Agent skill

AI Hotspots

by huangruiteng in huangruiteng/CS-Notes

Track and synthesize current AI hotspots into a bilingual HTML daily report.

MITAuto-check passedWriting & Content

Install AI Hotspots

skills CLI
$ npx skills add huangruiteng/CS-Notes --skill ai-hotspots -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install huangruiteng/CS-Notes ai-hotspots --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/huangruiteng/CS-Notes.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/ai-hotspots .claude/skills/ai-hotspots && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ai-hotspots
GitHub stars
4k
Token cost
~1.2k tokens
SKILL.md length
629 words
Files
3 (incl. references)
Skills in repo
39
Repo updated
First seen
Licence
MIT

At a glance

Track and synthesize current AI hotspots into a bilingual HTML daily report.

  • Works in 4 steps: Agent infra, coding agents,… → RL infra, agent runner,… → LLM serving constraints for agent… → …
  • The user says AI热点
  • SKILL.md covers Trigger, Sources, Selection Rules and Workflow, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

AI Hotspots is an agent skill from huangruiteng/CS-Notes. 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.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/source-list.md`).

It sits in Writing & Content, covering Translation. The licence is MIT.

When your agent uses it

  • The user says AI热点
  • Asks for AI日报/AI日报 HTML/AI hot topics
  • Wants the best recent AI products
  • Cognition-shifting items from AI/news aggregators

Example prompts

  • “/ai-hotspots”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Agent infra, coding agents, memory/context/runtime/eval.
  2. RL infra, agent runner, rollout/replay/reward.
  3. LLM serving constraints for agent runtime, vLLM, SGLang, Ray, verl.
  4. AI product interfaces and RecSys/search + LLM.

What it can do on your machine

Read from SKILL.md and the folder at commit f7b4e92. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

AI Hotspots loads about 1.2k tokens when it runs, and up to ~1.7k if it reads all its reference files. Until then it costs about 68 tokens; SKILL.md has 629 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~68
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from huangruiteng/CS-Notes at commit f7b4e92, republished under its MIT licence (© huangruiteng). 629 words, ~1,249 tokens.

Download SKILL.mdSave it as .claude/skills/ai-hotspots/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
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.

AI Hotspots

Use this skill to produce a high-signal AI daily report, not a raw hot-list dump.

Trigger

When the user says AI热点, treat it as:

text
Find new AI-related products, papers, viewpoints, and cognition-shifting materials from the tracked sources. Pick up to 10 well-supported items. 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.

Sources

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:

  • product pages, launch posts, docs, release notes;
  • papers, arXiv pages, conference pages;
  • official repos, issues, PRs, changelogs;
  • original interviews or first-party engineering blogs.

Do not treat social posts or aggregator summaries as final truth.

Selection Rules

Aim for 10 items unless the user asks for another count; return fewer when evidence quality is insufficient and explain the coverage. Prefer:

  • new products or features with credible adoption or differentiated UX;
  • papers/repos that change agent infra, model behavior, evaluation, memory, RL, inference, or developer tooling;
  • sharp viewpoints from credible builders/researchers;
  • cognition updates that alter how the user should think, build, evaluate, or invest attention.

Rank for the user's current priorities:

  1. Agent infra, coding agents, memory/context/runtime/eval.
  2. RL infra, agent runner, rollout/replay/reward.
  3. LLM serving constraints for agent runtime, vLLM, SGLang, Ray, verl.
  4. AI product interfaces and RecSys/search + LLM.

Demote items that are only funding/news hype, duplicate commentary, thin product marketing, or unverifiable rumor.

