Agent skill

Generative UI Minis

by OpenMinis in OpenMinis/MinisSkills

In the current Minis environment, automatically convert text descriptions into a single-file HTML generator similar to Claude Artifact, with unified support for outputs such as cards, tables…

MITAuto-check passedFrontend & Design

Install Generative UI Minis

skills CLI
$ npx skills add OpenMinis/MinisSkills --skill generative-ui-minis -a claude-code

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

GitHub CLI
$ gh skill install OpenMinis/MinisSkills generative-ui-minis --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/OpenMinis/MinisSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/generative-ui-minis .claude/skills/generative-ui-minis && 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
generative-ui-minis
GitHub stars
446
Token cost
~1.1k tokens
SKILL.md length
358 words
Files
3 (incl. scripts)
Skills in repo
49
Repo updated
First seen
Licence
MIT

At a glance

In the current Minis environment, automatically convert text descriptions into a single-file HTML generator similar to Claude Artifact, with unified support for outputs such as cards, tables…

  • Works in 2 steps: Complete Artifact Generator → Render from a JSON spec
  • S mention these components
  • SKILL.md covers Automatic Trigger Scenarios, Currently Supported Unified…, Main Scripts and spec Format, plus 3 more sections
  • Runs Python scripts from its folder; calls python3

What it does

Generative UI Minis is an agent skill from OpenMinis/MinisSkills. In the current Minis environment, automatically convert text descriptions into a single-file HTML generator similar to Claude Artifact, with unified support for outputs such as cards, tables, records, timelines, code blocks, and charts. Use this skill first when users mention these components or visualization pages.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `scripts/generative_ui_artifact.py` and `scripts/generative_ui_demo.py`).

It sits in Frontend & Design, covering HTML artifacts. The repository describes itself as: Skills collection for Minis. The licence is MIT.

When your agent uses it

  • S mention these components
  • Visualization pages

Example prompts

  • “/generative-ui-minis”

Requirements

  • Python 3

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Complete Artifact Generator
  2. Render from a JSON spec

What it can do on your machine

Read from SKILL.md and the folder at commit ae8c5db. 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 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    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

Generative UI Minis loads about 1.1k tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 358 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~84
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 OpenMinis/MinisSkills at commit ae8c5db, republished under its MIT licence (© OpenMinis). 358 words, ~1,131 tokens.

Download SKILL.mdSave it as .claude/skills/generative-ui-minis/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
generative-ui-minis
description
In the current Minis environment, automatically convert text descriptions into a single-file HTML generator similar to Claude Artifact, with unified support for outputs such as cards, tables, records, timelines, code blocks, and charts. Use this skill first when users mention these components or visualization pages.

Generative UI Minis Skill

This is a Claude Artifact-style generator skill designed for the current Minis / iSH environment.

The goal is not to modify the chat host itself, but to:

  1. Organize user instructions into a structured spec
  2. Render them with Python into a single-file HTML artifact
  3. Save it to /var/minis/workspace/
  4. Let users preview, share, and continue iterating directly

Automatic Trigger Scenarios

Use this skill first when users express any of the following intentions:

  • "Create a Claude Artifact / Claude-style page"
  • "Turn the answer into cards"
  • "Generate a table / record sheet / checklist"
  • "Organize the content into a timeline"
  • "Generate a code block display page"
  • "Create a chart / visualization page"
  • "Render this content as an HTML prototype"
  • "Create an interactive explanation page / artifact"

In particular, when the user also mentions: cards, tables, records, code blocks, timelines, charts, visualization pages, artifacts assume by default that this skill should be invoked to generate an additional page.

Currently Supported Unified Components

  • cards: information cards / KPI cards
  • table: table
  • records: record list
  • timeline: timeline / step flow
  • code: code block
  • chart: built-in bar chart
  • details: collapsible details

Main Scripts

1) Complete Artifact Generator
bash
python3 /var/minis/skills/generative-ui-minis/scripts/generative_ui_artifact.py \
  "Weekly Project Report" \
  --text "Need overview cards\nNeed risk table\nNeed timeline\nNeed code block\nNeed chart"

