Agent skill

Clack

by pass-agent in pass-agent/loomkin

Build and maintain interactive Node.js/Bun CLIs with Clack (@clack/prompts and @clack/core).

MITAuto-check passed

Install Clack

skills CLI
$ npx skills add pass-agent/loomkin --skill clack -a claude-code

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

GitHub CLI
$ gh skill install pass-agent/loomkin clack --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/pass-agent/loomkin.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/cli/.agents/skills/clack .claude/skills/clack && 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
clack
GitHub stars
181
Token cost
~797 tokens
SKILL.md length
336 words
Files
11 (incl. scripts, references, assets)
Skills in repo
14
Repo updated
First seen
Licence
MIT

At a glance

Build and maintain interactive Node.js/Bun CLIs with Clack (@clack/prompts and @clack/core).

  • An AI agent needs to design prompt flows
  • SKILL.md covers Follow This Workflow, Bundled Resources, Non-Negotiable Rules and Freshness Policy
  • Runs JavaScript, TypeScript and Shell scripts from its folder; calls bash, npm and pnpm
  • Implement cancellation-safe input handling

What it does

Clack is an agent skill from pass-agent/loomkin. Build and maintain interactive Node.js/Bun CLIs with Clack (@clack/prompts and @clack/core). Use when an AI agent needs to design prompt flows, implement cancellation-safe input handling, add spinners/log/note UX, apply Clack best practices, or generate runnable examples aligned with official Clack docs.

Its SKILL.md is about 800 tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including scripts, reference files and assets (for example `assets/templates/basic-cli.ts`, `assets/templates/spinner-cli.ts` and `references/best-practices.md`).

It works with Node.js. The repository describes itself as: What if AI agents could form teams as fluidly as humans? Spawn specialists in milliseconds, share discoveries in real-time, review each other's work, and remember everything… The licence is MIT.

When your agent uses it

  • An AI agent needs to design prompt flows
  • Implement cancellation-safe input handling
  • Add spinners/log/note UX
  • Apply Clack best practices

Example prompts

  • “/clack”

Requirements

  • Node.js
  • A Bash shell

What it can do on your machine

Read from SKILL.md and the folder at commit f769ae7. 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/ (JavaScript, TypeScript and Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • bash
    • npm
    • pnpm
    • yarn

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

  • Network

    No URLs in SKILL.md. Its commands use npm, pnpm and yarn, which can reach the network depending on how they are called.

    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

Clack loads about 797 tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 79 tokens; SKILL.md has 336 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~797
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.3k

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 pass-agent/loomkin at commit f769ae7, republished under its MIT licence (© pass-agent). 336 words, ~797 tokens.

Download SKILL.mdSave it as .claude/skills/clack/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
clack
description
Build and maintain interactive Node.js/Bun CLIs with Clack (`@clack/prompts` and `@clack/core`). Use when an AI agent needs to design prompt flows, implement cancellation-safe input handling, add spinners/log/note UX, apply Clack best practices, or generate runnable examples aligned with official Clack docs.

Clack CLI Skill

Implement robust, user-friendly CLI flows with Clack.

Follow This Workflow

  1. Identify the implementation target.
  • Use @clack/prompts for most interactive CLI flows.
  • Use @clack/core for low-level/custom prompt rendering and lifecycle control.
  1. Load only the relevant references.
  • Prompt-centric workflows: references/prompts-api.md
  • Low-level/core extension work: references/core-api.md
  • UX and reliability review: references/best-practices.md
  • Pattern selection and scaffolding: references/examples.md
  • Source links and freshness checks: references/sources.md
  • If user asks for a starter file quickly, run scripts/scaffold-clack.sh.
  1. Build a minimal runnable skeleton first.
  • Include imports, intro(), flow logic, and outro().
  • Add install/run commands for the user's runtime.
  1. Add prompts with explicit validation and cancellation paths.
  • Validate every user-facing field that can fail constraints.
  • Handle cancellation after each prompt result with isCancel(...) and cancel(...).
  1. Add UX support functions intentionally.
  • Use log.* for structured feedback.
  • Use spinner() for long-running single operations.
  • Use note() for summaries and next actions.
  1. For asynchronous multi-step work, use task-oriented patterns.
  • Prefer clear status updates and concise task titles.
  • Keep success/error messages short and actionable.
  1. Finalize with a production-ready answer.
  • Return complete runnable code (not fragments) unless user asks otherwise.
  • Include quick verification steps.

