CommunityImagemgithub.com

linkedin-post-image

Designs and exports LinkedIn post images (single-image posts, quote cards, stat cards, and multi-slide carousels) as 1080x1350 or 1080x1080 PNGs, plus an optional PDF for document-style carousels. Use when the user asks for a LinkedIn post image, carousel, quote card, cheat sheet, or any visual to attach to a LinkedIn post.

O que é linkedin-post-image?

linkedin-post-image is a Claude Code agent skill that designs and exports LinkedIn post images (single-image posts, quote cards, stat cards, and multi-slide carousels) as 1080x1350 or 1080x1080 PNGs, plus an optional PDF for document-style carousels. Use when the user asks for a LinkedIn post image, carousel, quote card, cheat sheet, or any visual to attach to a LinkedIn post.

Funciona com✓Claude Code~Codex CLI~Cursor✓Antigravity
npx skills add https://github.com/kanchan-nath/claude-code-skills/tree/HEAD/skills/linkedin-post-image

Installed? Explore more Imagem skills: steipete/songsee, affaan-m/frontend-design, mattpocock/improve-codebase-architecture · View all 6 →

Perguntar na sua IA favorita

Abre um novo chat com esta habilidade de agente já pré-carregada.

Documentação

LinkedIn Post Image

Builds LinkedIn visuals as HTML/CSS slides, then screenshots them to PNG with Playwright. Adapted from the popular create-html-carousel skill (gooseworks-ai/goose-skills), rewritten for Google Antigravity: no Claude-specific question widgets, plain chat questions, and workspace-relative paths.

Use this skill when

  • The user wants an image, carousel, quote card, stat card, or cheat sheet for a LinkedIn post.
  • The user shares reference designs and wants something in that style.

Do not use this skill when

  • The user only wants post copy (no visual).
  • The user wants video, GIF, or a full slide presentation.

Specs (LinkedIn)

  • Default canvas: 1080x1350 (4:5 portrait, takes the most feed space on mobile). Alternative: 1080x1080 (1:1).
  • PNG, under 10 MB each. Max 20 images for a multi-image post; 5-8 slides performs best.
  • For a swipeable "document" carousel, also export one PDF (every page 1080x1350).
  • Keep all text inside a 80px safe margin. Minimum body text 28px, headline 64px+.

Instructions

1. Gather inputs (ask in one short message, skip anything already given)

  1. Topic or the exact text for the image(s).
  2. Format: single image or carousel (slide count).
  3. Style: pick from references/style-presets.md (or "match my reference images").
  4. Brand handle / name to show in the footer (optional).
  5. Photo or logo files to use (optional). If none are supplied, use CSS shapes, gradients or icons. Never download or embed photos of real people from the web.

If the user pasted content, do not rewrite it. Only trim to fit density rules.

2. Plan

  • One idea per slide. Slide 1 = hook, last slide = CTA (follow / repost / comment).
  • Density limits: headline max 2-3 lines, body max 3 lines, max 4 list items per slide. Must be readable in 2-3 seconds on a phone.
  • If the image contains a quote with a person's name, only use quotes the user supplied and tell the user to verify the attribution before posting.

3. Build HTML

  • Create output/<post-name>/slides/slide-01.html, slide-02.html, ... Start from assets/template.html.
  • Copy the chosen preset's CSS variables, fonts and layout rules from references/style-presets.md.
  • Each file is a fixed-size page (html, body { width:1080px; height:1350px; overflow:hidden }). No scrolling, no responsive units, no animations.
  • Load fonts from Google Fonts with <link>; always add a fallback stack.
  • Use inline SVG or CSS for icons, shapes and charts. Use local files from the user for images, referenced by relative path.

4. Render

From the skill folder (first time only: cd scripts && npm install && npx playwright install chromium):

node scripts/render.js output/<post-name>            # PNGs at 1080x1350, 2x sharpness
node scripts/render.js output/<post-name> --size 1080x1080
node scripts/render.js output/<post-name> --pdf      # also builds carousel.pdf

PNGs are written to output/<post-name>/exports/.

5. Verify (required)

Open 2-3 of the exported PNGs (use the browser or image viewer tool) and check: no clipped or overflowing text, contrast is high, fonts loaded (not default serif), footer and slide counter are inside the margin. Fix the HTML and re-render until clean. Retry at most 3 times.

6. Deliver

Report the folder path, file list, and the upload order. Do not add extra suggestions.

Rules

  • Do not invent statistics, quotes or testimonials. Use only what the user provided.
  • Do not use logos, photos or names of real people or brands unless the user supplied them.
  • One accent color per design. Max two typefaces.
  • Keep the same layout, margins and footer position on every slide of a carousel.

Troubleshooting

  • Default fonts in PNG: increase --wait (--wait 1500) or switch to a web-safe fallback.
  • Blurry text: render.js already uses deviceScaleFactor 2; pass --scale 1 only if file size exceeds 10 MB.
  • Overflow: shorten copy or split the slide; never shrink body text below 28px.

Individual skills in this repo

This repo contains 3 individual skills — each has its own dedicated page.

cold-email

Build a visually styled HTML cold-outreach email (feedback requests, intros, investor/recruiter outreach) with a small vector logo mark, an accent color, light icon use, and a clickable CTA button — not a plain-text paragraph email. Use this whenever the user asks to draft, write, or style a "cold email," "outreach email," "feedback request email," or asks to make an email "more visual," with "icons," "vector images," or "look nicer," especially for StudeQ outreach to founders/investors/recruiters. Produces both an HTML version (for Gmail draft creation) and a plain-text fallback.

hashnode

Write long form technical blog posts for Hashnode that rank on Google and actually get read start to finish. Use this whenever the user asks for a blog post, technical article, Hashnode post, or says things like "write a blog on X", "turn this code into a blog", "make a technical article about Y", "/hashnode", or shares a topic, a code file, or a markdown draft and expects a publish ready blog post back. Also trigger when the user pastes raw code or a README and asks to explain it as a post, or asks to improve/SEO audit an existing Hashnode draft. Input can be a topic alone, a code snippet, or a full markdown file. Output is always a complete markdown blog post, ready to paste into Hashnode.

motion-prompt-director

Turns any product, idea or brief into a complete, production-ready prompt pack for AI video and motion-graphics generators (Google Flow / Veo, Runway, Kling, Luma, Sora, Pika), plus key-frame image prompts, a music prompt and edit notes, using the Cinetic cinematic motion-design method (one product-specific idea, a story device, a reusable Style Bible, beat-timed shots, copy discipline, hard bans on generic AI looks). Use this whenever the user wants a prompt, shot list, storyboard, script or treatment for a launch video, product demo, feature animation or loop, logo sting or reveal, kinetic typography, teaser, trailer, intro or promo clip, or says things like "make a video about X", "write a Flow prompt", "animate this feature", "I need a launch clip", "storyboard this", "make this look premium, not AI", or pastes a video prompt to critique or rewrite. Also use it for 9:16 / 1:1 social versions, looping hero animations, and for turning a code-based motion brief into prompts for a...

Habilidades Relacionadas