By default, this outputs to:

bash
/var/minis/workspace/<title>_artifact.html
2) Render from a JSON spec
bash
python3 /var/minis/skills/generative-ui-minis/scripts/generative_ui_artifact.py \
  "Demo" \
  --spec /path/to/spec.json \
  --out /var/minis/workspace/demo_artifact.html \
  --json-out /var/minis/workspace/demo_spec.json

spec Format

json
{
  "title": "Generative UI Example",
  "summary": "Unified output of multiple components.",
  "chips": ["Artifact", "Cards", "Table"],
  "blocks": [
    {
      "type": "cards",
      "title": "Overview Cards",
      "items": [
        {"title": "Status", "value": "In Progress", "desc": "In the current iteration"}
      ]
    },
    {
      "type": "table",
      "title": "Record Sheet",
      "columns": ["Date", "Item", "Status"],
      "rows": [["03-17", "Generator Development", "Done"]]
    },
    {
      "type": "timeline",
      "title": "Timeline",
      "items": [
        {"title": "Phase One", "desc": "Requirements Organization"},
        {"title": "Phase Two", "desc": "Page Rendering"}
      ]
    },
    {
      "type": "code",
      "title": "Sample Code",
      "language": "python",
      "content": "print('hello artifact')"
    },
    {
      "type": "chart",
      "title": "Progress Chart",
      "series": [
        {"label": "Design", "value": 70},
        {"label": "Development", "value": 85}
      ]
    }
  ]
}
Show full SKILL.md (156 more words)Show less
  1. Determine whether the user needs an artifact page
  2. If the input is only a natural-language description, first use the script to automatically infer the basic blocks
  3. If the content is complex, organize it into a JSON spec before rendering
  4. After generating the HTML, send the workspace link directly to the user
  5. Continue modifying the spec or template based on feedback

Capability Boundaries

Can do:

  • Generate a unified single-file artifact HTML
  • Support cards, tables, records, timelines, code blocks, and charts
  • Serve as a visual supplement to an answer

Does not directly do yet:

  • Native message-level component injection into the chat host
  • Complex frontend applications driven by real-time databases
  • Long-running interactive server-side services

Trigger Recommendations

If the user says:

  • "Make me a card version"
  • "Also generate a table/timeline/code block"
  • "Organize it into an artifact page"

Do not respond with text only. Run this skill directly to generate an additional HTML artifact.

© OpenMinis, 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 2 other files (scripts) in generative-ui-minis of OpenMinis/MinisSkills.

  • SKILL.md
  • scripts/generative_ui_artifact.py
  • scripts/generative_ui_demo.py

Open the folder on GitHubat commit ae8c5db

Compare with similar skills

Generative UI Minis 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.

Generative UI Minis compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Generative UI Minis this skillOpenMinis/MinisSkills446—~1.1kAutomated safety check: PassMIT
LobeHub Interactive Prototypelobehub/lobehub83k—~1.6kAutomated safety check: PassCustom licence
Paperclip Pagepaperclipai/paperclip99k—~1kAutomated safety check: PassMIT
Openkb Deck NeonVectifyAI/OpenKB4.8k1 repos~4.3kAutomated safety check: PassApache-2.0
Webhome Homepage Builderwebhtv/webhtv1.7k—~3.8kAutomated safety check: PassGPL-3.0
Solo Artifactssolo-agent/solo698—~961Automated safety check: PassMIT

Similar skills

  • Builds single-file interactive HTML prototypes rendered with the real LobeHub UI components and written as production-style React, so they can later be split into files.

    83k GitHub stars~1.6k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Paperclip Page

    paperclipai/paperclip

    Publish static HTML pages and asset folders to the Paperclip S3/CloudFront page host.

    99k GitHub stars~1k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Openkb Deck Neon

    VectifyAI/OpenKB

    A skill your agent uses when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow /…

    4.8k GitHub starsUsed in 1 repo~4.3k tokens
    Frontend & DesignAuto-check passed
  • Build, review, debug, reverse-engineer data sources for, and package FongMi/WebHome custom homepage single-file HTML.

    1.7k GitHub stars~3.8k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • Solo Artifacts

    solo-agent/solo

    A skill your agent uses when a Solo task or thread should become an interactive, reviewable, self-contained HTML artifact for progress/status, review/decision, or comparison/leaderboard work inside…

    698 GitHub stars~961 tokensUpdated 27 days ago
    Frontend & DesignAuto-check passed
  • HTML

    plannotator/effective-html

    Create or redesign self-contained single-file HTML artifacts with a visual direction shaped by the user's brief, project, and subject.

