agentleFS
iusztinpauliusztinpaul/designing-real-world-ai-agents-workshop/.agents/skills/write-post/SKILL.md

write-post

Skill512 starsChanged 7 months agoMITView on GitHub

Generate a LinkedIn post using the LinkedIn Writer MCP server. Use this skill whenever the user wants to write a LinkedIn post, create social media content, draft a post from research, or generate a post with an image. Triggers on: 'write a post', 'create a LinkedIn post', 'draft a post about', 'turn this into a post', 'generate a post', or any request involving LinkedIn content creation. Also use when the user has a guideline.md and research.md ready.

3 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

5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    All output goes into outputs/{slug}/ relative to the project root.

    line 12
  2. Distinctive:

    Create the directory if it doesn't exist.

    line 16
  3. Very specific:

    If the user provides raw text for the guideline, create guideline.md in the working directory:

    line 22
  4. Very specific:

    If research.md is in a different location, copy it into the working directory.

    line 43
  5. Very specific:

    Read the WORKFLOW_INSTRUCTIONS from src/writing/routers/prompts.py and follow those steps exactly, using the linkedin-writer MCP tools.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 3 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

Write LinkedIn Post

Generate a LinkedIn post using the linkedin-writer MCP server.

Working Directory

All output goes into outputs/{slug}/ relative to the project root. Derive the slug from:

  • The dataset seed/guideline filename if the user references one (e.g., my-topic_seed.md → my-topic)
  • Otherwise, slugify the topic (lowercase, hyphens, no special chars, max 60 chars)

Create the directory if it doesn't exist.

Input Preparation

The working directory needs guideline.md and research.md.

If the user provides raw text for the guideline, create guideline.md in the working directory:

# LinkedIn Post Guideline

## Topic
[What the post is about]

## Angle
[What perspective or approach to take]

## Target Audience
[Who this post is for]

## Key Points to Cover
[3-5 bullet points]

## Tone
[How it should sound]

If research.md is in a different location, copy it into the working directory.

Execution

Read the WORKFLOW_INSTRUCTIONS from src/writing/routers/prompts.py and follow those steps exactly, using the linkedin-writer MCP tools. Pass outputs/{slug}/ as the working directory path to each tool.

After Completion

Present the final outputs/{slug}/post.md content to the user. If an image was generated, mention outputs/{slug}/post_image.png.

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.