skills-hub — agent-skills skills-hub, community, agent-skills, ide skills, claude-code

v1.0.0

About this Skill

Unify your AI skillbox. A local hub to visualize, manage, and sync skills across Antigravity, Claude, Cursor, Trae, and other AI agents.

# Core Topics

PotatoDog1669 PotatoDog1669
[8]
[0]
Updated: 3/27/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 1/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Locale and body language aligned
Review Score
1/11
Quality Score
36
Canonical Locale
en
Detected Body Locale
en

Unify your AI skillbox. A local hub to visualize, manage, and sync skills across Antigravity, Claude, Cursor, Trae, and other AI agents.

Core Value

Unify your AI skillbox. A local hub to visualize, manage, and sync skills across Antigravity, Claude, Cursor, Trae, and other AI agents.

Ideal Agent Persona

Suitable for operator workflows that need explicit guardrails before installation and execution.

Capabilities Granted for skills-hub

! Prerequisites & Limits

Why this page is reference-only

  • - The page lacks a strong recommendation layer.
  • - The page lacks concrete use-case guidance.
  • - The page lacks explicit limitations or caution signals.
  • - The underlying skill quality score is below the review floor.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is skills-hub?

Unify your AI skillbox. A local hub to visualize, manage, and sync skills across Antigravity, Claude, Cursor, Trae, and other AI agents.

How do I install skills-hub?

Run the command: npx killer-skills add PotatoDog1669/skills-hub/skills-hub. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

Which IDEs are compatible with skills-hub?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add PotatoDog1669/skills-hub/skills-hub. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use skills-hub immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

skills-hub

Install skills-hub, an AI agent skill for AI agent workflows and automation. Review the use cases, limitations, and setup path before rollout.

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Skills Hub

Use this skill as the Skills Hub orchestration and preset-selection entrypoint.

Use This Skill When

  • The user wants help choosing a project setup from Skills Hub presets.
  • The user asks which AGENTS.md and skills package fit a project.
  • The user wants to browse or inspect presets before installing.
  • The user wants to install a preset as a policy/package/kit.
  • The user wants to apply a saved kit with temporary added or removed skills.

Core Rule

Do not invent available presets or skills.

Always inspect the current Skills Hub catalog or local kit state first, then explain what you found.

Workflow

1. Read Project Context

First understand the user goal and the project context:

  • project path
  • language / framework
  • whether this is new feature work, backend work, research work, or release work
  • whether the user wants a preset or a custom/manual kit

If the project context is ambiguous, inspect the repository before recommending a preset.

2. Search Presets First

For first-pass recommendations, use the preset catalog before falling back to manual kit assembly.

Start with:

bash
1skills-hub kit preset-list

If you need to narrow candidates:

bash
1skills-hub kit preset-search <query>

Examples:

bash
1skills-hub kit preset-search nextjs 2skills-hub kit preset-search node api 3skills-hub kit preset-search scientific literature

3. Inspect Candidate Presets

For any promising candidate, inspect it before recommending installation:

bash
1skills-hub kit preset-inspect --id <preset-id>

Use the inspect output to explain:

  • which policy the preset uses
  • which source repos it draws skills from
  • which selected skills are included
  • whether it matches the current project and user goal

4. Recommend Before Installing

Before installing anything, present a short recommendation to the user:

  • recommended preset
  • why it fits
  • what policy it will create
  • what skills it will include
  • whether you suggest any temporary --with or --without adjustments at apply time

Do not install or apply until the user confirms.

5. Install the Preset

After confirmation:

bash
1skills-hub kit preset-install --id <preset-id>

This creates:

  • a preset-backed policy
  • a preset-backed package
  • a kit

6. Review Installed Kits If Needed

After installation, you can inspect saved kit state with:

bash
1skills-hub kit list 2skills-hub kit policy-list 3skills-hub kit package-list

Use these when the user wants to confirm what was created, or when multiple kits already exist.

7. Apply the Kit

Apply the installed kit only after the user confirms the target project and agent:

bash
1skills-hub kit apply --id <kit-id> --project <path> --agent <name>

If the user wants temporary adjustments for this one apply only:

bash
1skills-hub kit apply --id <kit-id> --project <path> --agent <name> --with <skill> --without <skill>

Notes:

  • --with adds a hub skill for this apply only
  • --without removes a skill from the saved loadout for this apply only
  • these flags do not mutate the saved kit

8. Fall Back to Manual Kit Workflows Only When Needed

If no preset fits, fall back to manual kit composition:

bash
1skills-hub kit policy-list 2skills-hub kit package-list 3skills-hub kit list

Then guide the user toward manual policy/package/kit creation or editing.

Recommendation Output Format

When recommending a preset, keep the answer compact and explicit:

text
1Recommended preset: <preset-id> 2 3Why: 4- <reason 1> 5- <reason 2> 6 7Policy: 8- <policy name> 9 10Selected skills: 11- <skill 1> 12- <skill 2> 13 14Suggested apply-time adjustments: 15- add: <skill> (optional) 16- remove: <skill> (optional) 17 18If you want, I can install this preset and then apply it to <project> for <agent>.

Produces

  • an inspected preset recommendation
  • optionally, a newly installed preset-backed policy/package/kit
  • optionally, an applied kit for a selected project and agent

Guardrails

  • Do not claim a preset exists unless skills-hub kit preset-list/search shows it.
  • Do not claim a skill is included unless skills-hub kit preset-inspect shows it.
  • Do not apply a kit without user confirmation.
  • If no official preset fits, say so directly and switch to manual kit guidance.

Related Skills

Looking for an alternative to skills-hub or another community skill for your workflow? Explore these related open-source skills.

View All

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

Generate customizable widget plugins for the prompts.chat feed system

149.6k
0
AI

flags

Logo of vercel
vercel

The React Framework

138.4k
0
Browser

pr-review

Logo of pytorch
pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

98.6k
0
Developer