Agent skill

Daily News Report

by rookie-ricardo in rookie-ricardo/erduo-skills

基于预设 URL 列表抓取内容,筛选高质量技术信息并生成每日 Markdown 报告. An agent skill from rookie-ricardo/erduo-skills.

MITAuto-check passed

Install Daily News Report

skills CLI
$ npx skills add rookie-ricardo/erduo-skills --skill daily-news-report -a claude-code

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

GitHub CLI
$ gh skill install rookie-ricardo/erduo-skills daily-news-report --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/rookie-ricardo/erduo-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/daily-news-report .claude/skills/daily-news-report && 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
daily-news-report
GitHub stars
935
Token cost
~2.1k tokens
SKILL.md length
177 words
Files
3
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

基于预设 URL 列表抓取内容,筛选高质量技术信息并生成每日 Markdown 报告. An agent skill from rookie-ricardo/erduo-skills.

  • Works in 8 steps: 初始化 → 调度 SubAgent → SubAgent 任务格式 → …
  • SKILL.md covers 核心架构, 配置文件, 执行流程详解 and SubAgent 调用示例, plus 5 more sections
  • Reaches news.ycombinator.com and huggingface.co

What it does

Daily News Report is an agent skill from rookie-ricardo/erduo-skills. 基于预设 URL 列表抓取内容,筛选高质量技术信息并生成每日 Markdown 报告。

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `cache.json` and `sources.json`).

The licence is MIT.

Example prompts

  • “/daily-news-report”

Requirements

  • Pre-approved tools (allowed-tools): Task, WebFetch, Read, Write, Bash(mkdir*), Bash(date*), Bash(ls*), mcp__chrome-devtools__*

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. 初始化
  2. 调度 SubAgent
  3. SubAgent 任务格式
  4. 主 Agent 监控与反馈
  5. 评估与筛选
  6. 浏览器抓取 (MCP Chrome DevTools)
  7. 生成日报
  8. 更新缓存

What it can do on your machine

Read from SKILL.md and the folder at commit 1fb6ec5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Task
    • WebFetch
    • Read
    • Write
    • Bash(mkdir*)
    • Bash(date*)
    • Bash(ls*)
    • mcp__chrome-devtools__*

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml and markdown).

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • news.ycombinator.com
    • huggingface.co

    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

Daily News Report loads about 2.1k tokens when it runs. Until then it costs about 15 tokens; SKILL.md has 177 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~15
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

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 rookie-ricardo/erduo-skills at commit 1fb6ec5, republished under its MIT licence (© rookie-ricardo). 177 words, ~2,051 tokens.

Download SKILL.mdSave it as .claude/skills/daily-news-report/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
daily-news-report
description
基于预设 URL 列表抓取内容,筛选高质量技术信息并生成每日 Markdown 报告。
allowed-tools
Task, WebFetch, Read, Write, Bash(mkdir*), Bash(date*), Bash(ls*), mcp__chrome-devtools__*
disable-model-invocation
false
user-invocable
true

