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-news-intelligencegit 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-news-intelligence)<a href="https://agentmods.dev/skills/zju-real/easel/skill-news-intelligence"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-news-intelligence/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-news-intelligence"><img src="https://agentmods.dev/badge/skills/zju-real/easel/skill-news-intelligence.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 | $0.00104 | $0.01729 |
| Opus 5 | $0.00052 | $0.00864 |
| Sonnet 5 | $0.00021 | $0.00346 |
| Haiku 4.5 | $0.00010 | $0.00173 |
Grade A, and why
skill-news-intelligence 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
资讯情报聚合
从中文行业媒体与垂类资讯源抓取深度内容，按创作者赛道过滤， 生成结构化中文情报简报，并给出可操作的选题方向。
与 skill-trending-topics 的分工
| skill-trending-topics | skill-news-intelligence（本 SKILL） | |
|---|---|---|
| 抓什么 | 微博/抖音/知乎/头条/B站实时热搜榜 | 中文行业媒体的深度文章 / 快讯 |
| 时效 | 分钟级，追热点 | 日级，看行业趋势 |
| 用途 | 蹭热点、快速二创选题 | 深度选题、行业观察、内容储备 |
| 输出 | 热搜排行 + 二创角度 | 情报简报 + 选题方向 |
边界规则：本 SKILL 不抓热搜榜（那是 trending-topics 的职责）。 若用户要的是"今天有什么热搜/热点"，路由到 skill-trending-topics。 本 SKILL 处理"行业里最近发生了什么、有什么值得深挖的选题"。
输入
用户 prompt 中提供以下信息（全部可选）：
- 赛道/领域：自媒体运营 / 科技数码 / 商业财经 / AI / 时事话题（有 Profile 时自动提取）
- 关键词：如 "AI"、"融资"、"新消费"（用于过滤标题）
- 深度：快速浏览 / 深度分析（深度模式下载正文，默认快速）
- 数量：每源 5-15 条（默认 10）
输出
# 资讯情报简报
日期: {date} | 赛道: {track} | 信息源: {sources}
## 要闻速览
#### 1. [标题](url)
- **来源**: 源名（领域标签） | **时间**: 发布时间
- **摘要**: 一句话中文摘要
- **洞察**: 💡 背景 / 影响 / 与创作者的关系
## 选题方向
基于今日资讯，推荐 3-5 个可操作的选题：
1. {选题} — 切入角度 + 建议平台/形式
工作流
Step 1 — 选择信息源
按赛道选择源组合（源 key 见下表，或 --list-sources 查看）：
| 赛道 | 推荐源 |
|---|---|
| 自媒体/内容运营 | woshipm,huxiu,aihot |
| 科技数码 | sspai,geekpark,infoq_cn,36kr |
| 商业财经 | wallstreetcn,huxiu,tmtpost,36kr |
| AI | aihot,infoq_cn |
| 时事/话题素材 | thepaper,tencent,huxiu |
Step 2 — 抓取数据
python3 skills/openclaw/skill-news-intelligence/scripts/fetch_news.py --source rss --limit 20 --keyword AI --no-save
参数：--source 源 key（逗号分隔，all 抓全部）；--limit 每源条数；
--keyword 关键词过滤（子串匹配，支持中文）；--deep 下载正文；--no-save 只输出 stdout。
Step 3 — 生成简报
读取 JSON，按「输出」格式生成中文简报。规则：
- 语言：全部简体中文，保留知名英文专有名词
- 反幻觉：只使用 JSON 中的数据，不编造资讯；时间缺失标"未知时间"
- 赛道过滤：有 Profile/赛道时，优先与赛道相关的条目
- 选题方向：末尾基于资讯给出 3-5 个可操作选题（切入角度 + 建议平台/形式）
- smart_fill 标记：标
smart_fill的条目是关键词不足时的宽泛补充，注明"相关度较低"
Step 4 — 保存产物
简报保存到 outputs/资讯简报/news-briefing-{date}.md。
每日简报模式
一键生成预设赛道简报：
python3 skills/openclaw/skill-news-intelligence/scripts/daily_briefing.py --profile 科技账号 --no-save
| Profile | 用途 | 包含源 |
|---|---|---|
creator |
创作者情报日报 | 人人都是产品经理 + 虎嗅 + 36氪 + AIHOT |
tech_digital |
科技数码日报 | 少数派 + 极客公园 + 36氪 + 钛媒体 + InfoQ |
business |
商业财经日报 | 华尔街见闻 + 虎嗅 + 钛媒体 + 36氪 |
ai |
AI 资讯日报 | AIHOT + InfoQ |
topics |
话题素材日报 | 澎湃 + 腾讯新闻 + 虎嗅 |
What ships with it
4 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.
- 8d ago First seen · 143 lines · 104 tokens per session scan A b013d89ecd3a
skill-news-intelligence is a skill published in the GitHub repository ZJU-REAL/Easel (841 stars, last pushed yesterday), licensed Apache-2.0. It adds 104 tokens to every session and 1,729 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 2026-09-03.
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.