mcpbeat Sign in

Converting Notion To Docusaurus Blog Agent Skill

Use when converting a Notion markdown export to a Docusaurus blog post for the dbt docs site, or when given a path to a Notion export folder/file.

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
205
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/dbt-labs/docs.getdbt.com --skill converting-notion-to-docusaurus-blog

What it tells the agent to use

found in the instruction text
Bash runs shell commands — read the instruction before connecting

The instruction itself

20 sections, as written by the author

Converting Notion Exports to Docusaurus Blog Posts

Overview

Automates conversion of Notion markdown exports into properly formatted Docusaurus blog posts for docs.getdbt.com. Handles frontmatter generation, image processing, content cleanup, and file organization.

When to Use

  • User provides a path to a Notion markdown export
  • User mentions converting Notion content to a blog post
  • User has exported content from Notion for the dbt developer blog

Workflow

1. Read Notion Export

Parse the markdown file and locate the accompanying image folder (same name as the .md file, without the hash suffix).

2. Extract Metadata

From the Notion export, extract:

  • Title: The H1 heading
  • Owner: Maps to author lookup
  • Remove the metadata block (Status, Owner, Created time) from output

3. Look Up Author

Search website/blog/authors.yml for a matching name from the Owner field.

If not found, prompt user:

Author "[Name]" not found in authors.yml.

How would you like to proceed?
1. Enter details now (name, title, photo URL, LinkedIn)
2. Scaffold empty entry to fill in manually later

Option 2 creates:

firstname_lastname:
  name: Full Name
  title: ""  # TODO
  image_url: /img/blog/authors/firstname-lastname.png  # TODO
  socials:
    linkedin: ""  # TODO
  page: true

4. Prompt for Confirmations

  • Date: Default to today + 2 days (YYYY-MM-DD)
  • Slug: Suggest SEO-optimized version (short, keywords only, drop filler words)
  • Description: Find a compelling sentence from within the article that captures the key value or insight - not just the opening line
  • Tag: Select the most appropriate tag based on content (see Tag Selection below)
  • End of content: Confirm where the publishable content ends (remove trailing internal notes)

Slug guidelines: Keep 2-4 words, include primary keywords, drop "introducing", "a", "the", "how to".

  • "Introducing dbt agent skills" → dbt-agent-skills
  • "Getting Started with git Branching Strategies" → git-branching-strategies-dbt

Tag selection: Check website/blog/categories.yml for available tags and their descriptions. Select the most appropriate tag based on the post content. Fall back to analytics craft only if no other tag fits.

5. Process Images

For each image in the Notion export folder:

  • Analyze the image to generate a semantic filename (e.g., skills-mcp-diagram.png not 74cb2aed-fe53-481b-89d0-eefd0054e0c2.png)
  • Generate alt text for accessibility
  • Copy to website/static/img/blog/YYYY-MM-DD-slug/

6. Copy Original File

Copy the Notion markdown file to website/blog/YYYY-MM-DD-slug.md first. This establishes the baseline for git diffs.

7. Commit the Raw Baseline

Stage the new blog file and any copied images and create a commit (e.g. chore: import raw Notion export for <slug>) before making any edits. This anchors the baseline in git history so that all subsequent transformations appear as a single, reviewable diff against the import commit.

8. Apply Transformations as Edits

Apply transformation rules (see below) as individual edits to the copied file. This makes changes visible in git diff, allowing review of exactly what was modified.

9. Spellcheck Pass

Run a spellcheck on the content and fix any typos or spelling errors. Be careful to preserve technical terms, product names (dbt, MetricFlow, BigQuery), and intentional stylistic choices.

10. Report Results

Summarize: files created, images processed, spelling corrections made, any TODO items (e.g., incomplete author entry).

Transformation Rules

Frontmatter

Generate YAML frontmatter:

---
title: "Title from H1"
description: "A compelling sentence from the article that captures the key value or insight"
slug: seo-optimized-slug

authors: [author_slug]

tags: [appropriate-tag]
hide_table_of_contents: false

date: YYYY-MM-DD
is_featured: true
---

Images

| Notion | Docusaurus |

|--------|------------|

| !alt | <Lightbox src="/img/blog/YYYY-MM-DD-slug/semantic-name.png" width="85%" alt="generated alt text" /> |

| Image with caption on next line | Merge caption into title attribute |

Content Cleanup

| Pattern | Action |

|---------|--------|

| H1 title | Remove (comes from frontmatter) |

| Status/Owner/Created time block | Remove |

| Trailing sections after conclusion | Remove (internal notes) |

| Code blocks with language markdown | Change to bash if shell commands |

| Notion callouts (> Note) | Convert to :::note admonitions |

| URL-encoded paths (%20) | Decode |

| asterisks for emphasis (*emphasised* content) | Replace with underscores (_emphasised_ content) |

| Internal Notion links (notion.so, notion.site) | Flag for review - replace with public resource links |

| Absolute docs site links (https://docs.getdbt.com/...) | Convert to relative paths (/docs/..., /reference/...) |

Truncate Marker

Insert <!-- truncate --> after the introduction (1-3 paragraphs, ~150-300 words) and before the first ## heading.

Quick Reference

Notion Export:
  my-post abc123.md
  my-post abc123/
    image.png
    image 1.png

Step 1 - Copy original + images, then commit:
  website/blog/YYYY-MM-DD-slug.md  (raw Notion content)
  website/static/img/blog/YYYY-MM-DD-slug/
    semantic-name.png
    another-semantic-name.png
  → git commit (baseline import)

Step 2 - Apply edits (diffable against baseline commit):
  website/blog/YYYY-MM-DD-slug.md  (transformed)

Other skills for the same job

different authors, same section of the catalogue
DOCX
by anthropics
vendor ×16

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

7k tokens
PDF
by anthropics
vendor ×16

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

13k tokens scripts
PPTX
by JayZeeDesign
×15

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

308k tokens scripts
Canvas Design
by anthropics
vendor ×13

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

1388k tokens
PDF
by anthropics
vendor ×10

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

15k tokens scripts
DOCX
by w95
×6

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

5k tokens
PPTX
by w95
×4

Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions \"deck,\" \"slides,\" \"presentation,\" or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.

2k tokens
Obsidian Markdown
by ZhanlinCui
×3

Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.

3k tokens

How to use it

Copy the folder

Take dbt-labs/converting-notion-to-docusaurus-blog from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.