Turn prompts or workflows into testable, launch-ready AI Skill products.
Turn messy notes, prompts, chat history, SOPs, and project docs into a reusable AI agent skill. Get a clean SKILL.md, reference-file plan, privacy review, and test prompts for Claude, Codex, Capafy, or local agents.
I specialize in safe Codex skill onboarding. This Agent inspects unclear websites, repositories, archives, file trees, snippets, and marketplace listings before installation. It explains candidate skills, identifies when Codex would use them, flags obvious installation risks, and requires explicit user confirmation before anything is downloaded or added to the skill library.
"Shortform Hook Doctor is an AI assistant specialized in evaluating and prescribing high-retention video hooks, visual cues, and audio directions for TikToks, Reels, and Shorts."
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
Meta-Skill Architect is a systems-engineering framework that transforms ideas into production-ready AI skills. It combines prompt engineering, software architecture, quality assurance, knowledge management, and validation workflows to create scalable, reusable, marketplace-ready skill packages with high reliability, traceability, and triggering accuracy.
Turn a rough skill idea into a structured blueprint: named, prompted, differentiated, and listing-ready.
Build review-ready Capafy Skills from idea to submission. This independent publisher assistant designs the architecture, writes SKILL.md and Agent Card content, applies sector guardrails, plans integrations and data disclosures, recommends monetization and pricing, creates test criteria and brand assets, validates the package, and prepares runtime and submission ZIPs. Not affiliated with or endorsed by Capafy.
このSkillは、Claude Code / Codex / OpenClaw 向けのAIエージェント用Skillを多数設計・公開してきた実務知見を落とし込んだものです。よくある失敗（ホスト側でSkillが発火しない description、権限を広く取りすぎたサブエージェント、シークレットの直書き、プロンプトインジェクションへの無防備さ）を体系化し、再現可能な作成フローとして提供します。貼られた情報だけを使い、不明点は[FILL IN]として創作しません。出力に対して、シークレット漏えい・過剰権限・外部送信・インジェクション面のセルフ監査を行い、公開前に是正できるようにしています。個人情報は扱いません。