Agent skill · Design & Presentation

antibes-holiday

Create original relaxed black-pen graphics from concepts or visual references, including sparse illustrations, narrative scenes, animals, objects, abstract relationships, icons, and logo marks. Use when the user wants quick hand-drawn line energy, causal story staging, non-equilibrium proportion, shorthand forms, open contours, structural line drift, misregistered junctions, selective retracing, physical pen texture, or a transferable illustration system that must not collapse into clean vector minimalism or polished period-sketch drawing.

haorantang97github.com/haorantang97GitHub ↗
claude-codeMIT
Install
npx skills add haorantang97/antibes-holiday --skill antibes-holiday --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 5
SKILL.md size: 12 KB
Bundled scripts: none
Path: plugins/antibes-holiday/skills/antibes-holiday/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 62

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Antibes Holiday Create original graphics that feel drawn in one alert but lightly unsteady sitting with a real black pen. Prioritize stroke life, tempo, shorthand, structural instability, and the courage to stop. Semantic compression remains useful, but a clean concept never compensates for lines that look professionally controlled. ## Start With Evidence When references are supplied: 1. Define the target style cluster from stroke material, tempo, omission, density, and composition. 2. Exclude unrelated style clusters from the same reference body. 3. Record dates inside the cluster and weight recent mature work most heavily. 4. Inspect at least three high-weight images at actual size. 5. Separate stroke behavior from recurring subjects and accessories. 6. Use references for line material and gesture only. Never reuse their subject, pose, composition, or signature motif. Default evidence weighting: - newest mature same-cluster works: `60%`; - recent supporting same-cluster works: `30%`; - early same-cluster works: `10%`; - different styles or experiments: `0%`. Read [style-system.md](references/style-system.md) before drawing. Read [prompt-recipes.md](references/prompt-recipes.md)

What's inside
Steps it walks through
  1. Start With Evidence
  2. Define The Drawing
  3. Draw In Three Passes
  4. Pass 1: Gesture
  5. Pass 2: Recognition
  6. Pass 3: Pen Life
  7. Adapt Without Humanizing
  8. Compose Story Scenes
  9. Select Rendering Capability
  10. Use Image Generation
  11. Build Logos
  12. Comparative Validation
  13. Deliver
Ships with 4 files
  • agents/openai.yaml
  • assets/stroke-calibration.png
  • references/prompt-recipes.md
  • references/style-system.md
About this skill
What does the antibes-holiday skill do?

Create original relaxed black-pen graphics from concepts or visual references, including sparse illustrations, narrative scenes, animals, objects, abstract relationships, icons, and logo marks. Use when the user wants quick hand-drawn line energy, causal story staging, non-equilibrium proportion, shorthand forms, open contours, structural line drift, misregistered junctions, selective retracing, physical pen texture, or a transferable illustration system that must not collapse into clean vector minimalism or polished period-sketch drawing.

How do I install it?

Run `npx skills add haorantang97/antibes-holiday --skill antibes-holiday --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From haorantang97/antibes-holiday, a repository with 62 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going