npx claudepluginhub aiotnetwork/aiotaiagentskillsA collection of Claude Code skills for AI-assisted development workflows
AIOTNetworkA collection of Claude Code skills for AI-assisted development workflows.
Add the AIOT skills marketplace to Claude Code:
/plugin marketplace add AIOTNetwork/AIOTAIAgentSkills
Then install the plugin:
/plugin install aiot-ai-agent-skills@aiot-skills
/plugin install AIOTNetwork/AIOTAIAgentSkills
Copy the skills/ directory to your project's .claude/skills/:
cp -r skills/* /path/to/your/project/.claude/skills/
/smart-commitAI-powered git workflow assistant. Generates conventional commit messages and runs pre-commit checks.
Features:
Usage:
/smart-commit # Review staged changes, then offer to commit
/smart-commit review # Analyze and suggest splits only
/smart-commit commit # Auto-commit with generated messages
/smart-commit precommit # Run pre-commit checks (lint, format, test)
Commit Message Format:
<type>(<scope>): <subject>
<body>
<footer>
Allowed Types:
| Type | Description |
|---|---|
build | Changes to build system or external dependencies |
ci | Changes to CI configuration files and scripts |
docs | Documentation only changes |
feat | A new feature |
fix | A bug fix |
perf | A code change that improves performance |
refactor | A code change that neither fixes a bug nor adds a feature |
style | Changes that do not affect the meaning of code |
test | Adding missing tests or correcting existing tests |
Examples:
feat(auth): add OAuth2 login support
fix(api): handle null response from external service
docs(readme): update installation instructions
refactor(core): extract validation logic into separate module
BREAKING CHANGE: rename authToken to accessToken in config
/plancraftPlan-first development workflow. Enforces human-in-the-loop review gates before any code is written.
Core principle: Never let the agent write code until you've reviewed and approved a written plan.
The Flow:
Research → Plan → Annotate (1-6x) → Todo → Implement → Feedback
Usage:
/plancraft research # Deep-read codebase, write research.md
/plancraft plan # Write implementation plan to plan.md
/plancraft annotate # Address inline notes in plan.md
/plancraft todo # Add granular task checklist to plan.md
/plancraft implement # Execute plan on feature branch, track progress
/plancraft resume # Recover context after session restart
/plancraft status # Show current phase and progress
Key Features:
> **[NOTE]:** inline notes, agent refines the plan (1-6 rounds)resume recovers from context compaction by reading plan.mdplancraft/<feature> branches, revert = clean slateWhen to use: Changes spanning multiple files, >30 min estimated work, architectural decisions, unfamiliar subsystems.
Annotation types:
| Prefix | Meaning |
|---|---|
[NOTE] | General feedback |
[REJECT] | Remove this section |
[CONSTRAINT] | Hard rule, don't change |
[QUESTION] | Agent should answer |
Methodology inspired by Boris Tane's Claude Code workflow
The plugin automatically triggers the /smart-commit skill when your prompt contains commit-related keywords:
commitcommitscommittingExamples that will auto-trigger:
"commit my changes"
"help me commit this"
"I want to commit"
"create a commit for these changes"
The plugin also includes a pre-commit hook that automatically runs when Claude executes a git commit command. It will:
Supported project types: Node.js, Python, Rust, Go
Open Design — local-first design app exposed to coding agents over MCP. Install once with your agent's plugin command and projects/files/skills are reachable through stdio.
Claude Code plugins for the Slidev presentation framework
Bundled plugins for actuating and debugging the Chrome browser.