Daily News Report v3.0

架构升级:主 Agent 调度 + SubAgent 执行 + 浏览器抓取 + 智能缓存

核心架构

┌─────────────────────────────────────────────────────────────────────┐
│                        主 Agent (Orchestrator)                       │
│  职责:调度、监控、评估、决策、汇总                                    │
├─────────────────────────────────────────────────────────────────────┤
│                                                                      │
│   ┌──────────┐    ┌──────────┐    ┌──────────┐    ┌──────────┐     │
│   │ 1. 初始化 │ → │ 2. 调度   │ → │ 3. 监控   │ → │ 4. 评估   │     │
│   │ 读取配置  │    │ 分发任务  │    │ 收集结果  │    │ 筛选排序  │     │
│   └──────────┘    └──────────┘    └──────────┘    └──────────┘     │
│         │               │               │               │           │
│         ▼               ▼               ▼               ▼           │
│   ┌──────────┐    ┌──────────┐    ┌──────────┐    ┌──────────┐     │
│   │ 5. 决策   │ ← │ 够20条?  │    │ 6. 生成   │ → │ 7. 更新   │     │
│   │ 继续/停止 │    │ Y/N      │    │ 日报文件  │    │ 缓存统计  │     │
│   └──────────┘    └──────────┘    └──────────┘    └──────────┘     │
│                                                                      │
└──────────────────────────────────────────────────────────────────────┘
         ↓ 调度                              ↑ 返回结果
┌─────────────────────────────────────────────────────────────────────┐
│                        SubAgent 执行层                               │
├─────────────────────────────────────────────────────────────────────┤
│                                                                      │
│   ┌─────────────┐   ┌─────────────┐   ┌─────────────┐              │
│   │ Worker A    │   │ Worker B    │   │ Browser     │              │
│   │ (WebFetch)  │   │ (WebFetch)  │   │ (Headless)  │              │
│   │ Tier1 Batch │   │ Tier2 Batch │   │ JS渲染页面   │              │
│   └─────────────┘   └─────────────┘   └─────────────┘              │
│         ↓                 ↓                 ↓                        │
│   ┌─────────────────────────────────────────────────────────────┐   │
│   │                    结构化结果返回                             │   │
│   │  { status, data: [...], errors: [...], metadata: {...} }    │   │
│   └─────────────────────────────────────────────────────────────┘   │
│                                                                      │
└─────────────────────────────────────────────────────────────────────┘

配置文件

本 Skill 使用以下配置文件:

文件用途
sources.json信息源配置、优先级、抓取方法
cache.json缓存数据、历史统计、去重指纹

执行流程详解

Phase 1: 初始化
yaml
步骤:
  1. 确定日期(用户参数或当前日期)
  2. 读取 sources.json 获取源配置
  3. 读取 cache.json 获取历史数据
  4. 创建输出目录 NewsReport/
  5. 检查今日是否已有部分报告(追加模式)
Phase 2: 调度 SubAgent

策略:并行调度,分批执行,早停机制

yaml
第1波 (并行):
  - Worker A: Tier1 Batch A (HN, HuggingFace Papers)
  - Worker B: Tier1 Batch B (OneUsefulThing, Paul Graham)

等待结果 → 评估数量

如果 < 15 条高质量:
  第2波 (并行):
    - Worker C: Tier2 Batch A (James Clear, FS Blog)
    - Worker D: Tier2 Batch B (HackerNoon, Scott Young)

如果仍 < 20 条:
  第3波 (浏览器):
    - Browser Worker: ProductHunt, Latent Space (需要JS渲染)
Phase 3: SubAgent 任务格式

每个 SubAgent 接收的任务格式:

yaml
task: fetch_and_extract
sources:
  - id: hn
    url: https://news.ycombinator.com
    extract: top_10
  - id: hf_papers
    url: https://huggingface.co/papers
    extract: top_voted

output_schema:
  items:
    - source_id: string      # 来源标识
      title: string          # 标题
      summary: string        # 2-4句摘要
      key_points: string[]   # 最多3个要点
      url: string            # 原文链接
      keywords: string[]     # 关键词
      quality_score: 1-5     # 质量评分

constraints:
  filter: "前沿技术/高深技术/提效技术/实用资讯"
  exclude: "泛科普/营销软文/过度学术化/招聘帖"
  max_items_per_source: 10
  skip_on_error: true

return_format: JSON
Phase 4: 主 Agent 监控与反馈

主 Agent 职责:

yaml
监控:
  - 检查 SubAgent 返回状态 (success/partial/failed)
  - 统计收集到的条目数量
  - 记录每个源的成功率

反馈循环:
  - 如果某 SubAgent 失败,决定是否重试或跳过
  - 如果某源持续失败,标记为禁用
  - 动态调整后续批次的源选择

决策:
  - 条目数 >= 25 且高质量 >= 20 → 停止抓取
  - 条目数 < 15 → 继续下一批
  - 所有批次完成但 < 20 → 用现有内容生成(宁缺毋滥)
Phase 5: 评估与筛选
yaml
去重:
  - 基于 URL 完全匹配
  - 基于标题相似度 (>80% 视为重复)
  - 检查 cache.json 避免与历史重复

评分校准:
  - 统一各 SubAgent 的评分标准
  - 根据来源可信度调整权重
  - 手动标注的高质量源加分

排序:
  - 按 quality_score 降序
  - 同分按来源优先级排序
  - 截取 Top 20
Phase 6: 浏览器抓取 (MCP Chrome DevTools)

