The AI skills I actually run

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy.

Use whenever the user is stuck on, weighing, agonizing over, or needs help thinking through any significant decision — career moves, hires, fires, big purchases, relationship choices, business bets, what to build next, whether to do X or Y.

Help the user decide what's in scope for an idea by aggressively expanding it into every possible thing it COULD include, then sorting each item into one of four scope buckets (Core / Nice-to-have / Maybe-later / Out). Use this skill whenev

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is look

Use when you need multiple hook options for any piece of content. Generates 10 hooks across different psychological triggers.

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written.

Build a single-file, self-contained HTML infographic from text content, data, or article material. Use this skill whenever the user asks for an infographic, visual summary, social graphic, one-pager, lead magnet, visual explainer, or wants

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

Best practices for Remotion - Video creation in React

Create new Claude Code Skills with proper YAML frontmatter, progressive disclosure structure, and complete directory organization. Use when you need to build custom skills for specific workflows, generate skill templates, or understand the

AI Marketing Suite orchestrator. Routes all /market commands and turns a website into marketing deliverables: full audits, optimized copy, email sequences, social calendars, ad creative, funnel and landing-page CRO analysis, competitor inte

Ad creative and copy generator for /market ads <url>. Produces ad headlines, body copy, and angles for Google, Meta, LinkedIn, and more.

Full marketing audit engine for /market audit <url>. Launches 5 parallel subagents (content, conversion, competitive, technical, strategy), scores the site across 6 weighted dimensions, and produces a client-ready MARKETING-AUDIT.md.

Brand voice analysis and guidelines for /market brand <url>. Defines tone, voice, and messaging guidelines from a site.

Competitive intelligence for /market competitors <url>. Scans competitors and produces a positioning and differentiation report.

Copywriting analysis and generation for /market copy <url>. Reviews headlines, value props, and CTAs and produces optimized before/after copy.

Email sequence generator for /market emails <topic/url>. Creates welcome, nurture, and launch sequences ready to send.

Sales funnel analysis and optimization for /market funnel <url>. Maps the funnel, finds friction and drop-off, and recommends fixes.

Landing page CRO analysis for /market landing <url>. Evaluates a landing page for conversion and gives prioritized fixes.

Product launch playbook generator for /market launch <product>. Builds a step-by-step launch plan with timeline, channels, and assets.

Client proposal generator for /market proposal <client>. Produces a professional services proposal with scope, deliverables, and pricing.

Marketing report generator (Markdown) for /market report <url>. Compiles available analysis into a structured MARKETING-REPORT.md.

Professional PDF marketing report for /market report-pdf <url>. Compiles analysis into a branded MARKETING-REPORT.pdf via the bundled Python generator (needs reportlab).

SEO content audit for /market seo <url>. Reviews on-page and content SEO and gives prioritized recommendations.

Social media content calendar generator for /market social <topic/url>. Produces a 30-day posting calendar with hooks and captions across platforms.

The canonical EatCookJoy / Aziz Saif house visual theme for azizsaif.com — warm cream paper, terracotta + gold + sage accents, Playfair Display + Inter + Space Grotesk typography, editorial layout with grain overlay, pill buttons, soft card

One-click Day-1 autorun for EatCookJoy UAE. Orchestrates all six department skills (social, reviews, SEO/AEO/GEO, website tech, KPI dashboard, reel factory) to produce a full day of ready-to-ship marketing and ops output in a single run.

EatCookJoy UAE KPI dashboard and reporting agent. Pulls social, review, SEO and booking metrics into one dashboard and writes the weekly GM report to WhatsApp.

EatCookJoy UAE content & reel factory agent. Generates the week's reel ideas and 30–60s scripts (hook · value · CTA) in English and Arabic, ready for voiceover and rendering.

EatCookJoy UAE reviews and reputation agent. After every completed booking it requests feedback on WhatsApp, routes happy customers to Google and unhappy ones to private recovery, drafts AI replies, and monitors sentiment.

EatCookJoy UAE SEO / AEO / GEO agent. Runs technical SEO audits, fixes meta and JSON-LD schema, manages local citations, and tracks whether EatCookJoy appears in ChatGPT, Perplexity and Google AI answers.

EatCookJoy UAE social media manager agent. Turns approved reel scripts into platform-ready captions (English + Arabic), hashtag sets and a posting schedule for Instagram, TikTok, LinkedIn and Facebook, then logs results.

EatCookJoy UAE website technical auto-fix agent. Monitors broken links, Core Web Vitals and indexing daily, auto-fixes low-risk issues (redirects, sitemap) and raises GitHub issues for code-level problems.

Full-featured SEO, GEO, and AEO website audit tool. Analyzes any URL or website for Search Engine Optimization (SEO), Generative Engine Optimization (GEO — for AI-powered search engines like Perplexity, ChatGPT Search, and Gemini), and Answ

Comprehensive GitHub code review with AI-powered swarm coordination

Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration

Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning

Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management

Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management

SPARC (Specification, Pseudocode, Architecture, Refinement, Completion) comprehensive development methodology with multi-agent orchestration

Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows

Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems."

Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or

Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more.

Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management.

Optimize AgentDB performance with quantization (4-32x memory reduction), HNSW indexing (150x faster search), caching, and batch operations. Use when optimizing memory usage, improving search speed, or scaling to millions of vectors."

Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases."

Implement ReasoningBank adaptive learning with AgentDB's 150x faster vector database. Includes trajectory tracking, verdict judgment, memory distillation, and pattern recognition.

Implement adaptive learning with ReasoningBank for pattern recognition, strategy optimization, and continuous improvement. Use when building self-learning agents, optimizing workflows, or implementing meta-cognitive systems."

Web browser automation with AI-optimized snapshots for claude-flow agents

Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre/post task hooks, session management, Git integration, memory coordination, and neural pattern training f

AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions.

Stream-JSON chaining for multi-agent pipelines, data transformation, and sequential workflows

Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.

CLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intelligent workflow automation."

Core module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with comprehensive testing."

Domain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern."

Deep agentic-flow@alpha integration implementing ADR-001. Eliminates 10,000+ duplicate lines by building claude-flow as specialized extension rather than parallel implementation."

MCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, load balancing, tool registry optimization, and performance monitoring for sub-100ms response times."

Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend)."

Achieve aggressive v3 performance targets: 2.49x-7.47x Flash Attention speedup, 150x-12,500x search improvements, 50-75% memory reduction. Comprehensive benchmarking and optimization suite."

Complete security architecture overhaul for claude-flow v3. Addresses critical CVEs (CVE-1, CVE-2, CVE-3) and implements secure-by-default patterns.

15-agent hierarchical mesh coordination for v3 implementation. Orchestrates parallel execution across security, core, and integration domains following 10 ADRs with 14-week timeline."

Generate the week’s reels + captions (EN + AR)

Punchy hooks for the nihari campaign

Make chef-outreach & customer WhatsApp sound human

“How EatCookJoy works” social infographic

Reviews on autopilot + AI-search visibility

Decide the next move: Abu Dhabi vs deepen Dubai

Scope a new feature (e.g. subscription meal plans)

A full day of marketing + ops in one run

Stretch a long ops session’s tokens

Audit the funnel & search

Build infographics for a blog post (like the 10-skills one)

Blog titles & LinkedIn hooks

Human-sounding intros & outreach emails

Audit before shipping any site HTML/JS

Marketing & SEO audit of the site

Decide: new page vs expand an existing one

Scope a new landing/section before building

Token-saver on a big refactor

Find a skill for a new need

30-day social calendar + sharper copy