agentleFS
anoochitanoochit/skills/create-blog-post/SKILL.md

create-blog-post

Skill1 starsChanged 5 days agoMITView on GitHub

Creates an Astro blog post from a given topic or reference, generates content, fetches a cover image from a free stock source like Picsum, and sets up frontmatter.

5 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

9 rules. 0 are common, 4 are distinctive, and 5 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Understand Topic & Generate Content: Write a comprehensive, well-structured blog post in Markdown format based on the user's topic or …

    line 12
  2. Very specific:

    Create a filename for the image based on the post title (e.g., my_post_title.jpg).

    line 15
  3. Very specific:

    Create a new Markdown file at src/content/posts/<filename>.md (use the same filename prefix as the image).

    line 19
  4. Distinctive:

    Ensure the frontmatter exactly matches the required format.

    line 20
  5. Very specific:

    Image URL: Must exactly follow the format https://blog.redlinesoft.net/images/post/<filename>.jpg to match the downloaded image.

    line 39
  6. Very specific:

    Date: Must be an ISO 8601 datetime in the Asia/Bangkok timezone (+07:00), e.g.

    line 40
  7. Very specific:

    Author: Must be 'AI Assistant'.

    line 41
  8. Distinctive:

    Tags: Use lower-case, hyphen-separated words.

    line 42
  9. Distinctive:

    After writing the file, notify the user that the blog post and cover image have been created successfully.

    line 46

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “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

Create Blog Post Skill

This skill automates the creation of a new Astro blog post in the workspace.

Workflow

  1. Understand Topic & Generate Content: Write a comprehensive, well-structured blog post in Markdown format based on the user's topic or reference.
  2. Download Image:
    • Fetch a random or relevant image from a free source like Picsum (e.g., https://picsum.photos/1200/630).
    • Create a filename for the image based on the post title (e.g., my_post_title.jpg).
    • Download the image and save it to public/images/post/<filename>.jpg.
      • Command Example: curl -L "https://picsum.photos/1200/630" -o public/images/post/<filename>.jpg
  3. Write Post Content:
    • Create a new Markdown file at src/content/posts/<filename>.md (use the same filename prefix as the image).
    • Ensure the frontmatter exactly matches the required format.

Frontmatter Format

The generated Markdown file must use the following frontmatter header exactly:

---
title: "<The Title of the Post>"
date: "<YYYY-MM-DDTHH:mm:ss+07:00>"
description: "<A concise summary of the post>"
author: "AI Assistant"
image: "https://blog.redlinesoft.net/images/post/<filename>.jpg"
alt: "<A descriptive alt text for the image>"
tags: ['tag1', 'tag2', 'tag3']
---

Important Details

  • Image URL: Must exactly follow the format https://blog.redlinesoft.net/images/post/<filename>.jpg to match the downloaded image.
  • Date: Must be an ISO 8601 datetime in the Asia/Bangkok timezone (+07:00), e.g. 2026-03-03T08:17:17+07:00. Use the current system datetime.
  • Author: Must be 'AI Assistant'.
  • Tags: Use lower-case, hyphen-separated words.

After writing the file, notify the user that the blog post and cover image have been created successfully.

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.