对于需要 JS 渲染的页面,使用无头浏览器:

yaml
流程:
  1. 调用 mcp__chrome-devtools__new_page 打开页面
  2. 调用 mcp__chrome-devtools__wait_for 等待内容加载
  3. 调用 mcp__chrome-devtools__take_snapshot 获取页面结构
  4. 解析 snapshot 提取所需内容
  5. 调用 mcp__chrome-devtools__close_page 关闭页面

适用场景:
  - ProductHunt (403 on WebFetch)
  - Latent Space (Substack JS 渲染)
  - 其他 SPA 应用
Phase 7: 生成日报
yaml
输出:
  - 目录: NewsReport/
  - 文件名: YYYY-MM-DD-news-report.md
  - 格式: 标准 Markdown

内容结构:
  - 标题 + 日期
  - 统计摘要(源数量、收录数量)
  - 20条高质量内容(按模板)
  - 生成信息(版本、时间戳)
Phase 8: 更新缓存
yaml
更新 cache.json:
  - last_run: 记录本次运行信息
  - source_stats: 更新各源统计数据
  - url_cache: 添加已处理的 URL
  - content_hashes: 添加内容指纹
  - article_history: 记录收录文章

SubAgent 调用示例

使用 general-purpose Agent

由于自定义 agent 需要 session 重启才能发现,可以使用 general-purpose 并注入 worker prompt:

Task 调用:
  subagent_type: general-purpose
  model: haiku
  prompt: |
    你是一个无状态的执行单元。只做被分配的任务,返回结构化 JSON。

    任务:抓取以下 URL 并提取内容

    URLs:
    - https://news.ycombinator.com (提取 Top 10)
    - https://huggingface.co/papers (提取高投票论文)

    输出格式:
    {
      "status": "success" | "partial" | "failed",
      "data": [
        {
          "source_id": "hn",
          "title": "...",
          "summary": "...",
          "key_points": ["...", "...", "..."],
          "url": "...",
          "keywords": ["...", "..."],
          "quality_score": 4
        }
      ],
      "errors": [],
      "metadata": { "processed": 2, "failed": 0 }
    }

    筛选标准:
    - 保留:前沿技术/高深技术/提效技术/实用资讯
    - 排除:泛科普/营销软文/过度学术化/招聘帖

    直接返回 JSON,不要解释。
使用 worker Agent(需重启 session)
Task 调用:
  subagent_type: worker
  prompt: |
    task: fetch_and_extract
    input:
      urls:
        - https://news.ycombinator.com
        - https://huggingface.co/papers
    output_schema:
      - source_id: string
      - title: string
      - summary: string
      - key_points: string[]
      - url: string
      - keywords: string[]
      - quality_score: 1-5
    constraints:
      filter: 前沿技术/高深技术/提效技术/实用资讯
      exclude: 泛科普/营销软文/过度学术化

输出模板

markdown
# Daily News Report(YYYY-MM-DD)

> 本日筛选自 N 个信息源,共收录 20 条高质量内容
> 生成耗时: X 分钟 | 版本: v3.0
>
> **Warning**: Sub-agent 'worker' not detected. Running in generic mode (Serial Execution). Performance might be degraded.
> **警告**:未检测到 Sub-agent 'worker'。正在以通用模式(串行执行)运行。性能可能会受影响。

---

## 1. 标题

- **摘要**:2-4 行概述
- **要点**:
  1. 要点一
  2. 要点二
  3. 要点三
- **来源**:[链接](URL)
- **关键词**:`keyword1` `keyword2` `keyword3`
- **评分**:⭐⭐⭐⭐⭐ (5/5)

---

## 2. 标题
...

---

*Generated by Daily News Report v3.0*
*Sources: HN, HuggingFace, OneUsefulThing, ...*

约束与原则

  1. 宁缺毋滥:低质量内容不进入日报
  2. 早停机制:够 20 条高质量就停止抓取
  3. 并行优先:同一批次的 SubAgent 并行执行
  4. 失败容错:单个源失败不影响整体流程
  5. 缓存复用:避免重复抓取相同内容
  6. 主 Agent 控制:所有决策由主 Agent 做出
  7. Fallback Awareness:检测 sub-agent 可用性,不可用时优雅降级