Bundled Resources

  • scripts/scaffold-clack.sh

  • Generate a starter CLI from curated templates in JS or TS.

  • Usage: bash scripts/scaffold-clack.sh <target-dir> [basic|spinner] [js|ts] [auto|npm|pnpm|yarn|bun]

  • assets/templates/basic-cli.mjs

  • Baseline prompt flow with validation, cancellation handling, and summary note.

  • assets/templates/spinner-cli.mjs

  • Prompt flow plus spinner-driven execution pattern for longer operations.

  • assets/templates/basic-cli.ts

  • TypeScript variant of the baseline prompt flow.

  • assets/templates/spinner-cli.ts

  • TypeScript variant of the spinner flow.

Non-Negotiable Rules

  • Always include a cancellation-safe path.
  • Never assume valid input; validate and explain fixups in-place.
  • Use consistent tone in status and error messages.
  • Keep prompt trees shallow; split complex flows into grouped steps.
  • Prefer sensible defaults to reduce user typing and errors.

Freshness Policy

  • Treat Clack APIs as evolving.
  • Use references/sources.md as the source-of-truth link map.
  • If the user asks for the latest behavior or version-specific details, re-check the official docs before finalizing.
  • If no web access is available, state that constraint explicitly and stick to documented APIs in this skill.

© pass-agent, 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 10 other files (scripts, references, assets) in apps/cli/.agents/skills/clack of pass-agent/loomkin.

  • SKILL.md
  • assets/templates/basic-cli.mjs
  • assets/templates/basic-cli.ts
  • assets/templates/spinner-cli.mjs
  • assets/templates/spinner-cli.ts
  • references/best-practices.md
  • references/core-api.md
  • references/examples.md
  • references/prompts-api.md
  • references/sources.md
  • scripts/scaffold-clack.sh

Open the folder on GitHubat commit f769ae7

Compare with similar skills

Clack 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.

Clack compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Clack this skillpass-agent/loomkin181—~797Automated safety check: PassMIT
Chart Visualizationbytedance/deer-flow83k2 repos~840Automated safety check: PassMIT
Web Access via Browser CDPeze-is/web-access9.1k4 repos~2.2kAutomated safety check: PassMIT
Knap Markdown Templateskepano/obsidian-skills49k2 repos~986Automated safety check: PassMIT
Electron Multi-Process ArchitectureiOfficeAI/AionUi33k1 repos~1.8kAutomated safety check: PassApache-2.0
Chrome CDP Browser Controlzenstory-ai/oh-story-claudecode7.3k2 repos~1.2kAutomated safety check: PassMIT

Similar skills

  • Chart Visualization

    bytedance/deer-flow

    Picks a suitable chart type from 26 options for your data, maps the data to that chart's parameters and generates a chart image through a JavaScript script.

    83k GitHub starsUsed in 2 repos~840 tokens
    Data & AnalyticsAuto-check passed
  • Routes every web task, from searching to logged-in browsing, through a tiered choice of search, fetch, curl or a real Chrome or Edge session driven over CDP.

    9.1k GitHub starsUsed in 4 repos~2.2k tokens
    Productivity & AutomationAuto-check passed
  • Knap Markdown Templates

    kepano/obsidian-skills

    Renders Markdown notes from Knap templates and JSON data on the command line, including notes built from Defuddle web page output.

    49k GitHub starsUsed in 2 repos~986 tokens
    Documents & OfficeAuto-check passed
  • Tells the agent where new code belongs in an Electron multi-process project and which APIs each process may use, with rules for new bridges, services, agents and workers.

    33k GitHub starsUsed in 1 repo~1.8k tokens
    DevelopmentAuto-check passed
  • Chrome CDP Browser Control

    zenstory-ai/oh-story-claudecode

    Drives a Chrome window over the DevTools Protocol with the agent-browser CLI, so the agent can reuse your logged-in sessions, read pages and pull tokens.

