MCP App StoreMCP App Store
de ai-factory921
Génère des Agent Skills et des packages de compétences prêts pour la production (SKILL.md, scripts, références, modèles) selon la spécification Agent Skills ; inclut l'analyse de sécurité
AI Factory: Skill Generator crée des packages Agent Skill complets et conformes aux spécifications. Il synthétise des fichiers SKILL.md, gère les références, les scripts et les modèles, et impose des vérifications de structure et de sécurité afin que les compétences générées soient déployables et auditables. Il fournit également des flux de validation et d'analyse de sécurité à deux niveaux pour détecter les injections de prompts et autres risques.
Utilisez cette compétence pour rédiger un nouvel Agent Skill, convertir des URL ou des documents en un package de compétences réutilisable (Learn Mode), ou valider/analyser des répertoires SKILL.md existants avant l'installation. Utile également pour générer des modèles et imposer des overrides de contexte de compétence spécifiques au projet.
Conçu pour les outils de développement et les environnements multi-agents (Claude Code, Codex, agents de type Copilot). Il s'intègre aux scanners basés sur Python et aux outils CLI pour la validation locale.
Well-structured Agent Skill generator and security scanner. The SKILL.md is comprehensive with clear workflows for skill creation, security scanning, validation, and learn mode. Scripts are defensive security tools (pattern-based scanner, cleanup helper, validator, skills.sh search). All 4 scripts exited with usage errors when run without arguments, which is expected behavior for CLI tools. No security concerns — the scripts are themselves security utilities with proper input validation and path traversal protections.
This is a legitimate, well-built skill for generating and security-scanning Agent Skills. The SKILL.md is thorough (security scanning workflow, anti-manipulation rules, validation). Scripts have proper argument parsing, error handling, and exit codes. The security scanner patterns look for malicious content — the regex patterns matching 'rm -rf', 'curl | bash', etc. are detection rules, not instructions to execute them. No hardcoded credentials, no data exfiltration, no destructive commands.
Development Worktree
Create an isolated git worktree for feature work, auto-run project setup, and verify a clean test baseline before development.
Readwise Reader Document Management
Manage Readwise Reader documents: list, save, search, move, tag, highlight, export and bulk-edit via official and custom CLIs.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Junshi — Research Advisor
Daily strategic research advisor that scans arXiv/venues, digests papers, and proposes bold, ranked research ideas tailored to the user's profile.
TradeOS
Natural-language driven CEX trading and portfolio management for agents: API key vaulting, multi-exchange orders, DCA, arbitrage scanning, alerts and security r
Full Stack Builder
End-to-end builder that scaffolds, implements, tests, and optionally deploys web and API applications from a natural-language specification.
ezBookkeeping API Tools
Command-line API tools for ezBookkeeping: record and query transactions, retrieve accounts/categories/tags, and fetch exchange rates for self-hosted personal fi
Feishu Voice Sender
Convert MP3s and send them as native Feishu voice messages (playable voice clips) to users or groups.
