원클릭으로 Manus에서 모든 스킬 실행

curate-external-feed-topics

스타62

포크11

업데이트2026년 4월 4일 07:03

Curates foreign tech blogs (e.g. Daily Dose of Data Science Substack) via RSS, classifies items into learn-likecc RAG vs Agent “技术热点” sub-topics, drafts Chinese summaries with attribution, and appends rows to the site HTML tables. Use when the user asks to ingest Daily Dose of DS, Substack feeds, auto-fetch hot topics, translate articles for topic-rag-hot or topic-agent-hot, or refresh external curated content for the course site.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

Harzva

Harzva/learn-likecc

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Curate external feeds into RAG / Agent 热点专题

Preconditions

Read reference.md for the target site’s RSS URL, robots.txt notes, and RAG vs Agent routing hints.
Confirm the user wants summaries + links (recommended) rather than republishing full translated articles (copyright risk).

Workflow

1) Fetch latest items (no extra deps)

python3 tools/fetch_substack_rss.py --url https://blog.dailydoseofds.com/feed --limit 25 --json

Use another --url for a different Substack or any RSS 2.0 feed.

2) Filter & classify

Drop duplicates (same link).
Assign each item to site/topic-rag-hot.html or site/topic-agent-hot.html using the keyword heuristic in reference.md. If both apply, pick the stronger match or ask the user once.

3) Translate & summarize for the table

For each selected item, produce:

中文标题：忠实意译，可加括号标注原文关键术语。
一句话摘要：1–2 句中文，避免大段照搬。
标签：如 Agent / RAG / 工程 / 训练 等简短词。

Always keep the 原文链接 (link from RSS).

4) Patch the site

Append a <tr> block inside the <tbody> of the target page’s curated table. Match existing columns:

日期（可用 RSS pubDate 转短日期或 — 若不可靠）
中文标题 / 摘要
原文
归档（RAG 技术热点 或 Agent 技术热点）

Add a footnote line if the batch is large: “本期条目来自 RSS 抓取 + 人工摘要，版权归原作者。”

5) Quick QA

Links open in target="_blank" with rel="noopener noreferrer".
No paywalled content quoted at length; prefer summary + outbound link.
Run a local spot-check of the edited HTML in the browser if available.

Anti-patterns

Do not scrape aggressively (no parallel hammering); RSS polling is enough for “what’s new”.
Do not mirror full post HTML into the repo without rights clearance.
Do not strip attribution or canonical URLs.

Related site pages

RAG 专题入口：site/topic-rag.html（All-in-RAG 体系参考见同页 #all-in-rag）→ 论文分析 / 技术热点
Agent 专题入口：site/topic-agent.html → 论文分析 / 技术热点 / 生态对比

이 저장소의 다른 Skills

같은 저장소

auto-dot-claude

Harzva/learn-likecc

Use when a project needs a standard .claude workspace initialized or repaired incrementally. This skill audits the existing .claude folder, adds missing files and directories without overwriting existing rules/skills/settings, and can optionally evolve the structure over time for the current project.

2026-04-2757

gen-zhihu-article

Harzva/learn-likecc

Generate Zhihu article in the style of 22-庖丁解牛专题页-知乎图文终版.md

2026-04-2757

github-repo-search-download

Harzva/learn-likecc

Use when the user wants to search GitHub repositories by keyword, inspect ranked candidates, compare likely matches, and optionally clone the selected repository into a specified local directory. Good for prompts like “帮我搜 GitHub 上相关仓库”, “帮我找并下载一个相关仓库”, “搜索 GitHub 上的项目然后拉到 reference”, or “按关键词找仓库并 clone 到指定位置”.

2026-04-2757

hot-topic-curation

Harzva/learn-likecc

Use when the task is to build or maintain a repo-local 热门话题/AI日报专项, aggregate multiple public hot-topic sources such as AIbase Daily or RSS feeds, normalize them into a reusable snapshot, route the findings into the best existing site hotspot pages, and keep the hot-topic hub updated over time.

2026-04-2757

keyword-site-topic

Harzva/learn-likecc

Use when the task is to take a user-provided keyword, search the web for relevant articles, summarize and cluster the findings, choose the most appropriate existing `site/` topic or hotspot page in this project, and draft a publish-ready Markdown article with explicit image prompt placeholders or Mermaid notes.

2026-04-2757

loloop

Harzva/learn-likecc

Use when a task should advance through repeated plan-driven loop cycles for an engineering project, paper, or long-running repo change. loloop wraps the official /loop idea with the repo's loop-in-loop method: read the current plan, inspect prior evolution notes, execute the current iteration, write a new evolution record, draft the next plan when a version is complete, and prepare the next /loop handoff.

2026-04-2757

name

curate-external-feed-topics

description

Curate external feeds into RAG / Agent 热点专题

Preconditions

Read reference.md for the target site’s RSS URL, robots.txt notes, and RAG vs Agent routing hints.
Confirm the user wants summaries + links (recommended) rather than republishing full translated articles (copyright risk).

Workflow

1) Fetch latest items (no extra deps)

python3 tools/fetch_substack_rss.py --url https://blog.dailydoseofds.com/feed --limit 25 --json

Use another --url for a different Substack or any RSS 2.0 feed.

2) Filter & classify

Drop duplicates (same link).
Assign each item to site/topic-rag-hot.html or site/topic-agent-hot.html using the keyword heuristic in reference.md. If both apply, pick the stronger match or ask the user once.

3) Translate & summarize for the table

For each selected item, produce:

中文标题：忠实意译，可加括号标注原文关键术语。
一句话摘要：1–2 句中文，避免大段照搬。
标签：如 Agent / RAG / 工程 / 训练 等简短词。

Always keep the 原文链接 (link from RSS).

4) Patch the site

Append a <tr> block inside the <tbody> of the target page’s curated table. Match existing columns:

日期（可用 RSS pubDate 转短日期或 — 若不可靠）
中文标题 / 摘要
原文
归档（RAG 技术热点 或 Agent 技术热点）

Add a footnote line if the batch is large: “本期条目来自 RSS 抓取 + 人工摘要，版权归原作者。”

5) Quick QA

Links open in target="_blank" with rel="noopener noreferrer".
No paywalled content quoted at length; prefer summary + outbound link.
Run a local spot-check of the edited HTML in the browser if available.

Anti-patterns

Do not scrape aggressively (no parallel hammering); RSS polling is enough for “what’s new”.
Do not mirror full post HTML into the repo without rights clearance.
Do not strip attribution or canonical URLs.

Related site pages

RAG 专题入口：site/topic-rag.html（All-in-RAG 体系参考见同页 #all-in-rag）→ 论文分析 / 技术热点
Agent 专题入口：site/topic-agent.html → 论文分析 / 技术热点 / 生态对比