template
Health Warn
- License — License: MIT
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Low visibility — Only 9 GitHub stars
Code Pass
- Code scan — Scanned 12 files during light audit, no dangerous patterns found
Permissions Pass
- Permissions — No dangerous permissions requested
This project is a universal template for authoring and packaging AI assistant plugins. It allows developers to write a plugin once and automatically format it for distribution across major platforms like Claude Code, Cursor, Gemini CLI, and OpenAI Codex.
Security Assessment
Overall risk: Low. The automated code scan of 12 files found no dangerous patterns, hardcoded secrets, or requests for overly permissive access. The tool acts primarily as a scaffolding and build utility (using standard JavaScript/TypeScript commands) to generate directory structures and configuration manifests. It does not appear to execute arbitrary shell commands or make suspicious network requests. It functions entirely as a local development and packaging framework.
Quality Assessment
The project is actively maintained, with its most recent code push occurring today. However, it has very low community visibility, currently sitting at only 6 GitHub stars, meaning it has not been broadly battle-tested by the public. Additionally, the repository lacks a license file. While the code itself is safe, the absence of a license technically means others do not have explicit legal permission to use, modify, or distribute it. Developers relying on this for professional or commercial work should proceed with this legal ambiguity in mind.
Verdict
Safe to use as a local development utility, but use with caution in production environments due to the lack of a formal software license.
A single marketplace repo that works with claude, cursor, kiro, gemini and agent skills
AI Plugin Marketplace Template
Author AI assistant plugins once and ship them to multiple host platforms —
Claude Code, Cursor, Gemini CLI, Kiro, and Vercel Skills CLI — at the
highest fidelity each one accepts.
This repository is a thin consumer of the@ai-plugin-marketplace
toolkit. It contains your plugin sources and a dependency on the toolkit —
nothing else. All validation, scaffolding, and build logic lives in the
versioned @ai-plugin-marketplace/* npm packages, so you upgrade your tooling
with a single pnpm up and never get stranded on a forked copy of the build
scripts.
Getting started
This repo is a GitHub template. Click "Use this template" (or runaipm init in an empty directory to generate the same layout from scratch),
then:
pnpm install
Note:
pnpm installrequires the@ai-plugin-marketplace/*packages to be
published to npm. See CONTRIBUTING.md.
Authoring plugins
Add a new plugin
aipm scaffold my-plugin
This creates plugins/my-plugin/ with an aipm.config.ts support envelope and
skeleton manifests for each declared target, and registers the plugin in the
repo-root marketplace registries.
Build generated artifacts
aipm build
aipm build regenerates every toolkit-owned artifact — per-plugin hook JSON
(hooks/claude.json, hooks/hooks.json) and the standalone bundles underdist/gemini/ and dist/kiro/. Both authored sources and generated outputs are
committed, so plugins stay browsable on GitHub and pull-request diffs stay
honest.
Validate
aipm validate
Validation checks the support envelope, every target manifest's schema,
cross-target name consistency, MCP server-key sync, marketplace registration,
and freshness (that the committed generated artifacts match what aipm build
would produce).
package.json exposes these as pnpm build, pnpm check, andpnpm scaffold if you prefer the npm-script entry points.
The support envelope
Each plugin declares the targets it supports in plugins/<name>/aipm.config.ts:
import { defineConfig } from '@ai-plugin-marketplace/core';
export default defineConfig({
version: '0.1.0',
targets: ['claude', 'cursor', 'gemini', 'kiro', 'vercel'],
});
The toolkit emits artifacts only for declared targets and refuses to validate a
plugin that carries files for a target outside its envelope. To expand a
plugin's envelope, run aipm add-target <plugin> <target> to scaffold the
skeleton files for a new target, then fill in the manifest fields.
Repository structure
.
├── .claude-plugin/
│ └── marketplace.json # Claude Code marketplace registry
├── .cursor-plugin/
│ └── marketplace.json # Cursor marketplace registry
├── plugins/
│ └── <plugin-name>/ # One directory per plugin (authored sources)
│ ├── aipm.config.ts # Support envelope + plugin version
│ └── ... # Manifests, agents, skills, commands, hooks, rules
├── dist/ # Generated standalone bundles (committed)
│ ├── gemini/
│ └── kiro/
├── package.json # Depends on @ai-plugin-marketplace/cli + core
├── LICENSE
└── README.md
Upgrading the toolkit
Because the build logic lives in npm packages, upgrading is a routine
dependency bump — no copied scripts to reconcile:
pnpm up @ai-plugin-marketplace/cli @ai-plugin-marketplace/core
aipm build
git commit -am "chore: upgrade @ai-plugin-marketplace"
A minor or patch toolkit upgrade never requires you to change your plugin
manifests. Major upgrades may ask you to run aipm migrate; the CLI tells you
when.
Example plugin: skill-evaluator
The included skill-evaluator plugin demonstrates the full multi-platform
pattern end-to-end — it evaluates AI skills across model tiers (opus → sonnet →
haiku) using blind sub-agent testing. See
plugins/skill-evaluator/README.md.
License
MIT — see LICENSE.
Reviews (0)
Sign in to leave a review.
Leave a reviewNo results found