agentleFS
tizonaitizonai/hyperui/skills/setup/SKILL.md

setup

Skill2 starsChanged 29 days agoApache-2.0View on GitHub

Install the hyperui stack (HyperFrames, Motion, Motion AI Kit, UI UX Pro Max, 21st.dev MCP, frontend-design, Impeccable, optional Playwright MCP) into the current project, and help install missing prerequisites (node, python3). Manual: /hyperui:setup [--global] [--21st-key KEY] [--skip-*] [--motion-plus] [--playwright-mcp] [--install-prereqs] [--telemetry | --no-telemetry] [--dry-run]

  • Reads credentials
  • Installs packages

191 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-voice-transcription, add-discord and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • juancruzmunozalbeloSkill

    add-voice-transcription

    Add voice message transcription to NanoClaw using OpenAI's Whisper API. Automatically transcribes WhatsApp voice notes so the agent can read and respond to them.

    Also in 5 projects that use this

  • MicrosoftSkill

    add-discord

    Add Discord bot channel integration via Chat SDK.

    Also in 11 projects that use this

  • MicrosoftSkill

    add-slack

    Add Slack channel integration via Chat SDK.

    Also in 11 projects that use this

  • juancruzmunozalbeloSkill

    add-telegram-swarm

    Add Agent Swarm (Teams) support to Telegram. Each subagent gets its own bot identity in the group. Requires Telegram channel to be set up first (use /add-telegram). Triggers on "agent swarm", "agent teams telegram", "telegram swarm", "bot pool".

    Also in 7 projects that use this

  • +8 more from microsoft

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 171 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the 21st.dev MCP row says skipped (no key), add one line: get a free key at https://21st.dev/mcp, then rerun /hyperui:setup --21st-key …

    line 32
  2. Very specific:

    Never improvise extra installs or fixes beyond what the script does.

    line 48

“Common” is measured: kept by at least 6 in 10 of the 171 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

hyperui:setup

Install the frontend craft stack into the current project. The script is idempotent and checks each component before touching anything.

Steps

  1. Run exactly:

    ${CLAUDE_PLUGIN_ROOT}/scripts/setup.sh $ARGUMENTS
  2. Preflight failed ([hyperui] ✗ node … or ✗ python3 …): show the install line the script printed for this OS, then ask ONCE, in the user's language: "Shall I install it for you?" — on yes, run exactly ${CLAUDE_PLUGIN_ROOT}/scripts/setup.sh --install-prereqs $ARGUMENTS (macOS with Homebrew: runs brew install node / brew install python and re-runs preflight; Homebrew missing or Linux/WSL2: the script prints the official lines for the user to run, since they need a password), then re-run step 1. On no, continue and relay which steps were skipped. Never run an install the user did not say yes to. Windows: say to use WSL2 and follow the Linux lines. Terraform is never installed here.
  3. Show the [hyperui] summary table verbatim to the user.
  4. If the 21st.dev MCP row says skipped (no key), add one line: get a free key at https://21st.dev/mcp, then rerun /hyperui:setup --21st-key <key> (or export TWENTY_FIRST_API_KEY). The key is stored at user scope, never in the project.
  5. --telemetry / --no-telemetry store the anonymous-usage answer (Telemetry row); with neither flag nothing changes — hyperui asks once, after the first finished task. No Telemetry row → nothing to say.
  6. Confirm with:

    ${CLAUDE_PLUGIN_ROOT}/scripts/doctor.sh
  7. Close with one line on what to try next: /hyperui:design for a design brief, /motion for Motion docs, springs and audits, /hyperframes for a video, /ui-ux-pro-max, /frontend-design, /impeccable audit.

Rules

  • Never improvise extra installs or fixes beyond what the script does. If a step fails, relay the [hyperui] ✗ line and the script's own hint; the user decides.
  • Flags pass straight through: --global, --21st-key <key>, --skip-hyperframes, --skip-uipro, --skip-motion, --skip-motion-kit, --skip-21st, --skip-frontend-design, --skip-impeccable, --motion-plus (also registers the motion-plus MCP for Motion+ subscribers), --playwright-mcp (registers the Playwright MCP, headless, as the browser fallback for visual checks when the session has no Claude in Chrome), --install-prereqs, --dry-run. --dry-run prints every command, including the prerequisite ones.
  • Relay the script's closing hint: live visual checks need Claude Code started with claude --chrome.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.