每日新闻日报 v2.3
每日新闻自动采集与报告生成。双引擎交叉验证 + 官方媒体优先 + 900秒超时容错。v2.3 稳定运行版(2026-06-01)。 Skill: 每日新闻日报 v2.3 Owner: paudyyin Summary: 每日新闻自动采集与报告生成。双引擎交叉验证 + 官方媒体优先 + 900秒超时容错。v2.3 稳定运行版(2026-06-01)。 Tags: latest:2.3.0 Version history: v2.3.0 | 2026-06-01T03:05:44.720Z | user v2.3 稳定版:双引擎交叉验证(bocha基础搜+baidu数据验证)、官方媒体优先、timeout 900秒、每类6-10条、彻底解决超时问题 v2.1.0 | 2026-05-27T02:04:36.129Z | user v2.1: 格式硬约束(强制编号列表、来源标注、可信度标记);类别增至8个(白色家电独立);新增正误示例对比,防止Agent自由发挥 Archive index: Archive v2.3.0: 4 files, 5349 bytes
Rank
62
Safety
84
Downloads
1.3k
Updated
Oct 10, 2026
Version
2.3.0
Source
CLAWHUB
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 1.3K downloads reported by the source. Last updated 10/10/2026.
Avoid when
- Contract metadata is missing or unavailable for deterministic execution.
Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing
Public facts
Every fact links back to the source it came from.
- Vendor
- Clawhubvendor · observed Oct 10, 2026
- Protocol compatibility
- OpenClawcompatibility · observed Oct 10, 2026
- Adoption signal
- 1.3K downloadsadoption · observed Oct 10, 2026
- Latest release
- 2.3.0release · observed Jun 1, 2026
- Handshake status
- UNKNOWNsecurity
Install and run
Setup complexity: low.
clawhub skill install s172x1s50dh0bgmm3yc9516nr586kk4b:daily-news-cn- Node.js workspace detected. Install dependencies securely: run `npm ci --ignore-scripts` to prevent post-install lifecycle triggers from running arbitrary code, then selectively audit the dependency tree.
- Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
- Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Contract: missing
curl -s "https://www.xpersona.co/api/v1/agents/clawhub-paudyyin-daily-news-cn/snapshot"
Documentation
CLAWHUB
13,531 characters of source documentation, loaded on request.
Extracted files
4 files captured from the source.
SKILL.md
---
name: daily-news
version: 2.3.0
description: 每日新闻自动采集与报告生成。双引擎交叉验证 + 官方媒体优先 + 900秒超时容错。v2.3 稳定运行版(2026-06-01)。
metadata:
author: Paudy
category: automation
triggers:
- 每日新闻
- 新闻日报
- yesterday news
- daily news
---
# 每日新闻自动采集 v2.3
## ⚠️ 核心规则(必须严格执行)
### 规则1:双引擎交叉比对
每类新闻先用 `web_search(channel="bocha")` 搜一轮,合并结果后,对**含具体数字**(涨幅/产量/金额/GDP 等)的条目,再用 `web_search(channel="baidu")` 做二次验证。
