By j2h4u
Claude Code meta-tools: skill creation, CLAUDE.md management; mcp-server-design (MCP design patterns, audit, client compatibility)
This skill should be used when the user asks to "update CLAUDE.md", "edit CLAUDE.md", "write to CLAUDE.md", "create CLAUDE.md", "add to project memory", mentions "CLAUDE.md", or refers to project-specific notes and learnings. Redirects these operations to AGENTS.md instead, working with the PostToolUse hook that ensures @./AGENTS.md reference in CLAUDE.md for proper project context management.
This skill should be used when the user asks to "create CLAUDE.md", "refactor CLAUDE.md", "split large CLAUDE.md", "optimize memory files", "set up .claude/rules", "my CLAUDE.md is too big", "organize project documentation", "implement 3-tier documentation", "add conditional rules", "use paths frontmatter", or needs guidance on CLAUDE.md best practices, size limits, memory hierarchy, or the official 3-Tier documentation system.
This skill should be used when the user asks to "find orphaned processes", "kill claude processes", "clean up claude orphans", "terminate stuck claude", "claude consuming CPU", "check for orphan processes", "cleanup claude code processes", "find zombie claude processes". Finds and terminates orphaned Claude Code CLI processes that consume CPU resources on macOS and Linux.
This skill should be used when the user asks to "create skill for CLI tool", "document CLI tool", "create skill for docker", "create skill for kubectl", "document command-line tool", "create CLI guidance", "build skill for terminal commands", "introspect CLI tool", "create skill from help text", or needs to systematically introspect CLI tools through help text, man pages, GitHub repositories, and online research, then organize findings into effective skill documentation with proper mental model, command reference, and workflow patterns.
This skill should be used when the user asks to "design an MCP server", "audit an MCP server", "review MCP tools", "add MCP tool", "improve tool descriptions", "design tool surface", "add submit_feedback tool", "review tool schema", mentions "MCP transport", "tool annotations", "mcp stdio", "MCP Resources", "MCP Prompts", or is designing, reviewing, or auditing any MCP server. Covers design philosophy, tool naming, parameter schemas, agent UX, feedback channel, transport, security, and client compatibility. NOT for hands-on implementation from scratch (use mcp-builder for that).
Modifies files
Hook triggers on file write and edit operations
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Curated collection of Claude Code plugins for everyday development.
Skills, agents, and hooks that make Claude Code smarter about your workflow — from coding standards to git automation.
omcc-statusline — Claude Code statusline with git indicators (branch, CI, PRs, msgs), API usage and vibe pacing.
# Add marketplace
/plugin marketplace add j2h4u/oh-my-claude-plugins
# Install what you need
/plugin install coding-standards@oh-my-claude-plugins
Or browse interactively: /plugin → Browse and install plugins → oh-my-claude-plugins
oh-my-claude-plugins/
├── .claude-plugin/
│ ├── marketplace.json # Marketplace metadata
│ └── plugin.json # Plugin registry
├── agents/ # Custom agents
│ ├── plugin.json
│ ├── python-code-reviewer/
│ ├── python-quick-fixer/
│ └── quick-worker/
├── claude-code-meta/ # Claude Code tooling
│ ├── plugin.json
│ └── skills/
│ ├── claude-md-redirect/
│ ├── claude-md-writer/
│ ├── cli-skill-creator/
│ ├── mcp-builder/
│ └── opencode-config/
├── coding-standards/ # Code quality plugins
│ ├── plugin.json
│ └── skills/
│ ├── dignified-bash/
│ ├── dignified-python/
│ ├── kaizen/
│ └── software-architecture/
├── databases/ # Database tools
│ ├── plugin.json
│ └── skills/
│ ├── metabase-swiss-knife/
│ └── postgres-patterns/
├── devops/ # System administration
│ ├── plugin.json
│ └── skills/
│ └── linux-sysadmin/
├── docs/ # Documentation (plugin + official guides)
│ ├── plugin.json
│ ├── skills/ # Documentation creation skills
│ │ ├── doc-coauthoring/
│ │ ├── mermaid-best-practices/
│ │ └── readme-generator/
│ ├── plugins.md # Official Claude Code documentation
│ ├── hooks.md
│ └── plugin-development/
├── git-tools/ # Git workflow plugins
│ ├── plugin.json
│ └── skills/
│ ├── changelog-generator/
│ ├── gh/
│ └── git-workflow-manager/
├── productivity/ # Analysis tools
│ ├── plugin.json
│ └── skills/
│ └── meeting-insights-analyzer/
├── statusline/ # Utility: custom statusline
│ └── agents/
│ └── statusline-setup/
└── web-dev/ # Frontend development
├── plugin.json
└── skills/
├── vercel-react-best-practices/
├── web-artifacts-builder/
└── web-design-guidelines/
Each plugin directory contains:
plugin.json — Plugin manifestskills/ — Skill directories with SKILL.mdagents/ — Agent directories (where applicable)references/, examples/ — Supporting content (in skill dirs)Code quality and development philosophy.
| Skill | Description | Quality |
|---|---|---|
| dignified-bash | Strict mode, shellcheck, defensive patterns | ⭐⭐⭐⭐ |
| dignified-python | Pragmatic LBYL-leaning standards, version-aware (3.10-3.13), Click CLI | ⭐⭐⭐⭐⭐ |
| kaizen | Continuous improvement, poka-yoke, YAGNI | ⭐⭐⭐⭐⭐ |
| software-architecture | Clean Architecture & DDD principles | ⭐⭐ |
Git workflows and GitHub integration.
| Skill | Description | Quality |
|---|---|---|
| changelog-generator | Transform commits into user-friendly changelogs | ⭐⭐⭐ |
| gh | PR management, GraphQL API, Projects V2 | ⭐⭐⭐⭐⭐ |
| git-workflow-manager | Conventional commits, semantic versioning | ⭐⭐⭐ |
Frontend development.
| Skill | Description | Quality |
|---|---|---|
| vercel-react-best-practices | 45 performance rules: waterfalls, bundles, SSR | ⭐⭐⭐⭐ |
| web-artifacts-builder | Build React artifacts for Claude.ai | ⭐⭐ |
| web-design-guidelines | Vercel Web Interface Guidelines | ⭐⭐ |
Documentation creation.
| Skill | Description | Quality |
|---|---|---|
| doc-coauthoring | Collaborative workflow: gathering, refinement, reader testing | ⭐⭐⭐⭐ |
| mermaid-best-practices | Mermaid diagrams: syntax, quoting, shapes, rendering pitfalls | ⭐⭐⭐ |
| readme-generator | README best practices by project type | ⭐⭐⭐ |
System administration.
npx claudepluginhub j2h4u/oh-my-claude-plugins --plugin claude-code-metaWeb development: React/Next.js best practices, web artifacts, design guidelines
Git workflows: GitHub CLI, repo creation, changelogs, conventional commits, releases
DevOps tools: Linux system administration for Debian/Ubuntu
Vibe-based development workflow: feature design, multi-expert panel brainstorming
Documentation tools: collaborative doc writing, README generation, Mermaid diagrams
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
v9.54.1 — Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.