New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Gen Art

by autonomous-ai in autonomous-ai/openharness

Create original vector artwork and complete visual asset sets from a person's brief, with custom drawing programs, user-editable controls and real SVG/PNG/source delivery.

MITAuto-check passed

Install Gen Art

skills CLI
$ npx skills add autonomous-ai/openharness --skill gen-art -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install autonomous-ai/openharness gen-art --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/autonomous-ai/openharness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/store/agents/generative-art/skills/gen-art .claude/skills/gen-art && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gen-art
GitHub stars
1.2k
Token cost
~1.1k tokens
SKILL.md length
519 words
Files
2 (incl. scripts)
Skills in repo
100
Repo updated
First seen
Licence
MIT

At a glance

Create original vector artwork and complete visual asset sets from a person's brief, with custom drawing programs, user-editable controls and real SVG/PNG/source delivery.

  • SKILL.md covers Renderer contract, Project controls and assets and Build, deliver, revise
  • Runs Shell scripts from its folder; calls node

What it does

Gen Art is an agent skill from autonomous-ai/openharness. Create original vector artwork and complete visual asset sets from a person's brief, with custom drawing programs, user-editable controls and real SVG/PNG/source delivery.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/seed-verdict.sh`).

The repository describes itself as: The ultimate harness for coding agents and beyond. All your agents. All your machines. One command center. Start with code, then follow your curiosity and build across… The licence is MIT.

Example prompts

  • “/gen-art”

Requirements

  • A Bash shell

What it can do on your machine

Read from SKILL.md and the folder at commit cc4983e. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gen Art loads about 1.1k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 519 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from autonomous-ai/openharness at commit cc4983e, republished under its MIT licence (© autonomous-ai). 519 words, ~1,065 tokens.

Download SKILL.mdSave it as .claude/skills/gen-art/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
gen-art
description
Create original vector artwork and complete visual asset sets from a person's brief, with custom drawing programs, user-editable controls and real SVG/PNG/source delivery.

Original work from a brief

The studio is infrastructure. The program is the art. Never restrict a new brief to the example's flowers, palette or layout. Build the new system in these files:

  • sketch/project.json: spec: "fieldwork/1", a stable lowercase id, title, brief, seed, named formats with width/height in pixels, controls, and optional image assets.
  • sketch/artwork.js: JavaScript function body returning SVG children as a string.
  • sketch/DESIGN.md: the brief, decisions, requested deliverables, revisions and evidence.
  • studio/: reusable UI and runtime. Change it only when the task needs a new authoring capability.

Renderer contract

The function receives width, height, seed, values, assets, rng and svg. rng('named-stream') returns a stable random-number function. Never use time or Math.random() for the geometry. values contains the current control values; assets.name is an embedded image URL or an empty string. svg.el(tag, attributes, children) and svg.text(text, attributes) escape attributes and text. The latter is essential for the person's real text (including & and <).

js
const r = rng('constellation');
const marks = Array.from({length: values.stars}, () => svg.el('circle', {
  cx: r() * width, cy: r() * height, r: 1 + r() * 4, fill: values.ink
}));
return svg.el('rect', {width, height, fill: values.paper}) + marks.join('');

That tiny example illustrates the contract, not an acceptable finished commission. Use original composition and domain-appropriate detail. The full SVG vocabulary is available, including paths, gradients, masks, clipping, patterns, groups, transforms, typography and embedded images. Rendering runs in a worker with a five-second limit; keep it responsive. A render error preserves what was visible and disables stale exports until the drawing works again.

Project controls and assets

A control has key, label, type, value. Types:

  • text, optionally multiline: true; can also hold user-pasted CSV/JSON interpreted by the program.
  • color: six-digit hex.
  • range: min, max, optional positive step.
  • select: string options.
  • toggle: boolean.

Use at most 40 meaningful controls, not a wall of arbitrary knobs. Formats are 64–8192 pixels per side. PNGs are bounded to 32 megapixels. Every control must visibly affect the intended part. An asset has key, label, optional file relative to sketch/. The builder embeds PNG/JPEG/WebP/SVG bytes; it refuses a path outside that folder. The user can replace images in the pane. All exports must stay portable: no external image/font URLs, script tags or active SVG content.

Show full SKILL.md (187 more words)Show less

Build, deliver, revise

sh
node tools/build.mjs
node tools/check.mjs
node tools/export.mjs --seeds 3 --scale 1

GENART_DSH_DIR points to the installed package. Setup installs pinned Playwright locally and uses an installed Chrome or downloads a local Chromium. Export tooling supports BROWSER_EXECUTABLE and PLAYWRIGHT_MODULE for testing. Nothing sends art or prompts to a paid service.

The browser exports individual SVG/PNG, an all-format ZIP, a seeded edition ZIP, an editable project and a portable studio. Inspect their actual bytes and reopen the project. For revisions from a user-saved project, run node tools/import-project.mjs FILE first; it preserves a backup. Do not overwrite a browser user's choices with old source defaults without acknowledging the conflict.

The exporter checks same-seed geometry and PNG dimensions, but leaves ready:false. Inspect all formats and their text, image placement, clipping, margins, color and scale. If randomness is promised, test distinct seeds as well as repeated seeds. If a print edition promises a bounded range, sample that range. Document font differences and any remaining production work.

Only mark ready after the user's deliverables exist and pass both technical and visual review. Never label a starter, a thumbnail, a screenshot of a tool, or a successful reload as the finished work.

© autonomous-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in store/agents/generative-art/skills/gen-art of autonomous-ai/openharness.