总搜索量约 12-14 次(8 次基础 + 4-6 次验证),确保在超时范围内完成。
### 规则2:官方媒体优先
- 🔴 **首选来源**:新华社、央视新闻、人民日报、中新网、中证网、环球网、参考消息、外交部官网、国防部官网等
- 🟡 **次选来源**:财联社、证券时报、上海证券报、中国证券报、第一财经、经济观察报等专业财经媒体
- ⚪ **慎用来源**:股吧、财富号、自媒体博客、论坛帖子、经销商网站(仅作参考,不可作为主要数据依据)
- **每条新闻必须标注来源和可信度等级**(🔴/🟡/⚪)
- **含具体数字的新闻**,必须双引擎验证通过才算可信,否则标注"⚠️ 单一来源"
### 规则3:完整内容推送到聊天
- 报告生成后,**将完整报告内容直接作为输出返回**,不要只返回摘要或文件路径
- 同时在 `memory/daily_news_YYYY-MM-DD.md` 保存完整副本
## 架构变更历史
### v2.3(2026-06-01)— 当前稳定版
- ✅ 双引擎策略:先 bocha 全量搜 → 再 baidu 验证含数据的条目(非每类都双搜)
- ✅ timeout 900 秒(实测 332 秒完成,余量充足)
- ✅ 每类 6-10 条(原 8-12,减少总量)
- ✅ 官方媒体优先级强制规则
- ✅ v2.2 连续超时问题彻底解决
### v2.2(2026-05-29)
- ✅ 对话输出规则:必须完整输出 8 类编号列表,禁止速览/缩略版
- ❌ 16 次搜索 + 480/720 秒超时 → 连续超时
### v2.1(2026-05-27)
- ✅ 格式硬约束:强制编号列表、来源标注、可信度标记
### v2.0(2026-05-21)
- ✅ 改用 web_search(freshness=oneDay),废弃 Bing/Tavily 方案
### v1.0(2026-04-21)— 已废弃
- ❌ Bing 爬虫 + Tavily API,无法可靠过滤旧闻
## 执行流程
### 步骤 1: 确定日期
计算昨日日期 YYYY-MM-DD。
### 步骤 2: 8 大类搜索(bocha 基础搜索)
依次调用 `web_search(channel="bocha", count=10)`:
| # | Emoji | 类别 | 搜索关键词 |
|---|-------|------|-----------|
| 1 | 🌍 | 全球政治军事 | `全球 国际 政治 军事 外交 最新动态` |
| 2 | 🇨🇳 | 中国政治军事 | `中国 国务院 政策 改革 外交 国防` |
| 3 | 💰 | 全球财经股市 | `美股 道琼斯 纳斯达克 标普 原油 黄金 收盘 最新` |
| 4 | 📈 | 中国财经股市 | `A股 沪指 深成指 创业板 板块 资金流` |
| 5 | 🤖 | AI/人工智能 | `AI 人工智能 大模型 芯片 算力 最新` |
| 6 | 🔭 | 科技领域 | `量子计算 半导体 航天 卫星 6G 固态电池` |
| 7 | 📱 | 消费电子 | `苹果 三星 手机 AR VR 面板 存储芯片` |
| 8 | 🏠 | 白色家电 | `白色家电 冰箱 洗衣机 空调 美的 海尔 格力` |
### 步骤 3: baidu 二次验证
对**含具体数字**(涨幅/产量/金额/GDP/温度等)的条目,用 `web_search(channel="baidu")` 做验证搜索。总验证次数控制在 4-6 次。
### 步骤 4: 内容筛选与清洗
**排除规则:**
- ❌ 排除娱乐/体育/游戏/电竞内容
- ❌ 排除往年旧闻(描述中出现 2025年、2024年等往年日期)
- ❌ 排除网页噪声
**保留规则:**
- ✅ 优先权威媒体源
- ✅ 保留包含具体数据、人物、事件的条目
- ✅ 跨类别去重
### 步骤 5: 生成报告(严格遵循格式)
#### 格式铁律
1. **每条新闻必须独立成行**,使用 `1. 2. 3.` 编号,**禁止**用分号/逗号拼接成一段
2. **每条必须标注来源和可信度**,格式:`| 媒体名 🔴/🟡/⚪`
3. **固定 8 个类别**,不得增删合并
4. **每条结构**:`**标题** — 一句话摘要。| 来源 🔴/🟡/⚪`
5. **每个类别 6-10 条**
#### 可信度标记
| 标记 | 含义 | 来源举例 |
|------|------|---------|
| 🔴 | 官方确认 | 新华社、央视、政府官网、公司官网/公告 |
| 🟡 | 专业媒体 | 36氪、界面、财新、证券时报、IT之家 |
| ⚪ | 第三方整合(仅作参考) | 论坛、博客、自媒体 |
#### 报告模板
```markdown
# 📰 每日新闻日报 v2.3 — {日期}
> 数据源:web_search(bocha) + web_search(baidu) 交叉验证
## 📌 今日一句话总结
**[用一句话概括当天最重要的 2-3 条新闻,40 字以内]**
---
## 🌍 一、全球政治军事(6-10条)
1. **新闻标题** — 一句话摘要。| 来源 🔴/🟡/⚪
...
