agentleFS
Sign inStart free
reymerekar7reymerekar7/rm-skills/skills/linkedin-asset-analyzer/SKILL.md

linkedin-asset-analyzer

Skill37 starsChanged 4 months agoMITView on GitHub

Analyze LinkedIn carousels and infographics to understand why they performed. Focuses on visual design, format choices, and engagement mechanics — not copy. Use when a reference image or PDF is provided and you want to know what made it work. Supports image files (PNG, JPG, screenshots) and PDFs.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 1 is distinctive, and 2 are 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.

  • 2

    Very specific

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

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

    Images (PNG, JPG, screenshots): Use the Read tool directly on the file path.

    line 31
  2. Very specific:

    PDFs: Use the pdf skill to extract slides, then analyze.

    line 33
  3. Distinctive:

    Run every asset through these 4 lenses.

    line 39

≈ “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

LinkedIn Asset Analyzer

Overview

One job: look at a LinkedIn carousel or infographic and explain why it performed. Visual and structural analysis only — not copy critique.

When to Use

Trigger on:

  • "analyze this carousel / infographic"
  • "why did this perform"
  • "break down this image"
  • User drops an image or PDF of a LinkedIn asset without explanation

Input Formats

Images (PNG, JPG, screenshots): Use the Read tool directly on the file path. If multiple slides are separate images, read all in parallel.

PDFs: Use the pdf skill to extract slides, then analyze.

Analysis Framework

Run every asset through these 4 lenses.

1. FORMAT & LAYOUT

  • Asset type: Single infographic / Multi-slide carousel / Table / Grid
  • Slide count (carousel): Cover + body + CTA breakdown
  • Layout pattern: Single column / Two-column / Grid / Timeline / Comparison table
  • Information density: Dense / Balanced / Airy — how much per slide/section?
  • Scannability: Can someone get the value in 5 seconds without reading every word?

2. VISUAL DESIGN

  • Cover strength: What makes the cover slide stop-scroll? Bold text, color contrast, visual element, novelty?
  • Color palette: Background + accent + highlight. Consistent? High contrast?
  • Typography hierarchy: Is it immediately clear what to read first, second, third?
  • Icons / imagery: None / Emoji / Custom icons / Illustrations. Do they add meaning or just decoration?
  • Whitespace: Does the layout breathe or feel cluttered?
  • Brand consistency: Does it look like a system or a one-off?

3. ENGAGEMENT MECHANICS

  • Save trigger: Is there something worth bookmarking? Checklist / Cheat sheet / Reference table / Prompt list
  • Share trigger: Would someone tag a colleague or repost this to their feed?
  • Comment trigger: Does it invite a reaction, opinion, or follow-up question?
  • CTA placement: Where is the follow/repost ask? Does it feel earned or bolted on?
  • Algorithm fit: Carousel > infographic > single image. Does the format match the intent?

4. WHY IT WORKED

Synthesize the above into 3-5 bullet points explaining the performance. Be specific — not "good design" but what specifically about the design drove the result.

Format:

- [Specific element] → [Why it drove engagement/saves/shares]

Output Format

## LinkedIn Asset Analysis

**Asset:** [filename or description]
**Creator:** [if visible]
**Format:** [infographic / carousel / single image]

---

### Format & Layout
[findings]

### Visual Design
[findings]

### Engagement Mechanics
[findings]

### Why It Worked
- [element] → [reason]
- ...

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