A curated collection of skills and plugins for AI agents. Extend your agent capabilities with specialized workflows and integrations.
vscode://chat-plugin/add-marketplace?ref=MrMYHuang/agent-marketplace
myh-plugin folder — skills are organized here.SKILL.md file describing how to use it.Skills integrate directly into your agent. Reference a skill by name in your workflow:
myh-plugin/skills/github-fix-this/SKILL.md)Example: The github-fix-this skill automates GitHub workflow — from issue to pull request in one go.
| Skill | Purpose | Prerequisites |
|---|---|---|
| github-fix-this | Automate GitHub issue-to-PR workflow | gh CLI authenticated, Git repo with remote |
| sqlcl | Query/modify Oracle databases via SQLcl | SQLcl installed, saved named connection |
agent-marketplace/
├── myh-plugin/
│ └── skills/
│ ├── github-fix-this/ # GitHub workflow automation
│ │ └── SKILL.md
│ └── sqlcl/ # Oracle database tool
│ ├── SKILL.md
│ ├── agents/ # Agent configs (e.g., openai.yaml)
│ └── references/ # Usage examples & docs
├── myh-hooks/
│ └── hooks.json # Agent lifecycle hooks
└── README.md # This file
SKILL.md with detailed workflow and examplesmyh-plugin/skills/*/agents/ for agent-specific setupmyh-plugin/skills/*/references/To add a new skill:
myh-plugin/skills/<skill-name>/SKILL.md with Prerequisites, Workflow, and ChecklistQuestions? Refer to individual skill documentation for detailed usage patterns and troubleshooting.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub mrmyhuang/agent-marketplace --plugin myh-hooks[Internal] Hook スクリプトを claude-code-plugin リポジトリの正しい構造に配置・登録するための内部ユーティリティ
Create and validate production-grade agent skills with 100-point marketplace grading
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Memory compression system for Claude Code - persist context across sessions
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.