// Track and synthesize current AI hotspots into a bilingual HTML daily report. Use when the user says "AI热点", asks for AI日报/AI日报 HTML/AI hot topics, or wants the best recent AI products, papers, viewpoints, and cognition-shifting items from AI/news aggregators.
Use when the user asks Codex to research, find learning materials, process "素材：" links, "精读" a material, build a material radar, or use SenSight-like broad information retrieval for career learning and Agent infra tracking.
Extract a Markdown heading tree with line numbers before editing or integrating notes. Use when you need to inspect a long Markdown file quickly and choose the best insertion point instead of editing blind.
Fetch and extract full text from arxiv paper HTML pages. Invoke when user asks to read an arxiv paper, analyze a paper's content, or when given an arxiv ID/URL.
Inspect GitHub pull requests, issues, workflow runs, and API data with the gh CLI. Use when the user wants repository facts from GitHub without opening the browser, especially for PR status, CI failures, issue lists, or structured JSON output.
Organize tasting menus, menu photos, and visit notes into the right gourmet note. Use when the user shares a restaurant menu, wants a tasting write-up, or asks to merge a new visit into Notes/Gourmet.md without overwriting earlier visits.
Browser automation. When you need to visit a webpage, open a website, take a screenshot, or perform browser automation, **you MUST read this SKILL.md first** — contains required parameters and operating procedures. **Calling the browser tool without reading may result in failed operations or unexpected behavior.**
| name | ai-hotspots |
| description | Track and synthesize current AI hotspots into a bilingual HTML daily report. Use when the user says "AI热点", asks for AI日报/AI日报 HTML/AI hot topics, or wants the best recent AI products, papers, viewpoints, and cognition-shifting items from AI/news aggregators. |
Use this skill to produce a high-signal AI daily report, not a raw hot-list dump.
When the user says AI热点, treat it as:
Find new AI-related products, papers, viewpoints, and cognition-shifting materials from the tracked sources. Pick the best 10. If an item is longer than 1000 Chinese characters or roughly 700 English words, summarize it in <=100 Chinese characters plus the link. Return a detailed bilingual AI daily report in HTML page format.
Default delivery: do not paste the full HTML source into chat. Save a polished HTML report under .local/ai-hotspots/reports/ai-daily-YYYY-MM-DD.html, then respond with a compact Markdown digest and a file link. Paste raw HTML only if the user explicitly asks for source code.
If the user asks to schedule it every morning, create an automation only after the wake-up time is clear.
Read references/source-list.md for the default source set and source roles.
Use the listed aggregators as discovery surfaces. For factual or technical claims, follow primary sources before ranking when possible:
Do not treat social posts or aggregator summaries as final truth.
Pick exactly 10 items unless the user asks for another count. Prefer:
Rank for the user's current priorities:
Demote items that are only funding/news hype, duplicate commentary, thin product marketing, or unverifiable rumor.
Create a complete HTML page. Keep it readable as a standalone browser page, not as a code snippet in chat.
Required sections:
AI Daily / AI 日报 - YYYY-MM-DD;Visual requirements:
Use concise Chinese first, English second. Do not pad bilingual text if English adds no value; translate the core judgment, not every word mechanically.
If the report includes materials that deserve later reading, also add them to .local/LEARNING_MATERIAL_CANDIDATES.md using the existing S/A/B/Unread convention from the research material workflow.
If access fails, mark the source or item as unread. Never pretend a source was read.