Workflow

  1. Check the current date and browse live sources; this skill depends on recent information.
  2. Scan at least two different source types when possible: aggregator + primary source, paper + repo, product page + social reaction.
  3. Deduplicate the same event across sources and keep the strongest original link.
  4. Classify each candidate as Product, Paper, Viewpoint, Cognition, Tool/Repo, or Company/Market.
  5. For long articles, write a <=100 Chinese character summary and keep the original link.
  6. Produce a polished HTML document as a local file, then answer with a short Markdown digest: top 5 items, 3 trends, 1-3 actions, report path, and unread/access-blocked notes.
Show full SKILL.md (256 more words)Show less

HTML Output Contract

Create a complete HTML page. Keep it readable as a standalone browser page, not as a code snippet in chat.

Required sections:

  • title: AI Daily / AI 日报 - YYYY-MM-DD;
  • metadata: generated time, source window, source coverage, unread/access-blocked notes;
  • top 10 list: each item has rank, category, Chinese title, English title, source link, why it matters, bilingual summary, and suggested action;
  • pattern synthesis: 3-5 cross-item trends;
  • user's action queue: 1-3 concrete next actions mapped to the user's stated interests.

Visual requirements:

  • Use a restrained editorial layout: max-width content, clear hero, compact metadata, two-column desktop cards that become one column on narrow screens.
  • Each item card should expose rank, category, source, one-line Chinese judgment, short English note, and action. Avoid dense paragraphs.
  • Use neutral background, white cards, thin borders, and one accent color. Do not use raw tables for the main report.
  • Include a small source coverage block at the bottom so unread sources do not pollute the main reading flow.
  • Make links visible and scannable with source names, not bare URLs.

Use concise Chinese first, English second. Do not pad bilingual text if English adds no value; translate the core judgment, not every word mechanically.

Persistence

A report does not itself authorize queue mutations. If the user also requests material intake, use the project’s current material owner and supported workflow, verify its receipt/readback, and never append directly to retired candidate files. Without an active owner, provide reading suggestions only.

If access fails, mark the source or item as unread. Never pretend a source was read.

© huangruiteng, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in .codex/skills/ai-hotspots of huangruiteng/CS-Notes.

  • SKILL.md
  • agents/openai.yaml
  • references/source-list.md

Open the folder on GitHubat commit f7b4e92

Compare with similar skills

AI Hotspots next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

AI Hotspots compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AI Hotspots this skillhuangruiteng/CS-Notes4k—~1.2kAutomated safety check: PassMIT
Translation Diff ExportDevolutions/UniGetUI26k—~1.1kAutomated safety check: PassMIT
Sync Translationssymfony/symfony31k—~1.9kAutomated safety check: PassMIT
Translation Diff ImportDevolutions/UniGetUI26k—~750Automated safety check: PassMIT
Translation Diff TranslateDevolutions/UniGetUI26k—~934Automated safety check: PassMIT
Generate Translationspayloadcms/payload45k—~1.1kAutomated safety check: PassMIT

Similar skills

  • Translation Diff Export

    Devolutions/UniGetUI

    Compares UniGetUI JSON locale files against English, identifies untranslated or source-changed keys, and generates patch, reference, and handoff files for a target language.

    26k GitHub stars~1.1k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Sync Translations

    symfony/symfony

    Synchronize translation catalogs across maintained Symfony branches: find messages that newer branches added to the English catalogs but that are still missing from the oldest maintained branch…

    31k GitHub stars~1.9k tokensUpdated today
    Writing & ContentAuto-check passed
  • Translation Diff Import

    Devolutions/UniGetUI

    Merges translated key-value pairs from a UniGetUI JSON localization patch back into the full language file and validates the merged result.

    26k GitHub stars~750 tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Translation Diff Translate

    Devolutions/UniGetUI

    Translates a sparse UniGetUI JSON language patch, writes completed entries into the working copy, preserves placeholders and terminology, and prepares the patch for merge-back.

    26k GitHub stars~934 tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Generate Translations

    payloadcms/payload

    A skill your agent uses when new translation keys are added to packages to generate new translations strings

    45k GitHub stars~1.1k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Drives long-form fiction, scripts, storyboards, interactive films and long-document translation through InkOS, with every change made by a typed action.

