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.
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.
Resume Polishing Agent — ATS-Optimized with Diagnostic Scoring - Build a skill that takes a resume, scores it against ATS algorithms, rewrites for impact, and returns a polished PDF-ready version.
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。
Amazon listing + marketplace-compliance expertise (2026 policy-aware): SEO title, benefit-led bullets, A+ structure, backend keywords and a banned-word/claims/trademark scan.
Product management turns a plain idea or problem into the product documents PMs actually ship: PRDs, product strategy and lean canvases, GTM plans, user personas, OKRs, roadmaps, pricing analysis, SQL queries, and competitor analysis. 66 PM skills covering discovery, strategy, execution, research, data, and growth, all from chat with nothing to install.
Turn a rough skill idea into a structured blueprint: named, prompted, differentiated, and listing-ready.
Turn video scripts into structured retention audits — map hook failures, desertion windows, and re-engagement fixes using attention psychology.
Most broken skills are not broken. They load, they validate, and they are never invoked - because the description does not match how anyone actually asks. Covers the one-character YAML mistake that makes frontmatter load empty with no error, how to write a description as a match target rather than a summary, and how to prove invocation in two steps instead of hoping.