Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ZJU-REAL/Easel --skill skill-trending-topicsgit clone --depth 1 https://github.com/ZJU-REAL/EaselWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zju-real/easel/skill-trending-topics)<a href="https://agentmods.dev/skills/zju-real/easel/skill-trending-topics"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-trending-topics/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zju-real/easel/skill-trending-topics"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-trending-topics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00123 | $0.01261 |
| Opus 5 | $0.00062 | $0.00630 |
| Sonnet 5 | $0.00025 | $0.00252 |
| Haiku 4.5 | $0.00012 | $0.00126 |
Grade A, and why
skill-trending-topics scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
热点发现
抓取多平台实时热搜数据,筛选与创作者赛道相关的热点,输出可操作的二创选题。
输入
用户 prompt 中提供以下信息(全部可选):
- 平台:微博 / 抖音 / 知乎 / 头条 / B站(默认:微博 + 抖音)
- 赛道/领域:如"科技数码"、"美妆"、"职场"(有 Profile 时自动提取)
- 目的:浏览热搜 / 找二创选题 / 追热点写内容
输出
# 热点速报
日期: {date}
平台: {platforms}
## 🔥 全平台热搜 Top 10
| # | 平台 | 话题 | 热度 | 与你的相关度 |
## 🎯 推荐二创选题(3-5 个)
### 选题 1: {标题}
- 热点来源: {平台 + 原话题}
- 二创角度: {怎么切}
- 建议格式: {图文/短视频/thread}
- 时效性: {需要多快发}
## 📊 趋势洞察
{跨平台重合话题、上升趋势、可预判的后续热点}
执行步骤
-
抓取热搜数据 — 用 web_fetch 调用下面这些已验证可用的公益 API(返回 JSON,无需 key,环境已配外网代理会自动生效)。按用户指定平台抓取,未指定默认抓微博 + 抖音。
🚫 绝对不要 web_fetch 平台官网(weibo.com / zhihu.com / douyin.com)或 tophub.today —— 它们对服务器 IP 反爬,返回登录页 / 验证码 / 403,不是数据。也不要用未在此列出的第三方接口(vvhan / tenapi 等未验证,勿用)。
主源 60s(v2,路径必须带
/v2/) basehttps://60s.viki.moe:- 微博
https://60s.viki.moe/v2/weibo| 抖音https://60s.viki.moe/v2/douyin - 知乎
https://60s.viki.moe/v2/zhihu| 头条https://60s.viki.moe/v2/toutiao - 小红书
https://60s.viki.moe/v2/rednote| 百度https://60s.viki.moe/v2/baidu/hot - 返回
{"code":200,"data":[{"title","hot","url"},...]}(部分端点为嵌套data.data,解析时都判断一下)。
备源 xxapi(主源某端点失败时用,尤其 B站) base
https://v2.xxapi.cn:- 微博
/api/weibohot| 抖音/api/douyinhot| B站/api/bilibilihot| 百度/api/baiduhot
降级顺序:60s → xxapi → 若全部失败,如实告知并请用户粘贴热搜截图/文字。完整清单与注意事项见
shared/hotlist-apis.md(可选,上面的 URL 已够用)。 - 微博
-
解析数据 — 提取每条热搜的标题和热度值,按热度排序。
-
赛道匹配 — 如有 Profile 或用户指定了赛道,过滤出与赛道相关的话题,标注相关度(高/中/低)。无赛道信息时展示全量 Top 10。
-
二创分析 — 从相关话题中挑选 3-5 个有二创价值的选题:
- 有争议性或讨论空间
- 与创作者定位匹配
- 时效性窗口足够(不是已经过气的)
- 能产出差异化内容(不是简单搬运)
-
趋势洞察 — 分析跨平台重合的话题(同时上微博和抖音热搜的说明是大事件)、上升趋势、可预判的后续热点。
-
输出 — 按输出格式交付。
Profile 感知
- 有 Profile 时:
- 读取
identity.md获取赛道和定位,自动过滤相关热点 - 读取
style.md匹配二创建议的内容形式 - 读取
platforms.md优先抓取创作者活跃平台的热搜 - 读取
audience.md判断哪些热点对目标受众有吸引力
- 读取
- 无 Profile 时:
- 展示全平台 Top 10,不做赛道过滤
- 二创建议给出通用角度
- 附注"指定赛道或提供 Profile 可获得更精准的热点筛选"
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 81 lines · 123 tokens per session scan A af5e4fc9b2d2
skill-trending-topics is a skill published in the GitHub repository ZJU-REAL/Easel (794 stars, last pushed yesterday), licensed Apache-2.0. It adds 123 tokens to every session and 1,261 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
roadtrip-navigator
Generate North American road-trip itineraries as a map-first, offline-friendly single-file HTML page. Plans around daily driving segments, overnight stops, fuel/EV-charging, national-park reservations (Recreation.gov / NPS), seasonal road closures, and timezone/border crossings — for executable, decision-ready trips.…
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
github-code-review
Review PRs: diffs, inline comments via gh or REST.
simplify-code
Sequential 3-lens cleanup of recent code changes.
skill-authoring
Author SKILL.md: frontmatter, structure, writing principles.