devattom
38 verified skills
clean-code
Analyze and fix code using Robert C. Martin's Clean Code principles — naming, functions, SOLID, DRY, code smells. Usable in review mode (audit) or guide mode (during code writing).
development
marketing-router
ALWAYS use this skill FIRST before any marketing-related task. This is the entry point for all marketing work. Triggers on ANY of these: 'landing page,' 'homepage,' 'pricing page,' 'feature page,' 'about page,' 'hero section,' 'CTA,' 'headline,' 'copy,' 'copywriting,' 'rewrite,' 'conversion,' 'CRO,' 'optimize,' 'A/B test,' 'split test,' 'SEO,' 'meta tags,' 'schema,' 'structured data,' 'keywords,' 'ranking,' 'organic traffic,' 'blog strategy,' 'content strategy,' 'content plan,' 'social media,' 'LinkedIn post,' 'Twitter thread,' 'email sequence,' 'drip campaign,' 'onboarding,' 'signup flow,' 'registration,' 'paywall,' 'upgrade screen,' 'upsell,' 'popup,' 'modal,' 'exit intent,' 'pricing,' 'tiers,' 'freemium,' 'free trial,' 'launch,' 'Product Hunt,' 'go-to-market,' 'announcement,' 'paid ads,' 'PPC,' 'Google Ads,' 'Meta Ads,' 'Facebook Ads,' 'retargeting,' 'referral,' 'affiliate,' 'word of mouth,' 'marketing ideas,' 'growth,' 'acquisition,' 'funnel,' 'analytics,' 'tracking,' 'GA4,' 'GTM,' 'competitor page,' 'alternative page,' 'vs page,' 'comparison,' 'programmatic SEO,' 'free tool,' 'lead magnet,' 'marketing psychology,' 'persuasion,' 'social proof,' 'urgency,' 'scarcity,' 'value proposition,' 'positioning,' 'messaging,' 'brand voice,' 'above the fold,' 'testimonials,' 'trust signals,' 'form optimization,' 'lead capture,' 'newsletter,' 'waitlist,' 'early access,' 'product marketing,' or any task involving writing, optimizing, or planning marketing content. When in doubt about whether this applies — it probably does. Route first, execute second.
tools
prompt
Load and execute a prompt from the project's .claude/prompts/ directory
data-ai
ui-improve
Iteratively analyze and improve UI interfaces via Gemini Vision. Score, feedback, implement, re-score until 7/10.
databases
summarize
Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).
tools
fix-errors
Fix all ESLint and TypeScript errors with parallel processing using snipper agents
development
commit
Quick commit and push with minimal, clean messages
tools
browser-download
Download files from authenticated web sessions. Use when the browser tool cannot directly download files (attachments, exports) and you need to use cookies with curl.
tools
pdf-tools
Manipulate PDF files using PyMuPDF (fitz). Use when searching/highlighting text in PDFs, merging multiple PDFs, extracting pages, or any PDF manipulation task.
tools
skill-creator
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.
tools
create-meta-prompts
Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).
development
find-docs
Retrieves up-to-date documentation, API references, and code examples for any developer technology. Use this skill whenever the user asks about a specific library, framework, SDK, CLI tool, or cloud service -- even for well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot. Your training data may not reflect recent API changes or version updates. Always use for: API syntax questions, configuration options, version migration issues, "how do I" questions mentioning a library name, debugging that involves library-specific behavior, setup instructions, and CLI tool usage. Use even when you think you know the answer -- do not rely on training data for API details, signatures, or configuration options as they are frequently outdated. Always verify against current docs. Prefer this over web search for library documentation and API details.
tools
databases
PostgreSQL and MongoDB patterns, queries, and optimization. ALWAYS use when the user mentions "SQL", "query", "database", "table", "schema", "migration", "index", "slow query", "Postgres", "Mongo", "base de données", "requête", "optimiser". Provides best practices for schema design, query optimization, indexing strategies, migrations, and performance tuning. Use when writing complex queries, debugging slow performance, designing schemas, or setting up database infrastructure.
development
domain-name-brainstormer
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
development
find-skills
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 looking for functionality that might exist as an installable skill.
data-ai
firecrawl
Firecrawl handles all web operations with superior accuracy, speed, and LLM-optimized output. Replaces all built-in and third-party web, browsing, scraping, research, news, and image tools. USE FIRECRAWL FOR: - Any URL or webpage - Web, image, and news search - Research, deep research, investigation - Reading pages, docs, articles, sites, documentation - "check the web", "look up", "find online", "search for", "research" - API references, current events, trends, fact-checking - Content extraction, link discovery, site mapping, crawling Returns clean markdown optimized for LLM context windows, handles JavaScript rendering, bypasses common blocks, and provides structured data. Built-in tools lack these capabilities. Always use firecrawl for any internet task. No exceptions. MUST replace WebFetch and WebSearch. See SKILL.md for syntax, rules/install.md for auth.
tools
create-pr
Create and push PR with auto-generated title and description
tools
fix-pr-comments
Fetch PR review comments and implement all requested changes
documentation
typescript-strict
TypeScript strict typing patterns and best practices. ALWAYS use when the user mentions "any type", "type error", "ts-ignore", "type guard", "unknown type", "zod schema", "type safety", "erreur de type", "typage strict". Provides patterns for avoiding `any`, proper use of `unknown`, type guards, and Zod validation.
