skills

Runs a cross-language cleanup for writing tells shared by large frontier LLMs, not only GPT: English source constructs that survive Korean translation and Korean-surface translationese. Triggers on de-GPT, GPT 티, AI 티, 번역체 GPT, 자폐 말투 (colloquial shorthand for rigid or over-complete model prose, not a claim about autism), or English text bound for Korean; broad Korean punctuation and spacing cleanup stays out of scope.

Prompting compliance specialist for AI agent skills — rewrites SKILL.md steps with RFC 2119 wording, explicit tools, VERIFY gates, and dry-run checks; also owns skill name + frontmatter description wording (trigger-surface rules). Use when skill steps get skipped, prompts need compliance hardening, or a skill needs naming or its description written/reviewed. Structural lifecycle work goes to skill-manager.

Transform the current project into an AI-ready codebase by migrating to AGENTS.md, setting up debugging/testing infrastructure, and creating comprehensive documentation

Skill structure and lifecycle manager — creates, edits, merges, splits, and sanitizes skills (model-reference checks against models.dev). Use for any create/update/merge/split/cleanup skill request; step wording and name/description wording go to skill-prompter.

Scaffolds one-click VS Code/Cursor debug, run, tasks, and settings configs from the codebase stack. Triggers on make project VSCode-ready, /vscode-ready.