预期性能

场景预期时间说明
最优情况~2 分钟Tier1 足够,无需浏览器
正常情况~3-4 分钟需要 Tier2 补充
需要浏览器~5-6 分钟包含 JS 渲染页面

错误处理

错误类型处理方式
SubAgent 超时记录错误,继续下一个
源 403/404标记禁用,更新 sources.json
内容提取失败返回原始内容,主 Agent 决定
浏览器崩溃跳过该源,记录日志

兼容性与兜底 (Compatibility & Fallback)

为了确保在不同 Agent 环境下的可用性,必须执行以下检查:

  1. 环境检查:

    • 在 Phase 1 初始化阶段,尝试检测 worker sub-agent 是否存在。
    • 如果不存在(或未安装相关插件),自动切换到 串行执行模式 (Serial Mode)。
  2. 串行执行模式:

    • 不使用 parallel block。
    • 主 Agent 依次执行每个源的抓取任务。
    • 虽然速度较慢,但保证基本功能可用。
  3. 用户提示:

    • 必须在生成的日报开头(引用块部分)包含明显的警告信息,提示用户当前正在运行于降级模式。

© rookie-ricardo, 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 in skills/daily-news-report of rookie-ricardo/erduo-skills.

  • SKILL.md
  • cache.json
  • sources.json

Open the folder on GitHubat commit 1fb6ec5

Compare with similar skills

Daily News Report 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.

Daily News Report compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Daily News Report this skillrookie-ricardo/erduo-skills935—~2.1kAutomated safety check: PassMIT
Dailysickn33/agentic-awesome-skills47k3 repos~3.6kAutomated safety check: PassMIT
Daily News Digestclawdotnet/openclaw.net522—~211Automated safety check: PassMIT
Competitor News MonitorNousResearch/hermes-agent252k—~1.2kAutomated safety check: PassMIT
Newsalsk1992/CloddsBot3k—~462Automated safety check: PassMIT
Daily Financedigoal/blog8.6k—~1.2kAutomated safety check: PassGPL-2.0

Similar skills

  • Daily

    sickn33/agentic-awesome-skills

    Documentation and capabilities reference for Daily. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 3 repos~3.6k tokens
    AI & LLM EngineeringAuto-check passed
  • Daily News Digest

    clawdotnet/openclaw.net

    Produce a daily news brief (AI/security/dev) with links, key takeaways, and action items.

    522 GitHub stars~211 tokensUpdated today
    Writing & ContentAuto-check passed
  • Competitor News Monitor

    NousResearch/hermes-agent

    Watch named companies for material news; cited digests. An agent skill from NousResearch/hermes-agent.

    252k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed
  • News

    alsk1992/CloddsBot

    Monitor news and correlate with prediction market movements. An agent skill from alsk1992/CloddsBot.

    3k GitHub stars~462 tokensUpdated 8 days ago
    Auto-check passed
  • Daily Finance

    digoal/blog

    Generate stage-1 publishable daily financial news markdown by accessing current web data, filtering reliable macro/market news, validating numbers and article logic, and writing a source-backed brief.

    8.6k GitHub stars~1.2k tokensUpdated 2 days ago
    Marketing & SEOAuto-check passed
  • Daily Finance

    digoal/blog

    Generate stage-1 publishable daily financial news markdown by accessing current web data, filtering reliable macro/market news, validating numbers and article logic, and writing a source-backed brief.

    8.6k GitHub stars~1.6k tokensUpdated 2 days ago
    Marketing & SEOAuto-check passed

More from rookie-ricardo/erduo-skills

  • Anthropic Style Diagram

    rookie-ricardo/erduo-skills

    Draw architecture, flow and structural diagrams in the Anthropic/Claude visual language as SVG, then render and save them as PNG.

    935 GitHub stars~3k tokensUpdated 2 mo ago
    Auto-check passed
  • Ak Rss Digest

    rookie-ricardo/erduo-skills

    Curate a Chinese reading digest from a fixed bundle of RSS and Atom feeds, with a strong preference for AI agent thinking, frontier AI commentary, deep interviews, and non-boring high-signal essays.