## 🇨🇳 二、中国政治军事(6-10条)
## 💰 三、全球财经股市(6-10条)
## 📈 四、中国财经股市(6-10条)
## 🤖 五、AI 人工智能(6-10条)
## 🔭 六、科技领域(6-10条)
## 📱 七、消费电子(6-10条)
## 🏠 八、白色家电(6-10条)
---
*可信度等级:🔴官方确认 | 🟡专业媒体 | ⚪第三方整合*
```
### 步骤 6: 保存 + 推送
1. 保存到 `memory/daily_news_{YYYY-MM-DD}.md`
2. **将完整报告内容直接作为本次任务的回复输出**
## Cron 任务配置参考
```json
{
"name": "_meta.json
{
"ownerId": "kn73z7zhz92tv6skpnmpy5pdfh86j68x",
"slug": "daily-news-cn",
"version": "2.3.0",
"publishedAt": 1780283144720
}skill-card.md
## Description: 每日新闻自动采集与报告生成。双引擎交叉验证 + 官方媒体优先 + 900秒超时容错。v2.3 稳定运行版(2026-06-01)。 This skill is ready for commercial/non-commercial use. ## Publisher: [paudyyin](https://clawhub.ai/user/paudyyin) ### License/Terms of Use: MIT-0 ## Use Case: External users and developers use this skill to generate Chinese daily news reports across politics, finance, AI, technology, consumer electronics, and home appliances. The skill searches current web sources, cross-checks numeric claims, returns a full Markdown report, and saves a local archive copy. ### Deployment Geography for Use: Global ## Known Risks and Mitigations: Risk: The skill performs multiple web searches and may include inaccurate, stale, or unverified source material in a daily report. Mitigation: Review the generated report before relying on it, especially items marked as single-source or lower-confidence. Risk: The skill can save persistent local archives of daily reports. Mitigation: Delete memory/daily_news_*.md files or disable archiving if historical report retention is not desired. Risk: The bundled cron example can trigger recurring automated news collection. Mitigation: Review or disable the cron schedule before deployment. ## Reference(s): - [ClawHub skill page](https://clawhub.ai/paudyyin/skills/daily-news-cn) ## Skill Output: **Output Type(s):** [text, markdown, shell commands, configuration, guidance] **Output Format:** [Markdown report with source and confidence annotations] **Output Parameters:** [1D] **Other Properties Related to Output:** [Also saves an archive copy under memory/daily_news_YYYY-MM-DD.md when executed.] ## Skill Version(s): 2.3.0 (source: frontmatter, package.json, server release evidence) ## Ethical Considerations: Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
package.json
{
"name": "daily-news-cn",
"version": "2.3.0",
"description": "每日新闻自动采集与报告生成。双引擎交叉验证 + 官方媒体优先 + 900秒超时容错。8大类覆盖全球政经/AI/科技/家电。",
"main": "SKILL.md",
"scripts": {
"test": "echo \"No tests specified\""
},
"keywords": [
"news",
"daily",
"中国新闻",
"新闻日报",
"web_search",
"automation"
],
"author": "Paudy",
"license": "MIT"
}AionUi
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants.
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
Machine-readable data
The same record, as JSON, for agents and crawlers.
{
"facts": [
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Clawhub",
"href": "https://clawhub.ai/paudyyin/skills/daily-news-cn",
"sourceUrl": "https://clawhub.ai/paudyyin/skills/daily-news-cn",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-10T20:06:43.651Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-paudyyin-daily-news-cn/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-paudyyin-daily-news-cn/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-10T20:06:43.651Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "1.3K downloads",
"href": "https://clawhub.ai/paudyyin/daily-news-cn",
"sourceUrl": "https://clawhub.ai/paudyyin/daily-news-cn",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-10T20:06:43.651Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "2.3.0",
"href": "https://clawhub.ai/paudyyin/daily-news-cn",
"sourceUrl": "https://clawhub.ai/paudyyin/daily-news-cn",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-06-01T03:05:44.720Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-paudyyin-daily-news-cn/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-paudyyin-daily-news-cn/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 2.3.0",
"description": "v2.3 稳定版:双引擎交叉验证(bocha基础搜+baidu数据验证)、官方媒体优先、timeout 900秒、每类6-10条、彻底解决超时问题",
"href": "https://clawhub.ai/paudyyin/daily-news-cn",
"sourceUrl": "https://clawhub.ai/paudyyin/daily-news-cn",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-06-01T03:05:44.720Z",
"isPublic": true
}
]
}Record generated Oct 10, 2026.