  • SKILL.md
  • scripts/seed-verdict.sh

Open the folder on GitHubat commit cc4983e

Compare with similar skills

Gen Art next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gen Art compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gen Art this skillautonomous-ai/openharness1.2k—~1.1kAutomated safety check: PassMIT
Algorithmic Art with p5.jsanthropics/skills180k38 repos~4.9kAutomated safety check: PassApache-2.0
Game Asset Generatorhtdt/godogen7.1k—~2.8kAutomated safety check: PassMIT
Algorithmic Artnexu-io/open-design100k—~351Automated safety check: PassApache-2.0
Vector Searchruvnet/ruflo74k—~1.5kAutomated safety check: NotesMIT
AssetsBuilderIO/agent-native7.1k—~1.2kAutomated safety check: PassNone

Similar skills

  • Algorithmic Art with p5.js

    anthropics/skills

    Official

    Creates original generative art in two steps: a written algorithmic philosophy, then a p5.js sketch with seeded randomness and an interactive viewer for exploring parameters.

    180k GitHub starsUsed in 38 repos~4.9k tokens
    Media & CreativeAuto-check passed

  • Game Asset Generator

    htdt/godogen

    Generates game art from text prompts: PNG images, GLB 3D models, rigged characters, animations and sprites, with background removal.

    7.1k GitHub stars~2.8k tokensUpdated 9 days ago
    Game DevelopmentAuto-check passed

  • Algorithmic Art

    nexu-io/open-design

    Create generative art using p5.js with seeded randomness so every render is reproducible.

    100k GitHub stars~351 tokensUpdated today
    Media & CreativeAuto-check passed

  • Vector Search

    ruvnet/ruflo

    Vector search via embeddings (large-scale HNSW) and ruvllmhnsw (WASM router for ≤11 hot patterns), with RaBitQ 1-bit quantization for 32× memory reduction

    74k GitHub stars~1.5k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes

  • Assets

    BuilderIO/agent-native

    Use Agent-Native Assets for image and video generation requests, brand-safe asset search/export, and human-in-the-loop asset selection through the hosted Assets MCP app.

    7.1k GitHub stars~1.2k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Hunt RAG Vector

    sickn33/agentic-awesome-skills

    Hunt vector-store / embedding-layer weaknesses in RAG pipelines (OWASP LLM08 Vector and Embedding Weaknesses)

    47k GitHub starsUsed in 1 repo~3k tokens
    AI & LLM EngineeringAuto-check passed

More from autonomous-ai/openharness

All 100 skills in this repo

  • G-code Slicer Tool

    autonomous-ai/openharness

    Slices 3D mesh files into printer-profiled plain G-code through real slicer CLIs, with backend discovery, input inspection, dry runs and static validation.

    1.2k GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Home Assistant Automation Builder

    autonomous-ai/openharness

    Turns a home-automation request into standard, testable automations.yaml, run against Home Assistant Core's real triggers and verified with its own trace tool.

    1.2k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Score Music Composer

    autonomous-ai/openharness

    Turns a musical brief into LilyPond concert-pitch music, checked parts for each instrument and a playable practice pack.

    1.2k GitHub stars~1.1k tokensUpdated today
    Auto-check passed

  • OrcaSlicer 3MF and G-code Workflow

    autonomous-ai/openharness

    Turns an STL and explicit printer and material requirements into compared OrcaSlicer plans, an editable 3MF project, checked G-code and a portable handoff.

    1.2k GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Sheets and Docs Report Builder

    autonomous-ai/openharness

    Builds an editable DOCX report, a formula-driven XLSX workbook and a fresh LibreOffice PDF preview from one structured source file, then checks them together.

    1.2k GitHub stars~708 tokensUpdated today
    Auto-check passed

  • Bambu Labs

    autonomous-ai/openharness

    Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain .gcode, using Bambu LAN FTPS/MQTT handoffs.

    1.2k GitHub starsUsed in 1 repo~2.1k tokens
    Auto-check: warnings

Questions about Gen Art

What does Gen Art do?

Create original vector artwork and complete visual asset sets from a person's brief, with custom drawing programs, user-editable controls and real SVG/PNG/source delivery. Gen Art is an agent skill from autonomous-ai/openharness. Create original vector artwork and complete visual asset sets from a person's brief, with custom drawing programs, user-editable controls and real SVG/PNG/source delivery.

How do I install Gen Art in Claude Code?

Run `npx skills add autonomous-ai/openharness --skill gen-art -a claude-code`. Or copy the skill folder (store/agents/generative-art/skills/gen-art in autonomous-ai/openharness) into .claude/skills/gen-art in your project. Claude Code loads it when a task matches its description.

How do I install Gen Art in Codex?

Run `npx skills add autonomous-ai/openharness --skill gen-art -a codex`. Or copy the skill folder (store/agents/generative-art/skills/gen-art in autonomous-ai/openharness) into .agents/skills/gen-art in your project. Codex loads it when a task matches its description.

Can I use Gen Art in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add autonomous-ai/openharness --skill gen-art -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gen-art, .gemini/skills/gen-art, .github/skills/gen-art and .opencode/skills/gen-art in your project.

What does Gen Art need to run?

Going by SKILL.md and its folder, Gen Art needs a shell for the scripts in its folder and the command-line tools its instructions call (node). Our summary lists: A Bash shell.

Does Gen Art access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Gen Art safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Gen Art use?

Gen Art is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gen Art use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gen Art?

Skills that share tags, products or a category with Gen Art: Algorithmic Art with p5.js (anthropics/skills, 180k stars), Game Asset Generator (htdt/godogen, 7.1k stars), Algorithmic Art (nexu-io/open-design, 100k stars) and Vector Search (ruvnet/ruflo, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gen Art?

autonomous-ai (a GitHub organization) maintains it in autonomous-ai/openharness, which has 1,210 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 10, 2026.

Source: autonomous-ai/openharness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.