Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By atournayre
Run autonomous APEX workflows with parallel agents to implement features, fix bugs, merge Git branches intelligently, auto-commit/push changes, create PRs, resolve JS/TS errors via ESLint/Prettier, optimize LLM prompts, and research libraries or web facts.
npx claudepluginhub atournayre/claude-marketplace --plugin mlvnQuick commit and push with minimal, clean messages
Create and push PR with auto-generated title and description
Intelligently merge branches with context-aware conflict resolution
Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.
Fix all ESLint and TypeScript errors with parallel processing using snipper agents
Uses power tools
Uses Bash, Write, or Edit tools
Share bugs, ideas, or general feedback.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Plugin for effective agentic development
Use this agent when implementing AI/ML features, integrating language models, building recommendation systems, or adding intelligent automation to applications. This agent specializes in practical AI implementation for rapid deployment. Examples:\n\n<example>\nContext: Adding AI features to an app\nuser: "We need AI-powered content recommendations"\nassistant: "I'll implement a smart recommendation engine. Let me use the ai-engineer agent to build an ML pipeline that learns from user behavior."\n<commentary>\nRecommendation systems require careful ML implementation and continuous learning capabilities.\n</commentary>\n</example>\n\n<example>\nContext: Integrating language models\nuser: "Add an AI chatbot to help users navigate our app"\nassistant: "I'll integrate a conversational AI assistant. Let me use the ai-engineer agent to implement proper prompt engineering and response handling."\n<commentary>\nLLM integration requires expertise in prompt design, token management, and response streaming.\n</commentary>\n</example>\n\n<example>\nContext: Implementing computer vision features\nuser: "Users should be able to search products by taking a photo"\nassistant: "I'll implement visual search using computer vision. Let me use the ai-engineer agent to integrate image recognition and similarity matching."\n<commentary>\nComputer vision features require efficient processing and accurate model selection.\n</commentary>\n</example>
HelloAGENTS — The orchestration kernel that makes any AI CLI smarter. Adds intelligent routing, unified QA gates, safety guards, and notifications.
Non-technical progress summaries for Claude Code work (hides diffs/log noise).
Agentic engineering done right — 57 structured workflows, 17 specialist agent personas, persistent memory across sessions, integrated learning partner, and impeccable UI design system. Works with Claude Code, Windsurf, Cursor, Gemini CLI, OpenCode, and Codex.
Agents for UI/UX design, accessibility, and user experience optimization
Délégation Gemini CLI : contexte ultra-long (1M tokens), Deep Think, Google Search temps réel
Skills et agents utilitaires génériques : fix-grammar, action, explore-codebase
Agents spécialisés pour la code review automatique des PRs. Inclut 4 agents : code-reviewer, silent-failure-hunter, test-analyzer, git-history-reviewer.
Plugin pour atournayre/framework avec commandes et intégrations
Tests automatisés d'interface utilisateur dans Chrome : navigation, validation visuelle, tests fonctionnels et responsive
⚠️ DISCLAIMER: Ce marketplace est en cours de développement actif. Utilise-le avec précaution et n'hésite pas à remonter tout bug ou comportement inattendu via les issues GitHub.
Marketplace de plugins pour Claude Code, offrant un ensemble d'outils pour améliorer ton workflow de développement.
| Plugin | Version | Description | Documentation |
|---|---|---|---|
| 🌐 Chrome UI Test | 1.0.0 | Tests automatisés d'interface utilisateur dans Chrome (navigation, screenshots, responsive, GIF) | README |
| 🤖 Claude | 1.3.1 | Plugin de base : skill-creator, memory, make-subagent, challenge, doc-loader | README |
| 🎨 Customize | 1.1.1 | Personnalise ton expérience avec hooks, output styles, status lines + Bash Security Validator | README |
| ⚙️ Dev | 2.5.1 | Workflow 8 phases + oneshot, ralph-loop, examine step + 25 skills | README |
| 📚 Doc | 1.6.2 | Documentation : ADR, RTFM, génération docs, framework docs + 3 skills | README |
| 🏗️ Framework | 1.1.1 | Skills framework pour génération code PHP Elegant Objects | README |
| 🔮 Gemini | 1.4.2 | Délégation Gemini CLI : contexte ultra-long (1M tokens), Deep Think, Google Search + 3 skills | README |
| 🔧 Git | 1.13.0 | Workflow Git complet : branches, worktrees, commits, conflits, PR, fix-pr-comments + Task Management System | README |
| 🐙 GitHub | 1.3.2 | Gestion GitHub : issues, PR, analyse d'impact | README |
| 📱 Marketing | 1.2.2 | Génération de contenu marketing : posts LinkedIn, annonces, communications | README |
| 🎭 MLVN | 1.1.0 | Adaptation du repo AIBlueprint de Melvynx : agents spécialisés, workflows, skills Git/Meta/Utils (version épurée après migration) | README |
| 🔔 Notifications | 1.0.2 | Système de notifications avancé avec queue persistante, dispatchers multiples et gestion complète | README |
| 📝 Prompt | 2.3.0 | Système hybride Starters + Mode Plan + Checklists + Agent Teams - Templates légers, exploration contextuelle, validation automatisée, orchestration multi-agents | README |
| 📋 QA | 1.3.2 | Quality assurance : PHPStan, tests, linters | README |
| 🔍 Review | 1.0.1 | Agents spécialisés code review : code-reviewer, silent-failure-hunter, test-analyzer, git-history-reviewer | README |
| 🎯 Symfony | 1.3.2 | Plugin Symfony avec skills make, documentation et intégrations | README |
| 🛠️ Utils | 1.0.0 | Skills et agents utilitaires : fix-grammar, action, explore-codebase | README |
Certaines commandes du marketplace spécifient un output-style recommandé dans leur frontmatter pour optimiser le formatage de sortie.
Chaque commande concernée inclut un champ output-style dans son frontmatter YAML :
---
description: Génère un rapport HTML d'analyse d'impact
output-style: html-structured
---
Lors de l'exécution, Claude détecte ce champ et bascule automatiquement vers le style approprié.
| Style | Usage | Commandes |
|---|---|---|
html-structured | Rapports HTML complets | git:release-report |
markdown-focused | Documentation structurée | doc:adr, marketing:linkedin, doc:rtfm |
ultra-concise | Statuts et résumés courts | dev:status, dev:summary, git:branch |
bullet-points | Analyses et explorations | dev:explore, dev:discover, gemini:analyze, github:impact |
table-based | Comparaisons structurées | dev:design, dev:clarify |
Les output-styles sont définis dans ~/.claude/output-styles/. Claude Code les charge automatiquement au démarrage.
Pour créer un style personnalisé, crée un fichier ~/.claude/output-styles/mon-style.md :
---
name: Mon Style Custom
description: Description du style
---
Instructions de formatage pour Claude...
Le champ output-style dans le frontmatter n'est pas encore supporté nativement par Claude Code. Nous avons soumis une feature request pour ajouter ce support.
En attendant, les commandes incluent une instruction manuelle pour que Claude lise et applique le style automatiquement.
Voir : FEATURE_REQUEST.md pour les détails techniques et la proposition complète.
/plugin marketplace add atournayre/claude-marketplace
/plugin install <nom-plugin>@atournayre