    10k GitHub starsUsed in 1 repo~1.1k tokens
    Writing & ContentAuto-check passed

More from huangruiteng/CS-Notes

All 39 skills in this repo
  • CLI Creator

    huangruiteng/CS-Notes

    Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script.

    4k GitHub starsUsed in 2 repos~2.7k tokens
    Auto-check passed
  • Codex Thread Heartbeat

    huangruiteng/CS-Notes

    Inspect and manage guarded Codex App-native or launchd heartbeats for Codex main control threads.

    4k GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed
  • Slack

    huangruiteng/CS-Notes

    A skill your agent uses when you need to control Slack from Clawdbot via the slack tool, including reacting to messages or pinning/unpinning items in Slack channels or DMs.

    4k GitHub starsUsed in 10 repos~578 tokens
    Auto-check passed
  • Codex Thread Reader

    huangruiteng/CS-Notes

    Locate and read a Codex thread by a codex thread link, thread id, or rollout path across all local CODEXHOME directories (~/.codex, ~/.codex-gpt, ...).

    4k GitHub stars~1.4k tokensUpdated 2 days ago
    Auto-check passed
  • Research Material Scout

    huangruiteng/CS-Notes

    A skill your agent uses when the user asks Codex to research, find learning materials, process "素材:" links, "请你读" / "精读" a material, build a material radar, or use SenSight-like broad information…

    4k GitHub stars~8.3k tokensUpdated 2 days ago
    Auto-check passed
  • GitHub

    huangruiteng/CS-Notes

    Interact with GitHub using the gh CLI. An agent skill from huangruiteng/CS-Notes.

    4k GitHub starsUsed in 27 repos~279 tokens
    Auto-check passed

Questions about AI Hotspots

What does AI Hotspots do?

Track and synthesize current AI hotspots into a bilingual HTML daily report. AI Hotspots is an agent skill from huangruiteng/CS-Notes. Track and synthesize current AI hotspots into a bilingual HTML daily report.

When should I use AI Hotspots?

AI Hotspots fits situations like: the user says AI热点; asks for AI日报/AI日报 HTML/AI hot topics; wants the best recent AI products; cognition-shifting items from AI/news aggregators.

How do I install AI Hotspots in Claude Code?

Run `npx skills add huangruiteng/CS-Notes --skill ai-hotspots -a claude-code`. Or copy the skill folder (.codex/skills/ai-hotspots in huangruiteng/CS-Notes) into .claude/skills/ai-hotspots in your project. Claude Code loads it when a task matches its description.

How do I install AI Hotspots in Codex?

Run `npx skills add huangruiteng/CS-Notes --skill ai-hotspots -a codex`. Or copy the skill folder (.codex/skills/ai-hotspots in huangruiteng/CS-Notes) into .agents/skills/ai-hotspots in your project. Codex loads it when a task matches its description.

Can I use AI Hotspots in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add huangruiteng/CS-Notes --skill ai-hotspots -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-hotspots, .gemini/skills/ai-hotspots, .github/skills/ai-hotspots and .opencode/skills/ai-hotspots in your project.

What does AI Hotspots need to run?

SKILL.md names no scripts, command-line tools or credentials: AI Hotspots is instructions for the agent only.

Does AI Hotspots access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is AI Hotspots safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does AI Hotspots use?

AI Hotspots is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does AI Hotspots use?

About 1.2k tokens (SKILL.md is roughly 5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 412 tokens, read only when the agent opens those files.

What are the alternatives to AI Hotspots?

Skills that share tags, products or a category with AI Hotspots: Translation Diff Export (Devolutions/UniGetUI, 26k stars), Sync Translations (symfony/symfony, 31k stars), Translation Diff Import (Devolutions/UniGetUI, 26k stars) and Translation Diff Translate (Devolutions/UniGetUI, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Hotspots?

huangruiteng (a GitHub user) maintains it in huangruiteng/CS-Notes, which has 4,001 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on October 8, 2026.

Source: huangruiteng/CS-Notes on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.