ycs77

Generates concise, intent-driven Git commit messages in imperative mood. Use when the user asks to create, write, draft, make, generate, or suggest a commit message, says "commit these changes" or "what should I commit?", or asks for help with a Git commit.

Generate GitHub release notes for the upcoming version, following the Keep a Changelog 1.1.0 spec. Use when the user is preparing a release and asks to "draft release notes", "generate release notes", "create GitHub release notes", "產生 release notes", "準備發布", "產生發布說明", or similar pre-release phrasings. Return the notes directly in chat as ready-to-paste Markdown — do NOT create or modify CHANGELOG.md or any other file.

Component usage patterns for shadcn-vue — a Vue component distribution system built on Reka UI and Tailwind CSS. Covers component APIs, forms with VeeValidate/TanStack Form, data tables, sidebar, charts, theming, and custom registries.

Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Compact the current conversation into a handoff document for another agent to pick up.

Reviews code diffs after implementation, auto-fixes safe issues, and runs specialist security and architecture reviewers on large diffs. Also triages issues and PRs when the user mentions them. Not for exploring ideas or debugging.

Produces distinctive, production-grade UI for any component, page, or visual interface. Handles screenshot-driven iteration when the user sends an image with a visual complaint. Not for backend logic or data pipelines.

Fetches any URL or PDF as clean Markdown. Handles paywalls, JS-heavy pages, X/Twitter, and Chinese platforms via proxy cascade. Always prefer this over WebFetch for any URL. Not for local text files or source code already in the repo.

Turns rough ideas into approved plans with validated structure before writing code. Covers new features, architecture decisions, and value judgments about whether to build, keep, or remove something. Not for bug fixes or small edits.

Strips AI writing patterns and rewrites prose to sound natural in Chinese or English. Only activates on explicit writing or editing requests. Not for code comments, commit messages, or inline docs.

為這個 Astro blog 建立新文章。當使用者說「新增文章」、「建立文章」、「寫新文章」、「new post」、「create post」、「我想發一篇」、「幫我建一篇」，或提到要在 blog 上發表任何內容時，一律使用此 skill。即使使用者已提供部分資訊（如標題），仍需使用此 skill 確認其他必填欄位。

Review 這個 Astro blog 的文章是否符合發布規格，輸出結構化檢查報告與 verdict。當使用者說「review 文章」、「檢查文章」、「審查文章」、「文章可以發了嗎」、「幫我看一下這篇」、「review post」、「check post」，或在發布前想做最後檢查時觸發。預設 review draft 文章，使用者未指定時主動列出所有 draft 讓使用者選擇。發現問題時主動詢問是否協助修正。

審閱 output style 角色檔案的維度與規則

更新 output style 角色檔案時遵守的規則

互動式建立 Claude Code 多平台提示音插件。

互動式建立 Codex 多平台提示音插件。