Optimize, fill, and publish a stronger Capafy listing with better copy, policy links, logo direction, pricing, and readback checks.
Evidence-driven intelligence for finding the right Capafy Skills, uncovering what developers should build next, and matching buyers with solutions that truly meet their needs.
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.
Turn any prompt into a consistent, accessible UI — not just a pretty one. UI UX Pro Max equips your coding agent with a curated design-reasoning layer: proven UI styles, color palettes, font pairings, and 99 UX and accessibility guidelines, applied automatically across React, Next.js, Vue, Svelte, Tailwind, Flutter, SwiftUI, and more. Plan layouts, generate production-ready components, and ship — without leaving your editor, without a separate design tool.
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.
⚠ INDEPENDENT TOOL — NOT AN OFFICIAL CAPAFY PRODUCT. Not operated by, endorsed by, or affiliated with Capafy. You are responsible for reviewing the package contents, credentials, pricing, and final Submit-for-Review details before submitting. This helper wraps the publicly-documented publisher CLI and walks the standard web-form checkpoints via a headless browser, so you can repeat the public submission flow for a local agent skill. Operator approval is required at the pricing and submit gates.
Turn a rough skill idea into a structured blueprint: named, prompted, differentiated, and listing-ready.
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。
Turn prompts or workflows into testable, launch-ready AI Skill products.