oh-my-claude-plugins

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).

This skill should be used when the user asks to "write Python code", "review Python", "refactor Python", "fix Python types", "improve error handling", "use pathlib", "create ABC interface", "fix mypy errors", "add type hints", "make this pythonic", "LBYL vs EAFP", or mentions "Python", ".py files", "type annotations", "pathlib", "subprocess", or Python CLI patterns. Provides opinionated production Python standards with automatic version detection (3.10-3.13), modern type syntax, explicit condition checks where practical, pathlib operations, interface guidance, and pragmatic production patterns.

This skill should be used when the user asks to "create a diagram", "draw a flowchart", "make a mermaid diagram", "fix mermaid", "diagram not rendering", "sequence diagram", "state diagram", "flowchart", "ER diagram", "mermaid syntax", "mermaid chart", or needs guidance on creating Mermaid diagrams that render correctly in Obsidian, GitHub, and other markdown environments — including node quoting, shape syntax, subgraph labels, arrow types, and avoiding common pitfalls.

This skill should be used when the user asks to "write PostgreSQL query", "optimize postgres query", "use LATERAL join", "use CTE", "window functions in postgres", "explain analyze", "postgres performance", "rewrite SQL query", "postgres local variables", "advanced SQL patterns", mentions "PostgreSQL", "psql", or needs guidance on idiomatic PostgreSQL query patterns beyond basic SELECT/JOIN.

This skill should be used when the user asks to "create github repo", "create a new repository", "set up github remote", "configure deploy keys", "init github project", "push to new repo", "create repo with SSH keys", "set up git remote". Creates a GitHub repository, configures SSH deployment keys, and sets up git remote for the current folder.

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 "compress this", "make it shorter but keep everything", "create a cheat sheet", "dense summary", "reference format", "compact version", "information-dense", "condense this document". NOT for casual summaries—only when user explicitly wants maximum density with zero data loss.

This skill should be used when the user asks to "write typescript", "configure typescript project", "add type hints", "use generics", "migrate to typescript", "set up vite with typescript", "implement type-safe patterns", "use satisfies operator", "configure eslint for typescript", or needs guidance on enterprise TypeScript 5.9+ development with React, NestJS, or LangChain.js.

This skill should be used when the user asks to "simplify typescript code", "simplify javascript", "refactor this js code", "unbloat javascript", "unbloat typescript", "clean up this react component", "reduce complexity in typescript", "simplify tsx", or mentions code simplification for JS/TS/React/TSX files.

This skill should be used when the user asks to "write bash script", "create shell script", "review bash code", "write hook", "create systemd service script", "fix shellcheck warnings", "improve bash script", mentions "bash", "shell", ".sh files", or works with any shell scripting including hooks and CLI tools. Enforces bash purist style with strict mode, die() function, proper variable declarations, assertion comments, result comments, shellcheck compliance, and structured function layout.

This skill should be used when the user asks to "check metabase status", "inspect metabase", "find duplicate cards", "diagnose metabase issues", "backup metabase", "restore metabase backup", "create metabase card", "create metabase dashboard", "add card to dashboard", "run metabase query", mentions "metabase dashboards", "metabase cards", or needs to manage Metabase content via CLI.

This skill should be used when the user asks to "write documentation", "create a proposal", "draft technical spec", "write decision doc", "create structured content", "co-author documentation", mentions "writing docs", "creating proposals", "drafting specs", or needs to efficiently transfer context and refine content through a structured collaborative workflow.

This skill should be used when the user asks about "continuous improvement", "avoid over-engineering", "simplest solution", "YAGNI", "incremental improvements", "error proofing", "poka-yoke", "premature optimization", "iterative development", "make invalid states unrepresentable", "fail fast", "standardized work patterns", or needs guidance on applying kaizen principles including continuous improvement, error-proofing by design (poka-yoke), following established patterns, and building just-in-time (JIT) without premature abstraction or optimization.

This skill should be used when the user asks about "clean architecture", "domain driven design", "DDD", "should I use a library or write custom code", "library vs custom implementation", "avoid utils/helpers folders", "separation of concerns", "bounded contexts", "architecture best practices", "code organization patterns", "anti-patterns to avoid", requests architectural review, or wants guidance on structuring code following DDD and Clean Architecture principles with library-first approach.

This skill should be used when the user asks to "configure cron", "set up systemd service", "create systemd timer", "use .d directories", "set up sudoers", "configure sysctl", "manage system configs", "set up logging with journald", "create drop-in configs", "use systemd overrides", or works with Debian/Ubuntu system administration tasks involving cron.d, systemd units, sudoers.d, apt sources, and other modular configuration directories following modern Linux best practices.

This skill should be used when the user asks to "write README", "create README", "update README", "generate README", "improve README", "rewrite README", "create project documentation", or needs to create human-focused README.md files following current best practices with proper structure, quick start sections, and appropriate content organization based on project type (CLI tool, library, web app, full-stack).

This skill should be used when the user asks to "create a changelog", "generate changelog", "write release notes", "create release notes", "generate changelog from commits", "create changelog from git history", "summarize commits", "create changelog for version", "generate changelog since last release", "create changelog from past week/month", or needs to transform git commit history into user-friendly changelog entries for customers, product updates, or app store submissions.

This skill should be used when the user asks to "create a release", "bump version", "update changelog", "follow conventional commits", "semantic versioning", "commit with conventional format", "prepare a release", "create release notes", "tag a version", mentions "Keep a Changelog", or needs guidance on git workflow standards, conventional commit types (feat:, fix:, chore:, docs:), semantic version bumps (MAJOR.MINOR.PATCH), CHANGELOG.md format, or GitHub release creation with gh CLI.

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 "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 "configure OpenCode", "change default model", "add custom provider", "set baseURL for OpenCode", "configure Z.AI Coding Plan", "fix model selection issues", "set up opencode.json", "configure OpenAI-compatible provider", "troubleshoot OpenCode models", or needs guidance on OpenCode CLI configuration including provider setup, model selection, and config file structure.

This skill should be used when the user asks to "analyze meeting transcripts", "review my communication patterns", "tell me when I avoided conflict", "analyze my speaking ratio", "identify filler words in meetings", "review my facilitation style", "track communication improvement", "analyze leadership patterns", or mentions analyzing recordings from Granola, Zoom, Google Meet, or other transcription services. Uncovers behavioral patterns like conflict avoidance, interruptions, filler words, and listening effectiveness from meeting transcripts.

This skill should be used when the user asks to "create React artifact", "build complex artifact", "use shadcn/ui", "create multi-component artifact", "build dashboard artifact", "create interactive app", "use Tailwind CSS artifact", "bundle React to single HTML", mentions "artifact with state management", "artifact with routing", or needs to build elaborate, multi-component claude.ai HTML artifacts using React 18, TypeScript, Vite, Tailwind CSS, and shadcn/ui. Not for simple single-file HTML/JSX artifacts.

This skill should be used when the user asks to "review my UI", "check accessibility", "audit design", "review UX", "check against Web Interface Guidelines", "review my site", "check best practices", "audit web interface", "review frontend code", "check UI compliance", or needs to review UI code for compliance with Vercel's Web Interface Guidelines covering accessibility, performance, semantic HTML, ARIA patterns, responsive design, and modern web best practices.

This skill should be used when working with GitHub CLI (gh) for pull requests, issues, releases, and GitHub automation. Use when users mention gh commands, GitHub workflows, PR operations, issue management, or GitHub API access. Essential for understanding gh's mental model, command structure, and integration with git workflows.