Generate Architecture Decision Records following the project template and numbering convention. Use when documenting architecture decisions, technical choices, or when the user asks to create an ADR.

Create Architecture Decision Records (ADRs) that document significant technical decisions for the Fantasy Football Analytics project following the established ADR format and workflow.

Specialized skill for generating and managing Architecture Decision Records (ADRs). Supports Nygard, MADR, and custom templates with auto-numbering, linking, and status management.

Structured frameworks for documenting architectural decisions with human-in-the-loop AI assistance.

Generate phased implementation roadmaps from Architecture Decision Records

Document architecture decisions with clear context, alternatives, and consequences.

Activate for paid advertising campaigns on Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads. Includes ad copywriting, audience targeting, budget optimization, A/B testing, and ROAS tracking. Used by ads-specialist and campaign-manager agents.

Advanced debugging skill for MyJKKN project. Specialized workflows for debugging Next.js 15, Supabase, React Query, TypeScript, and service layer issues. Includes automated analysis tools, common error patterns, and step-by-step troubleshooting guides for reducing debugging time. Use when investigating bugs, errors, performance issues, or unexpected behavior. (project)

Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.

Advanced example showing all available metadata fields and complex folder structure

Use when planning, scaffolding, validating, or packaging Claude skills inside Advanced Memory MCP.

Specialized reverse engineering analysis workflows for binary analysis, pattern recognition, and vulnerability assessment

Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree. Use when user wants to write or refine a specification document using adversarial development.

Interactive conversational guidance - user implements with step-by-step advice. Use when you want hands-on implementation with expert guidance while maintaining control.

Recruit, structure, and manage advisory boards for strategic guidance

adw-bootstrap

Cloudflare Workers and Pages deployment for Adynato projects. Covers wrangler CLI, reading logs for debugging, KV/D1/R2 storage, environment variables, and common errors. Use when deploying to Cloudflare, debugging workers, or configuring edge functions.

Mobile app development conventions for Adynato projects using React Native and Expo. Covers navigation patterns, native APIs, performance optimization, and platform-specific considerations. Use when building or modifying mobile applications.

Vercel deployment and configuration for Adynato projects. Covers environment variables, vercel.json, project linking, common errors like VERCEL_ORG_ID/VERCEL_PROJECT_ID, and CI/CD setup. Use when deploying to Vercel, configuring builds, or troubleshooting deployment issues.

Measurement framework for Answer Engine Optimization (AEO). Provides AI visibility metrics, share of voice tracking, citation monitoring, and referral demand measurement. Use when discussing AEO/GEO metrics or AI visibility performance.

Set up and manage affiliate marketing programs for growth and revenue

Mandatory knowledge capture after completing work. Documents solution in Graphiti and tracks effectiveness for system improvement.

Master orchestration patterns, multi-agent coordination, and effective workflow composition using the Agency plugin's 51+ specialized agents. Activate when planning complex implementations, coordinating multiple agents, or optimizing development workflows.

Create Claude Desktop skills from descriptions, SOPs, or existing agents. Three modes - create from scratch, convert SOPs to skills, or migrate agents to skill format. Outputs ready-to-deploy .zip packages.

>

agent-assistant

Guide for authoring specialized AI agents. Use when creating, updating, or improving agents, choosing models, defining focus areas, configuring tools, or learning agent best practices.

Canonical skills live in categorized folders below. Each tool loads skills via the flat symlink directory at `~/dev/agent-skills/skills`.

Safely sync navigator's agent-browser fork with upstream vercel-labs/agent-browser, analyze changes, and generate integration documentation

Use when creating, improving, or troubleshooting Claude Code subagents. Expert guidance on agent design, system prompts, tool access, model selection, and best practices for building specialized AI assistants.

Comprehensive documentation of Claude's capabilities for visual regression testing, CI/CD integration, and quality assurance automation. Use when setting up testing infrastructure, implementing visual regression, or understanding agent testing capabilities. (project)

>

Create Claude Code slash commands and OpenCode command files that delegate to subagents. Use when creating new commands or refactoring existing ones to follow the delegation pattern.

Agent assignment matrix, blocker escalation, and TDM coordination patterns. Use when assigning work to specialists, managing blockers, or coordinating multi-agent workflows.

Creates specialized AI agents with optimized system prompts using the official 4-phase SOP methodology from Desktop .claude-flow, combined with evidence-based prompting techniques and Claude Agent SDK implementation. Use this skill when creating production-ready agents for specific domains, workflows, or tasks requiring consistent high-quality performance with deeply embedded domain knowledge.

>

Create specialized agent experts with pre-loaded domain knowledge using the Act-Learn-Reuse pattern. Use when building domain-specific agents that maintain mental models via expertise files and self-improve prompts.

Claude Code agent generation system that creates custom agents and sub-agents with enhanced YAML frontmatter, tool access patterns, and MCP integration support following proven production patterns

Stop AI agents from secretly bypassing your rules. Mechanical enforcement with git hooks, secret detection, deployment verification, and import registries. Born from real production incidents: server crashes, token leaks, code rewrites. Works with Claude Code, Clawdbot, Cursor. Install once, enforce forever.

Generate comprehensive handoff documentation optimized for AI agent takeover by analyzing project structure, design docs, and codebase

Self-improvement loop for multi-agent workflows. Diagnose failures, improve tool descriptions, and learn from success/failure patterns.

Initialize or improve AGENTS.md files that define how coding agents operate in a repo. Use when asked to set up or replace an agent init command (Codex, Claude), standardize multi-agent behavior, or audit an existing AGENTS.md for clarity, commands, boundaries, and repo-specific context. For Claude Code, also create CLAUDE.md as a symlink to AGENTS.md.

Agent Inventor Skill

Launches specialized Claude agents for targeted tasks. Analyzes requirements, selects appropriate agent, and executes with optimized configuration.

Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.

Retain and recall work context across sessions. Use when user asks to remember something, recall previous work, or reference past discussions. Triggered by phrases like 'remember this', 'save for later', 'recall', 'what did we discuss about'.

Create .agent/baseline.md and later compare against it. Use when capturing baseline build/lint/test results or investigating newly introduced findings.

Create/update .agent/constitution.md. Use when commands/boundaries/constraints must be confirmed before baseline or code changes. Draft v0 from repo evidence, then interview user.

Create focused, specific technical documentation for codebase sections. Analyzes code, identifies topics, presents options before writing. Supports code blocks with line numbers.