by haorantang97
A Codex marketplace of original visual and artistic creation skills.
# Add to your Claude Code skills
git clone https://github.com/haorantang97/TArtLast scanned: 8/23/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-08-23T04:35:18.089Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}TArt is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by haorantang97. A Codex marketplace of original visual and artistic creation skills. It has 270 GitHub stars.
Yes. TArt passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/haorantang97/TArt" and add it to your Claude Code skills directory (see the Installation section above).
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh TArt against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Antibes Holiday is a portable visual-creation skill for original relaxed black-pen illustrations, narrative scenes, expressive marks, and early logo exploration.
It focuses on physical stroke behavior, shorthand recognition, confident incompletion, causal story staging, active blank space, and non-equilibrium proportion. It is a general visual grammar, not an identity-bound imitation package.
These original outputs show the range of the system. They are release examples, not runtime style references.
plugins/antibes-holiday/.codex-plugin/plugin.json: Codex plugin metadata.plugins/antibes-holiday/skills/antibes-holiday/SKILL.md: execution workflow.references/style-system.md: detailed drawing and composition system.references/prompt-recipes.md: renderer-neutral prompt scaffolds.assets/stroke-calibration.png: original non-semantic stroke calibration asset.plugins/antibes-holiday/assets/examples/: seven selected original public outputs.Third-party screenshots, source identities, copied compositions, and private local paths are not included.
With GitHub CLI 2.90 or newer:
gh skill install haorantang97/antibes-holiday antibes-holiday
With the open skills installer:
npx skills add haorantang97/antibes-holiday --skill antibes-holiday
Add this repository as a marketplace, then install the plugin:
codex plugin marketplace add haorantang97/antibes-holiday
codex plugin add antibes-holiday@antibes-holiday
Start a new Codex task after installation so the new skill is loaded.
For a local checkout:
codex plugin marketplace add /absolute/path/to/antibes-holiday
codex plugin add antibes-holiday@antibes-holiday
| Environment | Behavior |
|---|---|
| Codex with built-in image generation | Full generation and editing workflow |
| Another agent with a raster image tool | Uses that platform's native renderer |
| Agent without local-image attachment support | Uses the textual stroke specification |
| Agent without image generation | Produces a renderer-ready prompt and validation checklist |
references/*.md files are supporting instructions, not standalone skills. The
main SKILL.md links to them explicitly so a compatible skill loader can read
them when required. Preserve the complete directory structure.
agents/openai.yaml supplies Codex UI metadata. Other agents may safely ignore it.
Claude Desktop does not automatically discover Codex plugins from disk and needs
its own project, connector, or instruction-loading setup.
The plugin does not bundle or install an image model. In Codex it prefers the system image-generation workflow. On other platforms it selects an available native renderer. Without a renderer it degrades honestly to prompts and review criteria instead of claiming an image was created.
Do not market outputs as the work or official style of a third party. Do not trace source images, reuse signature characters, or preserve source compositions. References are evidence for general line and composition mechanisms only.
The plugin instructions and bundled original calibration asset are distributed
under the PolyForm Noncommercial License 1.0.0. See LICENSE.
The release is checked with the Codex Skill and Plugin validators, a clean archive
extraction test, a real local Marketplace installation, and reference-free forward
tests. See docs/VALIDATION.md.