    3.6k GitHub stars~1.6k tokensUpdated 26 days ago
    Frontend & DesignAuto-check passed

More from OpenMinis/MinisSkills

All 49 skills in this repo
  • Android UI Automation

    OpenMinis/MinisSkills

    Automate Android apps that have no public API or web version by driving the UI layer through the Accessibility Service.

    446 GitHub stars~1.6k tokensUpdated 2 days ago
    Auto-check passed
  • Codex On Ish

    OpenMinis/MinisSkills

    Install and run OpenAI Codex CLI inside the Minis/iSH Alpine sandbox on iOS, where rustls TLS and async sockets are broken.

    446 GitHub stars~1k tokensUpdated 2 days ago
    Auto-check passed
  • Evidence Chain Builder

    OpenMinis/MinisSkills

    Score a claim against the evidence behind it. An agent skill from OpenMinis/MinisSkills.

    446 GitHub stars~2.4k tokensUpdated 2 days ago
    Auto-check passed
  • Hyperframes CLI

    OpenMinis/MinisSkills

    HyperFrames CLI and Minis rendering. An agent skill from OpenMinis/MinisSkills.

    446 GitHub stars~3.5k tokensUpdated 2 days ago
    Auto-check passed
  • Whenpeak

    OpenMinis/MinisSkills

    Predict when a person's brain works best from their sleep, using the WhenPeak performance-intelligence API, and turn it into concrete scheduling advice.

    446 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check passed
  • Openstreetmap Marker

    OpenMinis/MinisSkills

    Generate a mobile-first, immersive, Amap(Gaode)-style custom landmark marker HTML map for travel itinerary planning, place showcasing, location sharing, etc.

    446 GitHub stars~1.9k tokensUpdated 2 days ago
    Auto-check passed

Questions about Generative UI Minis

What does Generative UI Minis do?

In the current Minis environment, automatically convert text descriptions into a single-file HTML generator similar to Claude Artifact, with unified support for outputs such as cards, tables…. Generative UI Minis is an agent skill from OpenMinis/MinisSkills. In the current Minis environment, automatically convert text descriptions into a single-file HTML generator similar to Claude Artifact, with unified support for outputs such as cards, tables, records, timelines, code blocks, and charts.

When should I use Generative UI Minis?

Generative UI Minis fits situations like: S mention these components; visualization pages.

How do I install Generative UI Minis in Claude Code?

Run `npx skills add OpenMinis/MinisSkills --skill generative-ui-minis -a claude-code`. Or copy the skill folder (generative-ui-minis in OpenMinis/MinisSkills) into .claude/skills/generative-ui-minis in your project. Claude Code loads it when a task matches its description.

How do I install Generative UI Minis in Codex?

Run `npx skills add OpenMinis/MinisSkills --skill generative-ui-minis -a codex`. Or copy the skill folder (generative-ui-minis in OpenMinis/MinisSkills) into .agents/skills/generative-ui-minis in your project. Codex loads it when a task matches its description.

Can I use Generative UI Minis 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 OpenMinis/MinisSkills --skill generative-ui-minis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/generative-ui-minis, .gemini/skills/generative-ui-minis, .github/skills/generative-ui-minis and .opencode/skills/generative-ui-minis in your project.

What does Generative UI Minis need to run?

Going by SKILL.md and its folder, Generative UI Minis needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Generative UI Minis 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 Generative UI Minis 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 Generative UI Minis use?

Generative UI Minis 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 Generative UI Minis use?

About 1.1k tokens (SKILL.md is roughly 4.5k 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 Generative UI Minis?

Skills that share tags, products or a category with Generative UI Minis: LobeHub Interactive Prototype (lobehub/lobehub, 83k stars), Paperclip Page (paperclipai/paperclip, 99k stars), Openkb Deck Neon (VectifyAI/OpenKB, 4.8k stars) and Webhome Homepage Builder (webhtv/webhtv, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Generative UI Minis?

OpenMinis (a GitHub organization) maintains it in OpenMinis/MinisSkills, which has 446 GitHub stars. The repository holds 49 skills in this directory. The repository was last updated on October 7, 2026.

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