claude-code-skills

Run a multi-agent code review on a GitHub pull request, with parallel security / performance / architecture / style passes, inline comments, and quality-gate enforcement. Use when asked to "github code review", "review github pr", "run code review on PR", "swarm review", "automated PR review", or "post inline review comments".

Manage GitHub issues, project boards, sprints, and milestones with swarm-coordinated automation — issue triage, decomposition into subtasks, board sync, sprint planning, KPI tracking. Use when asked to "github project management", "manage github projects", "github issue automation", "swarm project board", "automate sprint", "triage issues", or "set up project board".

Extract clean article content from a URL (blog post, news article, tutorial) and save it as readable text with ads, navigation, and other clutter removed. Use when asked to "extract article", "scrape text from URL", "download blog post", "parse HTML article", "save article as text", or "clean article content from a webpage".

Dispatch one focused agent per independent problem domain so investigations run concurrently. Use when facing 2+ independent tasks with no shared state — for example "spawn agents in parallel", "parallel debugging", "fan out tasks", "investigate multiple failures at once", or "distribute independent work across agents".

Create HTML dashboards with KPI cards, bar/pie/line charts, progress indicators, and data tables. Use when asked to "create dashboard", "build KPI dashboard", "generate metrics visualization", "make analytics dashboard", "show performance dashboard", or "render data visualization as HTML".

Guide for choosing the right AI coding tool for the task. Use when user asks "which AI should I use", "should I use Claude or Cursor", "what's the best tool for X", or when helping decide between Claude Code, Cursor, Windsurf, VSCode + Copilot, Gemini, Grok, Codex, Qwen, or this Claude interface.

Patterns for connecting to external APIs like Stripe, OpenAI, Anthropic, Supabase, Replicate, and others. Use when user wants to integrate a third-party service, asks about API keys, authentication, making HTTP requests, or is troubleshooting API connection issues like CORS, 401, 403, or rate limits.

Explain code in plain English for non-technical users. Use when user asks "what does this do", "explain this code", "I don't understand this", "what is happening here", or pastes code and wants to understand it without technical jargon.

Deployment patterns for Vercel, Netlify, Replit, Firebase Hosting, Railway, Render, and Cloudflare. Use when user wants to deploy, publish, go live, host a website, or mentions these platforms. Also use when troubleshooting deployment issues like "works locally but not deployed" or environment variable problems.

Interpret error messages and fix common coding issues without technical knowledge. Use when user shares error messages, stack traces, console errors, build failures, or says things like "I got an error", "it's not working", "what does this mean", or pastes red text from their terminal or browser.

Firebase patterns and troubleshooting for vibecoders. Use when user mentions Firebase, Firestore, Firebase Auth, Firebase hosting, security rules, or is working on projects using Firebase backend. Also use for errors like "permission denied", "missing index", or authentication issues in Firebase projects.

Version control made simple for vibecoders. Use when user asks about git, commits, branches, pushing, pulling, undoing changes, merge conflicts, or says things like "save my work", "go back to before", "I messed up git", "how do I undo", or needs to collaborate on code.

Emergency recovery patterns for when vibecoding goes wrong. Use when user mentions things like "everything broke", "nothing works", "it was working before", "I messed something up", "how do I undo", "project won't start", "dependencies broken", "git is messed up", errors after updates, blank screens, infinite loops, or any situation where a project that was working is now broken.

Templates for starting new projects with common stacks. Use when user wants to "start a new project", "create an app", "build something from scratch", or asks about project setup, folder structure, or boilerplate code. Covers Next.js, React, Node.js, Python, and mobile.

Use when creating new skills, agents, or improving existing ones. Provides the 10-step systematic process for high-quality skill development.

Debate-Weighted Aggregation council for critical multi-agent decisions. Automatically triggers for security, architectural, and high-risk operations requiring expert deliberation.

Use when creating REST APIs, FastAPI endpoints, GraphQL schemas, or designing API architecture. Provides patterns for models, services, routers, and comprehensive testing.

Use when stuck on hard problems, need deeper reasoning, standard approaches fail, or facing architecture decisions. Implements 5-tier escalation from standard reasoning to external expert models.

Multi-model consensus and escalation framework for critical decisions. Activates when facing architectural choices, security decisions, or when intelligent-gate recommends escalation. Integrates with consult-llm MCP for multi-model opinions.

Decision-making framework for risky operations. Activates when PreToolUse hook triggers on potentially dangerous commands. Provides methodology for AUDIT → ASSESS → RESEARCH → THINK → DECIDE → ACT workflow.

Use when needing free, private, or fast AI assistance for support tasks like explaining code, analyzing logs, research, or drafts. Routes to local Ollama models (devstral, qwen3-coder, llama4, llama3.2) for zero-cost operations. NOT for writing/editing code - Claude handles all coding.

Generate phylogenies from genome assemblies using BUSCO/compleasm-based single-copy orthologs with scheduler-aware workflow generation

Architecture design and ADR creation pipeline stage (Spec → Design)

TDD-driven implementation pipeline stage (Design → Code)

Product requirements to user stories pipeline stage (PM → Spec)

Comprehensive testing and quality verification pipeline stage (Code → Verified)

Use when starting work on any project to load project-specific context, conventions, and patterns. Triggers on project initialization, "how does this project work", or before making changes that should follow project conventions.

Use when writing Python code. Enforces modern Python 3.11+ patterns, comprehensive type hints, async patterns, and production-ready code quality standards.

Use before claiming any task complete. Enforces verification steps, test execution, and proof of success. Prevents premature completion claims and ensures work is actually done.

Create polished, professional reveal.js presentations. Use when the user asks to create slides, a presentation, a deck, or a slideshow. Supports themes, multi-column layouts, callout boxes, code highlighting, animations, speaker notes, and custom styling. Generates HTML + CSS with no build step required.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Engages structured analysis to explore multiple perspectives and context dependencies before responding. Use when users ask confirmation-seeking questions, make leading statements, request binary choices, or when feeling inclined to quickly agree or disagree without thorough consideration.

Token-aware patterns for efficient context usage. Activates when working on long sessions, large codebases, or when context pressure is detected. Provides strategies for reducing token consumption while maintaining quality.