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 Zhangs-11/zs-skills --skill ai-hot-pickergit clone --depth 1 https://github.com/Zhangs-11/zs-skillsWrote 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/zhangs-11/zs-skills/ai-hot-picker)<a href="https://agentmods.dev/skills/zhangs-11/zs-skills/ai-hot-picker"><img src="https://agentmods.dev/badge/skills/zhangs-11/zs-skills/ai-hot-picker/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/zhangs-11/zs-skills/ai-hot-picker"><img src="https://agentmods.dev/badge/skills/zhangs-11/zs-skills/ai-hot-picker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00090 | $0.01351 |
| Opus 5 | $0.00045 | $0.00675 |
| Sonnet 5 | $0.00018 | $0.00270 |
| Haiku 4.5 | $0.00009 | $0.00135 |
Grade A, and why
ai-hot-picker 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI HOT 选题助手
从 AI HOT 日报中获取今日 AI 热点，帮用户快速挑选公众号选题。
流程
1. 获取数据
先把当前 SKILL.md 所在目录记为 <skill-dir>，再执行：
python3 <skill-dir>/scripts/fetch_hot.py 10
从当前 skill 的真实安装位置解析 <skill-dir>，不要硬编码用户名或 ~/.claude、~/.codex 路径。
如果返回 error 字段，说明 AI HOT 站点不可用，提示用户稍后重试。
2. 展示选题表
先展示 hot_topics（站点服务端聚类的「当前热点」，多信源同时报道的大新闻，这是当天最不能漏的选题），再展示常规选题表。
🔥 当前热点（多信源聚焦）
1. Kimi K3 发布：2.8T 参数开源模型（12 个信源报道）[链接](url)
2. xAI 开源 Grok Build（6 个信源报道）[链接](url)
如果某个 hot_topic 和 items 表格里的条目是同一话题，在表格该行话题前加 🔥 标记，不必重复列出。hot_topics 为空时跳过该板块。
将 JSON 结果格式化为 Markdown 表格。规则：
- 标题超过 28 字截断加
... - 来源列保持简洁（𝕏 @handle / 公众号名 / HN）
- 分类列精简（"模型发布/更新" → "模型"，脚本已处理）
- 原文列用
[链接](url)格式，方便用户点击跳转截图
输出格式：
数据截至 {fetched_at}，共 {total} 条热点，展示 Top {showing}：
| # | 话题 | 来源 | 距今 | 分类 | 原文 |
|----|------|------|------|------|------|
| 1 | Thinking Machines 发布... | 𝕏 @thinkymachines | ~4.8h | 模型 | [链接](url) |
| 2 | xAI 开源 Grok Build | 𝕏 @elonmusk | ~2.1h | 产品 | [链接](url) |
...
如果 recent_drafts 中有词和当前 items 标题明显重叠，在表格上方注明「已排除近期写过的 N 个相似话题」，并从表格中去掉这些条目。
3. 智能推荐
分析所有话题后，给出 2-3 个推荐编号。推荐依据：
- 多信源聚焦：
hot_topics里的话题是全网多个信源同时报道的大新闻，优先推荐 - 写作潜力：有没有故事性、争议性、或实用干货
- 角度分散：技术、产品、行业、伦理尽量覆盖不同方向
- 账号契合：与「卡卡罗特学AI」定位匹配（AI实战、开发者视角、普通人能看懂）
- 时效性：越新的话题越有抢首发的价值
格式：
推荐 X、Y、Z：[一句话理由，说明为什么这几个搭配写比较好]。回复编号即可开始写文章。
4a. 用户说「写推文」或「发推」
如果用户的输入是"写推文""发推""推文"，或者在看完选题表后说"写推文"：
- 从推荐的 2-3 个话题中，每个生成一条推文
- 也可以额外挑 1-2 个有趣的非推荐话题写推文，凑够 4-5 条
- 推文风格要求：
- 口语化，像卡卡罗特在跟朋友聊天
- 有个人判断和态度，不是干巴巴的新闻摘要
- 每条 3-6 段，段落短，一句一段
- 可以用反问、感叹、吐槽来制造节奏
- 结尾可以留一个开放性的思考或一句短评
- 不用 hashtag，不用 emoji（除非特别合适的场景）
- 输出格式：每条推文用
---分隔，前面标注对应的话题编号和标题 - 用户可以说"改第X条"来微调某条推文
4b. 用户回复编号（写长文）
用户回复编号（如 3）后：
- 把该话题的 summary 和 url 提取出来
- 用 WebSearch 或 WebFetch 补充该话题的更多背景（原文内容、社区反响、相关事件）
- 把调研结果整理成素材摘要，展示给用户确认角度
- 用户确认后，调用 kakarot-writer skill 完成长文；只有用户同时明确要求存到公众号或发布时，才继续调用 wechat-publisher
注意
- 这个 skill 的核心价值是帮用户省掉每天刷 AI HOT 挑选题的时间
- 推荐要有判断力，不要列出所有话题都说好，要敢于说某些话题不适合写
- 如果今天的热点都比较平，坦诚说「今天没有特别炸的选题，建议等一天或者写库存话题」
What ships with it
3 files 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.
- 12d ago First seen · 102 lines · 90 tokens per session scan A 7ab549661063
ai-hot-picker is a skill published in the GitHub repository Zhangs-11/zs-skills (2 stars, last pushed 5d ago), licensed MIT. It adds 90 tokens to every session and 1,351 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
jacky-motion2-0-srt
A workflow for turning a Chinese spoken script and matching SRT subtitle file into a single 16:9 HTML information animation. SRT is a subtitle file that stores text with start and end times; the animation follows those times and adds recorded-screen placeholders when needed.
ally-skill
A Chinese-language content-writing guide based on anonymized experiences, observations, and opinions, with business analysis and comedy-style pacing.
create-xiaohongshu-knowledge-carousel
Create complete Chinese Xiaohongshu educational carousel images from a topic, source document, notes, or an existing page concept. Use when Codex must plan every definition and meaning without compressing knowledge points, maintain a recurring character and visual system, directly render fully typeset 3:4 final pages…
content-score-and-fix-cn
A Chinese-language content review and editing role for short-video scripts, spoken copy, titles, product content, cover images, and videos up to 60 seconds.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.