JSPM

  • ESM via JSPM
  • ES Module Entrypoint
  • Export Map
  • Keywords
  • License
  • Repository URL
  • TypeScript Types
  • README
  • Created
  • Published
  • Downloads 32
  • Score
    100M100P100Q39108F
  • License MIT

Generate category-based skill command files for AI coding agents. One tag loads all relevant skills — no more hunting for skill names.

Package Exports

    This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (skilltags) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

    Readme

    skilltags

    One tag. All relevant skills. Automatically.

    npm version license skills.sh


    Tired of hunting for the right skill name every time you want the agent to actually use the skills you've installed?

    skilltags generates category-based command files for AI coding agents. Add one tag to your prompt, and the agent reviews every relevant skill before it starts working.

    Built for the skills.sh ecosystem by Vercel.

    The Problem

    You install great skills — responsive-design, ui-ux-pro-max, supabase-postgres-best-practices — but when you prompt the agent, it just starts coding. It skips the skills entirely. You end up hunting for exact skill names and tagging them manually, every single time.

    The Fix

    Without skilltags

    I want to make my website components
look more modern and responsive.

    The agent starts coding immediately. It doesn't check what skills are available. Even when you have skills relevant to your prompt that would improve the agent's output, the agent doesn't use them unless you explicitly tag them with @{SKILL_NAME}.

    With skilltags

    I want to make my website components
look more modern and responsive.
/st-frontend

    The agent reads the st-frontend.md command file, which contains a curated list of your installed frontend skills. The header instructs the agent to review that list, identify which skills are relevant to your request, and read them before starting work.

    Quick Start

    npm install skilltags -g

    The setup wizard runs on install — pick your categories, enable auto-sync, done.

    [!TIP] New to skills? Browse and install from skills.sh:

    npx skills find            # search the skills directory
npx skills add owner/repo  # install a skill package

    Categories

    Add a category command to the end of your prompt using /:

    Command What it loads
    /st-frontend React, Next.js, Vue, Tailwind, CSS, responsive design
    /st-backend APIs, auth, serverless, Stripe, webhooks
    /st-database Postgres, Supabase, Prisma, Drizzle, Redis
    /st-design UI/UX, typography, design systems, dark mode
    /st-testing Vitest, Playwright, Cypress, TDD, E2E
    /st-performance Core Web Vitals, lazy loading, code splitting
    /st-mobile React Native, Expo, Flutter, SwiftUI
    /st-devops Docker, GitHub Actions, Terraform, deployment
    /st-marketing SEO, Open Graph, structured data, analytics
    /st-accessibility WCAG, ARIA, screen readers, keyboard nav
    /st-ai-agents MCP, subagents, skill creation, browser automation
    /st-documentation Markdown, MDX, OpenAPI, Docusaurus

    [!NOTE] Don't see a category you need? Suggest one — we're always expanding the list.

    How It Works

    flowchart LR
    A["Install"] --> B["Select Categories"]
    B --> C["Scan 30+ Paths"]
    C --> D["Match Skills to Categories"]
    D --> E["Generate st-*.md Files"]

    style A stroke-width:2px
    style E stroke-width:2px
    Step What happens
    Install Setup wizard asks which categories you want and whether to enable auto-sync
    Scan Checks 30+ agent skill directories on your machine — zero configuration
    Match Skills are mapped to categories via keyword analysis on names + descriptions
    Generate A st-{category}.md file is created for each category in ~/.cursor/commands/

    What's inside each command file

    Each generated st-{category}.md file contains two parts:

    1. An instructional header — tells the agent to review the skills listed below and identify which are relevant to the user's request before starting work.
    2. A curated skill list — every matched skill for that category, with its name, file path, and description.

    [!IMPORTANT] The instructional header is the key piece — it overrides the agent's default tendency to skip skill review and forces it to check the listed skills against your request.

    What does auto-sync do?

    When enabled, a shell wrapper is added to your ~/.zshrc (or equivalent) that runs skilltags sync --quiet after every skills add or skills remove. Your category files stay up to date automatically — no manual re-sync needed.

    Commands

    skilltags                      Sync category files from current config
skilltags sync                 Same as above (explicit)
skilltags update               Add or remove skill categories
skilltags update <category>    Edit skills within a specific category
    Flags
    Flag Description
    --local Write to .cursor/commands/ (project scope) instead of global
    --quiet Suppress all output (used by auto-sync hooks)
    -v, --version Print version
    -h, --help Show help

    Full reference: docs/usage.md

    Contributing

    Suggest a category — Think a new skill category would be useful? Open an issue with the category name and what types of skills it should cover. The more specific the better — "What keywords should match this category?" helps us get it right.

    Improve keyword matching — Category keyword mappings live in lib/categories.js. If a skill isn't landing in the right category, PRs to improve the keyword lists are welcome.

    MIT License