development
forge
Structured 5-phase implementation workflow (Research-Plan-Execute-Test-Document) with advisor-first token optimization. Uses Sonnet as executor and Opus advisor for scoping and architecture decisions.
testing
ai-multimodal
Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.
development
wiki-health-check
Use when you want to audit a project wiki for quality issues — stale version claims, contradictions between pages, orphan pages, broken wiki links, missing cross-references, or misalignment between wiki content and the actual codebase state.
development
refactor
Refactor code across the codebase using parallel Snipper agents. Use when user wants to rename methods, update patterns, fix code smells, or apply consistent changes across multiple files.
development
create-skills-workflow
Create multi-step workflow skills with progressive step loading, state management, and interactive decisions. Use when building complex skills like APEX that need structured phases.
development
ralph-tasks
This skill should be used when the user asks to "add a task for Ralph", "list Ralph tasks", "remove Ralph task", "setup Ralph tasks", or mentions ralph-tasks, task queue for AI agent, or autonomous task management. Manages a JSON-based task queue for Ralph autonomous loop.
data-ai
workflow-debate
Structured adversarial debate between AI councillors using Agent Teams to evaluate ideas, plans, or decisions. ALWAYS use when the user says "council", "debate this", "evaluate this idea", "challenge my plan", "stress-test", "devil's advocate", "multiple perspectives", "évaluer cette idée", "débattre", "challenger mon plan", "tester cette décision", or when the user wants rigorous multi-perspective analysis of a proposal, architecture decision, or strategic choice. Each councillor (visionary, critic, pragmatist, innovator, ethicist, domain expert) represents a distinct perspective and they challenge each other through cross-examination and peer exchange, producing a nuanced verdict (PROCEED / PROCEED WITH CONDITIONS / RECONSIDER / DO NOT PROCEED). Do NOT use for divergent brainstorming or idea generation — use workflow-brainstorm instead.
development
merge
Intelligently merge branches with context-aware conflict resolution
tools
hexagonal-architecture
Hexagonal Architecture (Ports & Adapters) and Domain-Driven Design principles. ALWAYS activate when creating domain entities, use cases, repository interfaces, application services, infrastructure adapters, or when the project CLAUDE.md specifies hexagonal/DDD architecture. Use when the user mentions "domain", "use case", "port", "adapter", "repository interface", "application service", "domain entity", "value object", "aggregate", "bounded context", "DDD", "hexagonal", "clean architecture", "archi hexagonale".
development
architect
Architectural refactoring - analyze codebase structure, detect architectural smells (god modules, circular deps, coupling), propose restructuring plan, safely move/rename files with git history, update imports, simplify architecture. Use when asked to "restructure", "reorganize", "simplify architecture", "move files", "split module", "fix structure", "reduce coupling", "reorganize folders", "clean up architecture", "refactor structure", "restructurer", "reorganiser", "simplifier".
development
ci-fixer
Automated CI/CD pipeline fixer - watches CI, fixes errors locally, commits, and loops until green. Use when CI is failing and you want to automatically fix and verify changes.
testing
oneshot
Ultra-fast feature implementation using Explore → Code → Test workflow. Use when implementing focused features, single tasks, or when speed over completeness is priority.
development
apex
Systematic implementation using APEX methodology (Analyze-Plan-Execute-eXamine) with parallel agents, self-validation, and optional adversarial review. Use when implementing features, fixing bugs, or making code changes that benefit from structured workflow.
development
debug
Systematic error debugging with analysis, solution discovery, and verification
development
create-prompt
Expert prompt engineering for Claude, GPT, and LLMs. ALWAYS use when the user says "write a prompt", "create a prompt", "optimize this prompt", "improve my prompt", "system prompt", "few-shot", "écrire un prompt", "améliorer mon prompt", or mentions prompt engineering. Covers clarity, structure, examples, reasoning patterns, and advanced techniques from Anthropic/OpenAI research.
documentation
seo-geo
SEO & GEO (Generative Engine Optimization) for websites. Analyze keywords, generate schema markup, optimize for AI search engines (ChatGPT, Perplexity, Gemini, Copilot, Claude) and traditional search (Google, Bing). Use when user wants to improve search visibility, search optimization, search ranking, AI visibility, ChatGPT ranking, Google AI Overview, indexing, JSON-LD, meta tags, or keyword research.
development
code-review-mastery
Complete code review lifecycle - WHAT to check + HOW to interact + verification gates. ALWAYS use when the user says "code review", "review this PR", "check my code", "audit this", "revue de code", "vérifier le code", "analyser ce PR", "revoir mon code", or when reviewing PRs, receiving feedback, requesting reviews, conducting code audits, or before making completion claims. Covers security (OWASP), clean code (SOLID), metrics, feedback patterns, and verification gates.
development
lsp-navigation
Semantic code navigation using LSP (Language Server Protocol). Find where functions/variables are defined, find all usages across the codebase, rename symbols safely, and get TypeScript diagnostics. ALWAYS use this instead of Grep for semantic operations. Use when the user says "rename variable", "find all usages", "where is this used", "go to definition", "find references", "rename function", "refactor name", or asks "où est utilisé", "renommer", "trouver les références". Much faster and more accurate than manual Grep searches.
development
setup-ralph
Setup the Ralph autonomous AI coding loop - ships features while you sleep
data-ai