agentleFS
AtmoskunAtmoskun/claude-skills/skills/substack/SKILL.md

substack

Skill0 starsChanged 9 months agoMITView on GitHub

Sync Substack newsletter articles into Obsidian vault with automatic summarization, ticker detection, and copyright-compliant excerpts. ~/.claude\skills\substack Pulls all new articles from subscribed feeds, deduplicates, and saves summaries to Obsidian. Accepts either https://name.substack.com or https://name.substack.com/feed. Normalizes to feed URL automatically. Shows all configured Substack feeds. Each note contains: - Standardized frontmatter (id, type=substack, source_platform, author, published_at, ingested_at, tickers, tags) - Summary (<=500 words) -- not full text (copyright compliance) - Key excerpts (<=3 paragraphs) - Link to original article 在 ticker…

  • Installs packages

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Extract: - If RSS content is truncated (<500 chars), fetch full text via trafilatura

    line 48
  2. Distinctive:

    Save: - Write Obsidian note with standardized frontmatter

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Substack RSS to Obsidian

Sync Substack newsletter articles into Obsidian vault with automatic summarization, ticker detection, and copyright-compliant excerpts.

Project Location

~/.claude\skills\substack

When to Use This Skill

  • User says /substack sync to pull all new articles
  • User says /substack add {url} to add a new subscription
  • User says /substack list to show current subscriptions
  • User mentions "substack", "newsletter sync", or "RSS feed"

Commands

Sync All Feeds

/substack sync

Pulls all new articles from subscribed feeds, deduplicates, and saves summaries to Obsidian.

Add Subscription

/substack add https://doomberg.substack.com

Accepts either https://name.substack.com or https://name.substack.com/feed. Normalizes to feed URL automatically.

List Subscriptions

/substack list

Shows all configured Substack feeds.

CLI Usage

python "~/.claude\skills\substack\substack_fetcher.py" sync
python "~/.claude\skills\substack\substack_fetcher.py" add "https://doomberg.substack.com"
python "~/.claude\skills\substack\substack_fetcher.py" list

Workflow

  1. Read feeds - Parse RSS via fastfeedparser for each subscription
  2. Dedup - Skip articles already ingested (shared ingestion_state.db)
  3. Extract - If RSS content is truncated (<500 chars), fetch full text via trafilatura
  4. Cache - Save raw HTML to local raw_cache/ (not synced to Obsidian)
  5. Summarize - Generate summary (<=500 words) + key excerpts (<=3 paragraphs)
  6. Detect tickers - Scan content for investment-relevant ticker symbols
  7. Save - Write Obsidian note with standardized frontmatter

Output

ItemLocation
Obsidian notesDocuments/Obsidian Vault/信息源/Substack/{author_name}/YYYY-MM-DD - {title}.md
Raw HTML cache.claude/skills/substack/raw_cache/ (local only)
Feed config.claude/skills/substack/substack_feeds.yaml

Note Format

Each note contains:

  • Standardized frontmatter (id, type=substack, source_platform, author, published_at, ingested_at, tickers, tags)
  • Summary (<=500 words) -- not full text (copyright compliance)
  • Key excerpts (<=3 paragraphs)
  • Link to original article

Dependencies

pip install fastfeedparser trafilatura markdownify pyyaml

Framework Tagging (after ticker detection)

在 ticker 检测之后,自动标注内容属于分析框架的哪些维度:

from shared.framework_tagger import tag_content
sections = tag_content(text, mode="hybrid")  # e.g. ["S1", "S4.2"]

将结果添加到 frontmatter extra dict:

framework_sections: [S1, S4.2, S7]

如果 framework_tagger 不可用或返回空列表,跳过(不报错)。

Post-Ingestion

自动执行: 完成所有处理后,立即对输出文件夹执行 link 扫描(等同于 /link 信息源/Substack/),为新增笔记添加 [[wikilinks]]。 用户说"跳过 link"时跳过此步。

Related

  • /wechat-hao - Similar pipeline for WeChat articles
  • /podcast - Newsletter-like ingestion for podcast transcripts
  • /link - Auto-link new notes after ingestion
  • Shared utilities: shared/frontmatter_utils.py, shared/ticker_detector.py

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.