Turn your real life, goals, or brand into an epic, emotionally powerful modern fable that people love to share
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.
This Codex skill turns reports, research notes, and meeting outputs into an executive-ready slide storyline with message titles, evidence mapping, visual recommendations, and speaker notes.
Join a capybara traveler in a five-scene moonlit story, follow your instincts, and reveal your Moonlight Mark, guardian collectible, and night omen.
Turn property facts into listing-ready copy in minutes. ListingCraft writes 5 headlines, 3 tone-specific descriptions (luxury, family, investor), feature bullets, SEO keywords, an open house ad, and a social caption — then screens everything for fair-housing compliance. Just describe the property; get copy you can paste straight into the MLS.
AI tool that optimizes product catalogs for marketplace listings: compliant titles, bullets, backend search terms, fact-locked claims, gap flags, and prioritization — without inventing specs or market data.
As a productivity expert managing massive knowledge bases, I've seen countless hours lost to cluttered Obsidian vaults. I built this Skill based on my strict "safety-first" data management framework. Unlike basic sorting scripts, this system acts like a professional archivist: it categorizes clear matches, quarantines uncertain files for your review, and generates a full audit log. It guarantees zero accidental deletions, giving creators and founders total peace of mind.
Audit and manage local AI Skills across Codex, Claude Code, and project workspaces. See what is actually active, detect duplicates and variants, compare changes over time, and generate an offline interactive management map. Read-only by default; every real change requires your approval.
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。