Agent skill

info-feed-aggregator

多源信息聚合与精炼报告工具。从学术数据库(arXiv、Semantic Scholar、IEEE Xplore、Crossref) 和社交媒体(微信公众号、小红书、RSS)聚合搜索结果,经去重评分后生成精炼分析报告(PDF), 包含方向分类、核心贡献提炼、趋势分析与推荐精读。 触发词:搜论文、学术搜索、信息聚合、论文监控、搜公众号、feed、aggregate

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill info-feed-aggregator --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 5 KB
Bundled scripts: none
Path: skills/analysis/info-feed-aggregator/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Info Feed Aggregator 多源信息聚合 Skill —— 从学术论文到社交媒体,一站式搜集、去重、评分、报告。 ## 能力概览 | 来源 | 状态 | 说明 | |------|------|------| | arXiv | 默认开启 | 免费 API,无需密钥 | | Semantic Scholar | 默认开启 | 免费 API,1000次/5min | | IEEE Xplore | 默认开启 | 直接搜索,无需密钥 | | Crossref | 可选 | 免费,补充 DOI 元数据 | | 微信公众号 | 默认开启 | 搜狗微信搜索,无需配置 | | 小红书 | 暂停 | 搜索引擎索引有限,后续接入 | | 通用 RSS | 可选 | 任意 RSSHub 路由 | ## 工作流 ### 1. 即时搜索(Ad-hoc) 当用户请求搜索特定关键词时: ```bash cd /Users/zhanglinghao/Documents/Code/Skills/skills/info-feed-aggregator python3 scripts/search.py --keywords "关键词1" "关键词2" --max-results 20 ``` 读取 stdout 输出的 JSON 摘要,获取报告文件路径,然后读取 Markdown 报告并呈现给用户。 **参数说明:** - `--keywords`:搜索关键词列表(支持中英文) - `--sources`:指定数据源(默认使用所有已启用源),如 `--sources arxiv semantic_scholar` - `--max-results`:最大结果数(默认 20) - `--time-range`:时间范围,如 `7d`(7天)、`30d`(30天)、`1y`(1年) - `--language`:报告语言 `zh` 或 `en` - `--output-format`:原始报告输出格式 `json`、`markdown`、`pdf`、`both`(默认 `both` = JSON + MD)。注意:精炼报告 PDF 由 Section 4 流程单独生成,不受此参数控制 ### 2. Profile 定时搜索 当用户要求按预设方案搜索时: ```bash python3 scripts/search.py --profile daily_academic ``` Profile 文件位于 `config/profiles/` 目录,定义了多个搜索主题(topic),每个主题包含关键词、分类、时间范围等。 **列出可用 Profile:** ```bash python3 scripts/search.py --list-profiles ``` ### 3. 健

What's inside
Steps it walks through
  1. 能力概览
  2. 工作流
  3. 1. 即时搜索(Ad-hoc)
  4. 2. Profile 定时搜索
  5. 3. 健康检查
  6. 4. 精炼报告生成(核心输出)
  7. 5. 深度分析(可选后续步骤)
  8. 配置
  9. 数据源配置
  10. 搜索 Profile
  11. 输出示例
  12. 依赖安装
  13. 定时任务
Ships with 1 file
  • metadata.json
Commands it runs
cd /Users/zhanglinghao/Documents/Code/Skills/skills/info-feed-aggregator
python3 scripts/search.py --keywords "关键词1" "关键词2" --max-results 20
python3 scripts/search.py --profile daily_academic
python3 scripts/search.py --list-profiles
python3 scripts/search.py --health
python3 scripts/render_pdf.py -i reports/{timestamp}_briefing.md -o reports/{timestamp}_briefing.pdf
pip install requests feedparser
PDF 渲染依赖(pandoc + xelatex)
brew install pandoc
brew install --cask mactex  # 或 basictex + 手动安装 CJK 包
More from claude-skill-registry
All skills →
About this skill
What does the info-feed-aggregator skill do?

多源信息聚合与精炼报告工具。从学术数据库(arXiv、Semantic Scholar、IEEE Xplore、Crossref) 和社交媒体(微信公众号、小红书、RSS)聚合搜索结果,经去重评分后生成精炼分析报告(PDF), 包含方向分类、核心贡献提炼、趋势分析与推荐精读。 触发词:搜论文、学术搜索、信息聚合、论文监控、搜公众号、feed、aggregate

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill info-feed-aggregator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going