graphic-designer
- Repo stars 1,355
- Author updated Live
- Author repo social-media-skills
- Domain
- Design
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @charlie947 · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools,默认拥有全部工具权限。
---
name: graphic-designer
description: > When this skill triggers, go straight to Step 1. Do not summarise. Do not explain options. Sta…
category: design
runtime: no special runtime
---
# graphic-designer output preview
## PART A: Task fit
- Use case: > When this skill triggers, go straight to Step 1. Do not summarise. Do not explain options. Start immediately. Check the project for the most recent post file. If found, read it. If not, say: runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “CRITICAL: Auto-start on load / Step 1. Read the post / Path A: HTML/CSS structured graphic” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “> When this skill triggers, go straight to Step 1. Do not summarise. Do not explain options. Start immediately. Check the project for the most recent post file. If found, read it. If not, say: runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “CRITICAL: Auto-start on load / Step 1. Read the post / Path A: HTML/CSS structured graphic” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Start with a small task and check whether the result follows “CRITICAL: Auto-start on load / Step 1. Read the post / Path A: HTML/CSS structured graphic”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: graphic-designer
description: > When this skill triggers, go straight to Step 1. Do not summarise. Do not explain options. Sta…
category: design
source: charlie947/social-media-skills
---
# graphic-designer
## When to use
- > When this skill triggers, go straight to Step 1. Do not summarise. Do not explain options. Start immediately. Check…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “CRITICAL: Auto-start on load / Step 1. Read the post / Path A: HTML/CSS structured graphic” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "graphic-designer" {
input -> user goal + target files + boundaries + acceptance criteria
context -> CRITICAL: Auto-start on load / Step 1. Read the post / Path A: HTML/CSS structured graphic
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
} Graphic Designer
CRITICAL: Auto-start on load
When this skill triggers, go straight to Step 1. Do not summarise. Do not explain options. Start immediately.
Step 1. Read the post
Check the project for the most recent post file. If found, read it. If not, say:
Paste the post you want a graphic for.
Wait for the post, then call AskUserQuestion:
[
{
"question": "What type of graphic fits this post best?",
"header": "Style",
"multiSelect": false,
"options": [
{"label": "HTML/CSS graphic", "description": "Clean structured layout. Framework, comparison, steps, data. Fully editable, screenshot to export."},
{"label": "Whiteboard infographic", "description": "Hand-drawn marker style on a whiteboard or notebook page. Recaps the post visually. Generated in Gemini."},
{"label": "Branded infographic", "description": "Professional infographic using your brand colours. Recaps the post visually. Generated in Gemini."},
{"label": "You decide", "description": "Analyse the post and pick the best format automatically"}
]
}
]
If "You decide": analyse the post. If it contains numbered steps, frameworks, comparisons, or data tables, go Path A (HTML/CSS). If it recaps a workflow, shares tips, teaches a concept, or tells a story, go Path B (image prompt) and pick whichever style fits better.
Path A: HTML/CSS structured graphic
Design constraints:
- 1200 x 1400 pixels (LinkedIn optimal)
- Dark background (#1a1a2e or user's brand colour) with high contrast text
- Clean sans-serif font (Inter, system-ui)
- White or light text on dark background
- One accent colour for highlights and dividers
- 40px minimum padding on all sides
- No stock photo backgrounds
- Let the post content dictate how many sections the graphic has. 3 steps = 3 blocks. 10 tips = 10 blocks. The constraint is legibility, not a fixed number. Every element must be large enough to read on a mobile screen.
Single self-contained HTML file with inline CSS. Include viewport meta tag.
Extract the core framework or steps from the post. Do not copy the full post. Distil into:
- A short headline (5 to 8 words)
- Key points as visual blocks (Unicode icons fine)
- Footer with author name from about-me.md if available
Save the HTML file. Tell the user:
Open the HTML in your browser and screenshot it.
Path B: Image generation prompt
The graphic must recap the post content visually. It is not an abstract illustration or stock photo. It summarises the key information from the post in a visual format the reader can scan.
First, extract the content for the infographic from the post:
- The main headline or hook (shortened to 5 to 10 words)
- 3 to 6 key points, steps, or takeaways (one short line each)
- Any numbers, stats, or data worth highlighting
- A footer line (author name and CTA if appropriate)
Then build the prompt based on the chosen style.
Style 1: Whiteboard infographic
Use this prompt template. Fill in the content sections from the post.
Generate a single image of a physical, hand-drawn infographic on a large whiteboard or notebook page.
Crucial Style Instructions (Read First):
Medium: The image must look like a photograph of a real whiteboard or large paper notepad.
Texture: All elements must look created by hand using colored marker pens (black, blue, red, green) and highlighters (yellow/orange). Lines should be slightly imperfect, wobbly, and have the texture of ink on a surface.
No Digital Fonts: All text, headings, and bullet points must appear handwritten or hand-printed in marker pen.
Layout: Structure the 1080x1350 image as follows:
TITLE (large, bold marker, top of page):
[Insert headline from the post]
CONTENT (hand-drawn sections with marker pen):
[Insert 3 to 6 key points, each as a short hand-written line with a bullet, number, or small icon drawn next to it]
[If there are stats or numbers, draw them large with a circle or box around them]
Use multi-colored markers for emphasis. Keep text large and legible. Make everything look hand-drawn with slight imperfections. Make it look like a photograph of an actual notebook page.
Always include the handwritten text "[Author name from about-me.md] | Repost" at the bottom of the image, in the same hand-drawn marker style.
Style 2: Branded infographic
Ask the user for brand colours if not already known. If about-me.md exists, check there first.
Generate a professional infographic image at 1080x1350 pixels.
Style: Clean, modern, editorial. Flat design with sharp edges and strong typography. No 3D effects, no gradients, no stock photos.
Colour palette:
- Background: [primary brand colour or dark neutral]
- Text: [white or high-contrast colour]
- Accent: [secondary brand colour]
Layout:
HEADLINE (top, large bold text):
[Insert headline from the post]
BODY (structured sections, each with an icon or number):
[Insert 3 to 6 key points as short lines, each with a visual marker: numbered circle, checkmark, or simple icon]
[If there are stats, display them as large feature numbers with a label underneath]
FOOTER:
[Author name from about-me.md] | [CTA or tagline if appropriate]
Keep text large and scannable. Maximum 40 words on the entire image. No decorative borders. No watermarks. No logos unless the user provides one.
Output the complete prompt in a code block. Tell the user:
Paste this into Gemini or your image generator. The prompt is ready to go.
After either path
Say:
Graphic ready. Say "score my post" when you want feedback before publishing.
Rules
- Always read the post before designing. The graphic must recap the post content, not illustrate an abstract concept.
- Structured graphics (Path A) must be a single HTML file with inline CSS.
- Image prompts (Path B) must be fully self-contained. The user pastes it cold into Gemini and gets the graphic.
- Extract and distil the post content into the graphic. No copying the full post text.
- Whiteboard style: always hand-drawn marker look, imperfect lines, coloured pens, notebook/whiteboard texture.
- Branded style: always clean, flat, modern, using the user's brand colours.
- Never use em dashes in any output.
- British English throughout.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review