    935 GitHub stars~1.4k tokensUpdated 2 mo ago
    Auto-check passed
  • Web To Markdown

    rookie-ricardo/erduo-skills

    Convert a web URL into cleaned Markdown with deterministic routing.

    935 GitHub stars~894 tokensUpdated 2 mo ago
    Auto-check passed
  • Gemini Watermark Remover

    rookie-ricardo/erduo-skills

    Remove the visible Gemini AI watermark from images using reverse alpha blending.

    935 GitHub stars~359 tokensUpdated 2 mo ago
    Auto-check passed
  • Translate Polisher

    rookie-ricardo/erduo-skills

    高质量文章翻译技能,采用"分析→初译→审校→终稿"四步精翻工作流。仅支持中文↔英文、中文↔日文翻译。当用户明确提出"翻译"、"translate"、"精翻"、"翻訳"、"翻译文章"、"translate to Chinese/English/Japanese"、"改成中文"、"改成英文"、"改成日文"、"翻成中文"、"翻成日文"、"翻成英文"、"英译中"、"中译英"、"中译日"、"日译中"、"日…

    935 GitHub stars~3.6k tokensUpdated 2 mo ago
    Auto-check passed
  • Transcript Polisher

    rookie-ricardo/erduo-skills

    将语音转录文本(访谈、演讲、播客、会议)精修为可读性更高的文章段落。当用户提到"字幕精修"、"transcript polish"、"润色字幕"、"把视频字幕整理成文章"、"访谈文字整理"、处理访谈记录、转录文本优化、语音转文字整理、或者需要将大段对话/演讲文本整理成可读文章时触发。适用于单人演说或多人对谈的转录文本整理,要求保留原句原词、拒绝高度概括。即使用户只是说"帮我整理一下这段文字"并附…

    935 GitHub stars~1.5k tokensUpdated 2 mo ago
    Auto-check passed

Questions about Daily News Report

What does Daily News Report do?

基于预设 URL 列表抓取内容,筛选高质量技术信息并生成每日 Markdown 报告. An agent skill from rookie-ricardo/erduo-skills. Daily News Report is an agent skill from rookie-ricardo/erduo-skills.

How do I install Daily News Report in Claude Code?

Run `npx skills add rookie-ricardo/erduo-skills --skill daily-news-report -a claude-code`. Or copy the skill folder (skills/daily-news-report in rookie-ricardo/erduo-skills) into .claude/skills/daily-news-report in your project. Claude Code loads it when a task matches its description.

How do I install Daily News Report in Codex?

Run `npx skills add rookie-ricardo/erduo-skills --skill daily-news-report -a codex`. Or copy the skill folder (skills/daily-news-report in rookie-ricardo/erduo-skills) into .agents/skills/daily-news-report in your project. Codex loads it when a task matches its description.

Can I use Daily News Report 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 rookie-ricardo/erduo-skills --skill daily-news-report -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/daily-news-report, .gemini/skills/daily-news-report, .github/skills/daily-news-report and .opencode/skills/daily-news-report in your project.

What does Daily News Report need to run?

SKILL.md names no scripts, command-line tools or credentials: Daily News Report is instructions for the agent only. Its frontmatter pre-approves these tools: Task, WebFetch, Read, Write, Bash(mkdir*), Bash(date*), Bash(ls*), mcp__chrome-devtools__*.

Does Daily News Report access the network?

SKILL.md names 2 domains. In commands or code: news.ycombinator.com and huggingface.co; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Daily News Report 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 Daily News Report use?

Daily News Report 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 Daily News Report use?

About 2.1k tokens (SKILL.md is roughly 8.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Daily News Report?

Skills that share tags, products or a category with Daily News Report: Daily (sickn33/agentic-awesome-skills, 47k stars), Daily News Digest (clawdotnet/openclaw.net, 522 stars), Competitor News Monitor (NousResearch/hermes-agent, 252k stars) and News (alsk1992/CloddsBot, 3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Daily News Report?

rookie-ricardo (a GitHub user) maintains it in rookie-ricardo/erduo-skills, which has 935 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on July 25, 2026.

Source: rookie-ricardo/erduo-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.