    7.3k GitHub starsUsed in 2 repos~1.2k tokens
    Productivity & AutomationAuto-check passed
  • DeerFlow Smoke Test

    bytedance/deer-flow

    Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.

    83k GitHub stars~2.5k tokensUpdated today
    Testing & QAAuto-check: notes

More from pass-agent/loomkin

All 14 skills in this repo
  • React Ink

    pass-agent/loomkin

    A skill your agent uses when building terminal user interfaces with React Ink - interactive CLI apps, terminal dashboards, progress displays, or keyboard-driven TUI components.

    181 GitHub starsUsed in 1 repo~3.1k tokens
    Auto-check passed
  • Modern CSS

    pass-agent/loomkin

    Specialized knowledge for writing modern high-quality CSS. An agent skill from pass-agent/loomkin.

    181 GitHub stars~3.8k tokensUpdated 4 mo ago
    Auto-check passed
  • Elixir Expert

    pass-agent/loomkin

    Expert in Elixir, Phoenix Framework, and OTP. An agent skill from pass-agent/loomkin.

    181 GitHub starsUsed in 1 repo~796 tokens
    Auto-check passed
  • Tui Design

    pass-agent/loomkin

    This skill should be used when designing terminal user interfaces, creating TUI layouts, choosing TUI color schemes, implementing keyboard navigation, building terminal dashboards, or working with…

    181 GitHub stars~5k tokensUpdated 4 mo ago
    Auto-check passed
  • Vault Groom

    pass-agent/loomkin

    Audit and clean up knowledge base state — archive completed work, fix inconsistencies

    181 GitHub stars~567 tokensUpdated 4 mo ago
    Auto-check passed
  • Vault Meeting

    pass-agent/loomkin

    Process a meeting transcript — extract decisions, action items, and key discussion points into structured vault entries

    181 GitHub stars~1.5k tokensUpdated 4 mo ago
    Auto-check passed

Works with

Questions about Clack

What does Clack do?

Build and maintain interactive Node.js/Bun CLIs with Clack (@clack/prompts and @clack/core). Clack is an agent skill from pass-agent/loomkin.js/Bun CLIs with Clack (@clack/prompts and @clack/core).

When should I use Clack?

Clack fits situations like: an AI agent needs to design prompt flows; implement cancellation-safe input handling; add spinners/log/note UX; apply Clack best practices.

How do I install Clack in Claude Code?

Run `npx skills add pass-agent/loomkin --skill clack -a claude-code`. Or copy the skill folder (apps/cli/.agents/skills/clack in pass-agent/loomkin) into .claude/skills/clack in your project. Claude Code loads it when a task matches its description.

How do I install Clack in Codex?

Run `npx skills add pass-agent/loomkin --skill clack -a codex`. Or copy the skill folder (apps/cli/.agents/skills/clack in pass-agent/loomkin) into .agents/skills/clack in your project. Codex loads it when a task matches its description.

Can I use Clack 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 pass-agent/loomkin --skill clack -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/clack, .gemini/skills/clack, .github/skills/clack and .opencode/skills/clack in your project.

What does Clack need to run?

Going by SKILL.md and its folder, Clack needs JavaScript, TypeScript and a shell for the scripts in its folder and the command-line tools its instructions call (bash, npm, pnpm and yarn). Our summary lists: Node.js; A Bash shell.

Does Clack access the network?

SKILL.md contains no URLs. Its commands use npm, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Clack 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 Clack use?

Clack 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 Clack use?

About 797 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.5k tokens, read only when the agent opens those files.

What are the alternatives to Clack?

Skills that share tags, products or a category with Clack: Chart Visualization (bytedance/deer-flow, 83k stars), Web Access via Browser CDP (eze-is/web-access, 9.1k stars), Knap Markdown Templates (kepano/obsidian-skills, 49k stars) and Electron Multi-Process Architecture (iOfficeAI/AionUi, 33k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Clack?

pass-agent (a GitHub organization) maintains it in pass-agent/loomkin, which has 181 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on May 17, 2026.

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