manuscript + tagged GitHub release. Use for computational-bio / bioinformatics / clinical-genomics on TCGA, GEO, GDC, cBioPortal, or when user says "end-to-end paper" / "what's publishable here".

Todoist CRUD via API v1 — tasks (due + deadline), projects, sections, labels, comments, reminders. Use when user mentions Todoist, their todo list, scheduling/completing a task, "加到待辦", "今天的 Todoist".

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.

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 Pages.

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

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 medical / evidence-based clinical questions, references OpenEvidence, asks for "OE answers", or wants citations + BibTeX from OpenEvidence. Portable to claude.ai's /mnt sandbox - just drop the folder and a fresh cookies.json next to scripts/oe.py.

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", "openevidence throttling", "openevidence 429", "openevidence retry", "openevidence backoff".

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 Slides 的 HTML", or when converting an outline, document, or deck into importable slide HTML.

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 / can't-control-paste-position issues appear.

血液腫瘤考古題單題(題幹/選項/答案/共筆詳解/個人筆記,筆記可讀可寫,可從 HTML 或 OpenEvidence 公開對話匯入圖文筆記)。當使用者輸入 /mcq 年-題號(例如 /mcq 114-001、也接受 114-1)時使用。

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.

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 nursing」、「實證照護」、「證據等級」、「文獻評讀」，或任何護理人員詢問升等寫作、臨床問題轉化為實證主題、實證文獻搜尋策略、CASP 評讀表、Oxford 證據等級、APA 第 7 版格式、實證介入應用至個案、護理常規挑戰、去除護理迷思等情境，**務必觸發此技能**。即使使用者只是隨口問「我要寫報告」、「我要升 N3」、「幫我找主題」、「幫我設 PICO」、「這篇文獻要怎麼評讀」，也應主動啟動以提供完整的結構、句型與審查通過率最高的寫作策略。

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。此技能不產出可拿去攻擊特定真實對象的攻擊文本。

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 Anki/AnkiWeb, create or remove an Anki deck, or list their existing Anki decks or note types — e.g. "add a card to my Spanish deck", "make an Anki deck called X", "save this as a flashcard".

Queries Meta Threads via threads-scraper.p.rapidapi.com to find latest posts or users matching a keyword. Use when the user asks to scout Threads / 脈搜索 a topic, build a content pulse for zh-TW medical writing, or wants the latest discussion on a Chinese-language keyword.

The ultimate GitHub repo bootstrapper. Trigger this skill whenever a user wants to start a new project, build an idea, create a repo, scaffold a codebase, or says things like "I want to build X", "help me start a project", "create a repo for Z", "let's build something that does W", or even vaguely "I have this idea…". Guides the user from raw idea → methodology-informed plan → approved design → scaffolded repo → GitHub push. Always use for new project creation even when GitHub is not mentioned explicitly.