By using-system
Personal skills and hooks for AI dev CLI agents: GitHub Actions best practices, DevOps patterns, and cloud-native workflows
Use when running kubectl commands against an AKS cluster - enforces az aks command invoke for private cluster access, requires --file for complex commands, and persists cluster identity in memory
Use when writing or editing documentation, code comments, docstrings, README files, CHANGELOG entries, PR descriptions, commit messages, or any committed textual artifact - enforces English as the sole language regardless of the language used in the conversation
Use when creating git commits - enforces Conventional Commits specification for semantic versioning compatibility
Use when performing any git merge operation (direct merge, PR merge, or MR merge) - requires explicit user confirmation before executing the merge command
Use when reviewing, writing, or modifying GitHub Actions workflows or referencing any GitHub Action - enforces version pinning by commit SHA, latest version verification, and version commenting
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.
A curated collection of personal agent extensions, skills, and CLI hooks to enhance AI coding agents like Claude Code, Cursor, Codex, OpenCode, Copilot, and Gemini.
Each skill lives in its own directory under skills/ with a SKILL.md describing when and how it applies. Browse that folder for the current catalogue — no listing is maintained here to avoid drift.
claude plugin marketplace add using-system/ai-dev-extensions
claude plugin install ai-dev-extensions@using-system
Or for a single session from a local clone:
claude --plugin-dir /path/to/ai-dev-extensions
/plugin marketplace add using-system/ai-dev-extensions
/plugin install ai-dev-extensions@using-system
copilot plugin marketplace add using-system/ai-dev-extensions
copilot plugin install ai-dev-extensions@using-system
git clone https://github.com/using-system/ai-dev-extensions.git ~/.codex/ai-dev-extensions
mkdir -p ~/.agents/skills
ln -s ~/.codex/ai-dev-extensions/skills ~/.agents/skills/ai-dev-extensions
See docs/README.codex.md for details.
Add to your opencode.json:
{
"plugin": ["ai-dev-extensions@git+https://github.com/using-system/ai-dev-extensions.git"]
}
See docs/README.opencode.md for details.
gemini extensions install https://github.com/using-system/ai-dev-extensions
ai-dev-extensions/
├── skills/ # Skills (one directory per skill, each with a SKILL.md)
├── hooks/ # Hooks for CLI agents and git
│ ├── session-start # Session start hook (multi-platform)
│ ├── commit-msg # Git hook: validates Conventional Commits
│ ├── install-hooks # Install git hooks into any repo
│ ├── hooks.json # Claude Code plugin hooks
│ └── hooks-cursor.json # Cursor plugin hooks
├── docs/ # Platform-specific install guides
├── .claude-plugin/ # Claude Code plugin manifest
├── .cursor-plugin/ # Cursor plugin manifest
└── CLAUDE.md # Contributor guidelines
Install the git hooks (Conventional Commits validation) into any repo:
/path/to/ai-dev-extensions/hooks/install-hooks /path/to/your/repo
This symlinks commit-msg into your repo's .git/hooks/. Works for all agents and humans alike.
Apache-2.0
npx claudepluginhub using-system/ai-dev-extensions --plugin ai-dev-extensionsCore skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.