agentleFS
Sign inStart free
Howie126313Howie126313/obsidian-vault-kit/skills/article-to-markdown/SKILL.md

article-to-markdown

Skill3 starsChanged 7 months agoApache-2.0View on GitHub

Convert external URLs into structured Markdown and save to the Obsidian vault. Use when the user provides an external URL (article, blog post, tweet thread, newsletter) and wants it saved as an Obsidian note. Triggers: "save this article", "archive this link to obsidian", "bookmark article", or when user pastes a URL and asks to save/summarize/archive it.

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:

    Use mcp__firecrawl__firecrawl_scrape to scrape the URL.

    line 30
  2. Distinctive:

    If firecrawl fails, ask the user to paste the article content directly.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Article to Markdown

Convert external article URLs into structured Markdown notes and save them to the Obsidian vault.

Workflow

Step 1: Fetch and Detect Environment

1a. Detect vault root — follow ../../_shared/common-steps.md "Vault Detection" section.

1b. Fetch article content:

Use mcp__firecrawl__firecrawl_scrape to scrape the URL. This covers most pages including JS-rendered content.

If firecrawl fails, ask the user to paste the article content directly. Do not attempt other fallback tools.

Special cases:

  • Tweet threads: use mcp__firecrawl__firecrawl_scrape, reconstruct thread order
  • Paywalled content: ask the user to paste content directly

Step 2: Restructure and Link

2a. Understand and restructure — do NOT simply copy the raw text:

  1. Identify the article's core thesis, key arguments, and supporting details
  2. Determine author, publication date, and source platform
  3. Restructure the content into logical sections with clear headings
  4. Generate 3-8 relevant tags and a 1-3 sentence summary

2b. Search for bidirectional links — follow the Bidirectional Link Search in ../../_shared/common-steps.md.

2c. Format as Obsidian Markdown — follow the template in references/article-template.md exactly:

  • YAML frontmatter with title, date, tags, summary, source
  • Blockquote metadata line with original link, author, date
  • Sections: Background → content → Key Conclusions → Further Thoughts
  • Include [[wikilink]] connections from Step 2b
  • Code blocks with language identifiers

2d. (Optional) Mermaid architecture diagram — if the article has a clear multi-layered architecture or flow worth visualizing, embed a Mermaid diagram after the blockquote metadata and before ## Background. Skip for simple or short articles. Use:

  • graph TD / graph LR for flows
  • subgraph for logical grouping
  • Concise node labels (keywords, not sentences)
  • 3-5 layers, 2-5 nodes per layer

Step 3: Save and Confirm

3a. Determine target directory — follow the Directory Mapping Rules in ../../_shared/common-steps.md. For external URL sources, match against the configured categories; if no rule matches, use the configured default directory.

3b. Save — follow the Save and Open in Obsidian section in ../../_shared/common-steps.md.

3c. Update index.md — follow the Index Update section in ../../_shared/common-steps.md. Use the article's title, summary (condensed to under 80 chars), and top 2 tags.

3d. Report to user:

  • Article title and brief summary
  • File path where it was saved
  • Tag list for review
  • Related notes linked (list the [[wikilink]] connections made)

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.

Check your setup, free