AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Visual Plan

skill-gokulb20-crewm8-social-media-manager-skill-graph-visual-plan · by gokulb20

Plan visual assets for social content — carousel slide-by-slide copy, banners, quote cards, and mock demos — including layout specs, color/font guidance, and AI image prompt generation.

No reviews yet
0 installs
24 views
0.0% view→install

Install

$ agentstack add skill-gokulb20-crewm8-social-media-manager-skill-graph-visual-plan

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-gokulb20-crewm8-social-media-manager-skill-graph-visual-plan)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
4mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Visual Plan? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Visual Plan

Produce detailed visual asset specifications that a designer or AI image generator can execute. Every post that needs a visual gets a clear brief — slide-by-slide copy for carousels, layout descriptions, dimension specs, and color/font guidance.

Purpose

Most social visuals fail because nobody planned them. The text doesn't fit, the layout doesn't work for the platform, or the visual doesn't support the message. This skill produces a plan that removes all ambiguity before a single pixel is created.

When to Use

  • Content calendar calls for carousels, banners, quote cards, or graphics
  • Repurposing blog content into LinkedIn/IG carousels
  • Campaign requires consistent visual branding
  • Founder says "can you mock up what this would look like?"

Inputs Required

  • Key message (one sentence)
  • Tone (serious, playful, urgent, calm, inspiring)
  • Brand visual guidelines (colors, fonts, logo)
  • Target platform
  • Content format (carousel, single image, banner, video thumbnail)

Quick Reference

| Asset Type | Typical Slides | Best Platforms | Dimension Target | |-----------|---------------|--------------|-----------------| | Carousel | 5-10 slides | LinkedIn, IG | 4:5 (1080x1350) | | Quote card | 1 image | X, LinkedIn, IG | 16:9 for X, 4:5 for IG/LinkedIn | | Banner/Header | 1 image | LinkedIn, X | 1500x500 (LinkedIn), 1500x500 (X) | | Infographic | 1 long image or 3-5 slides | LinkedIn, IG | 4:5 | | Data/chart card | 1 image | X, LinkedIn | 16:9 or 1:1 |

Procedure

  1. Define the content context:
  • Key message (one sentence)
  • Emotional tone
  • Action the visual should drive (stop scroll, save, share, click)
  1. Choose the format:
  • Carousel: when content is sequential (step-by-step, list of insights, framework)
  • Single image: one powerful statement/quote/stat
  • Banner: profile or event-related visual
  1. For carousels, draft slide-by-slide:
  • Slide 1 (cover): Hook + visual that stops scroll. Max 10 words.
  • Slides 2-N-1: One idea per slide. Mix text and supporting visual.
  • Final slide: Summary + CTA + brand logo/handle.
  • Each slide: 15-25 words max
  1. For each slide, specify:
  • Exact copy
  • Visual direction (image, icon, or graphic)
  • Layout (text-heavy, image-heavy, split screen, centered)
  1. Apply brand guidelines:
  • Color palette (background, text, accent)
  • Typography (headline font, body font)
  • Logo placement (consistent)
  1. Generate AI image prompts for any AI-generated visuals (delegate to image-prompt).
  1. Specify exact dimensions using asset-format rules.

Output Format

# Visual Plan: [Asset Name]

## Content Context
**Key message:** [One sentence]
**Tone:** [Emotional register]
**Goal:** [Stop scroll / Save / Share / Click]

## Format: [Carousel / Single image / Banner / Thumbnail]

### Slide-by-Slide (for carousels)

#### Slide 1 (Cover)
**Copy:** [Exact text — max 10 words]
**Visual:** [Image/graphic description]
**Layout:** [Text-heavy / Split / Centered]
**Colors:** [Background + text + accent]

#### Slide 2...
...

### Specifications
- **Dimensions:** [Exact pixel dimensions]
- **Safe zones:** [Margins — avoid platform UI]
- **Font:** [Headline + body]
- **Color palette:** [Hex codes]

Done Criteria

The skill is complete when:

  1. All slides have exact copy, visual direction, and layout
  2. Dimensions match the target platform specification
  3. Brand colors and fonts are specified
  4. AI image prompts are provided (if AI generation is involved)
  5. The visual brief is detailed enough for a designer or AI to execute without clarification

Pitfalls

  • Carousel slides with too much text (20+ words per slide — nobody reads them)
  • Slide 1 that doesn't hook standalone (people see it in feed before they swipe)
  • Inconsistent visual branding across slides
  • Forgetting CTA on the final slide
  • Specifying wrong dimensions per platform (see asset-format)

Verification

Look at slide 1 in isolation — does it make you want to swipe? Does the sequence flow logically? Is the final slide satisfying? Can you picture exactly what each slide looks like from the description?

Example

Input: Topic = "3 signs your pricing is wrong." Tone = confident, slightly provocative. Platform = LinkedIn carousel. Brand = dark background (gray/black), white text, orange accent.

Output: 6-slide carousel.

  • Slide 1: "3 signs your pricing is wrong" (large text, centered, orange accent underline). Visual: subtle question mark icon.
  • Slide 2: "Sign 1: You've never raised prices" — copy: "If your prices are the same as 2 years ago, you're leaving money on the table." Visual: declining graph.
  • Slide 3-5: Same structure for remaining signs.
  • Slide 6: "Which sign hit closest? Drop it in the comments. → Follow for more pricing breakdowns." Visual: brand mark, orange accent.
  • Dimensions: 1080x1350 (4:5, LinkedIn). Font: Inter Bold for headers, Inter Regular for body. Colors: background #1a1a1a, text #ffffff, accent #ff6b35.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.