コーディング用スラッシュコマンド早見表

定義元の説明: 不明点や意思決定が必要なとき、利用可能なら AskQuestion で選択肢・推奨度（⭐5段階）・理由をセットで提示する。 ツールが使えない環境では Markdown リストにフォールバックする。 仕様検討、ライブラリ選定、実装方針の確認、曖昧な要求の明確化時に使用する。 推奨度付き選択肢、推奨度と理由付きで聞いて、などの依頼時にも適用する。
(cursor/skills/recommended-options/SKILL.md)

定義元の説明: プロジェクトの現状の実装仕様を docs/SPEC.md にまとめる・更新する。全ファイル読み直しはせず前回更新以降の git 差分だけ読んで追記。「現状の実装仕様をまとめて」「今実装してる内容を教えて」「仕様書更新して」で起動。
(claude/skills/spec-summary/SKILL.md)

定義元の説明: コードベースをシニアソフトウェアアーキテクトとして分析し、実態に基づいて AGENTS.md を生成する。 プロジェクトルールの初期化、/init、AGENTS.md の作成・更新、エージェント指示のセットアップ時に使用する。
(cursor/skills/init/SKILL.md)

定義元の説明: Use /onboard for a focused Cursor onboarding flow that learns basic preferences, picks a first goal, and routes the user to the right next action.
(cursor/skills-cursor/onboard/SKILL.md)

定義元の説明: 作業の中断・再開の引き継ぎを docs/HANDOFF.md に記録・参照する（完了したこと/次にやること/気になっていることの3点）。「一旦中断」「ここまでで引き継ぎ書いて」（書き出し）、「続きから」「HANDOFF読んで再開」（再開）で起動。
(claude/skills/handoff/SKILL.md)

定義元の説明: Review code changes with the Bugbot or Security Review subagent.
(cursor/skills-cursor/review/SKILL.md)

定義元の説明: プロジェクト全体のコードをレビューし、バグ・セキュリティ・パフォーマンス・保守性・可読性・SEO・命名規則・エラーハンドリング・各言語/フレームワーク/ライブラリのベストプラクティス観点で問題点を抽出する。各問題は番号・対応優先度・問題箇所・問題点・修正対応案・AI修正用プロンプトの形式でMarkdownファイルに出力する。コードレビューを依頼されたとき、/coding-review 実行時、部下やメンバーのコードをチェックしたいときに使用する。
(cursor/skills/coding-review/SKILL.md)

定義元の説明: Use this skill when the user asks to review frontend code or a pull request, or asks about problems in the code. Triggers include 「レビューして」「PRを見て」「コードチェック」「コードの問題を教えて」 「pull requestを確認して」. Produces priority-tagged feedback covering HTML semantics, CSS design, TypeScript/React patterns, security, and general code quality. Defers deep a11y / SEO / performance audits to the dedicated agents (`sa-a11y`, `sa-seo`, `sa-performance`).
(cursor/skills/frontend-code-review/SKILL.md)

定義元の説明: 生成物（コード・ドキュメント）に対し、レビューと改善を最大3回反復する。 /self-review 実行時、セルフレビュー反復、レビューと改善を3回、 実装後の品質向上、ドキュメントの仕上げ時に使用する。
(cursor/skills/self-review/SKILL.md)

定義元の説明: Review code changes with Bugbot subagent.
(cursor/skills-cursor/review-bugbot/SKILL.md)

定義元の説明: Review code changes with Security Review subagent.
(cursor/skills-cursor/review-security/SKILL.md)

定義元の説明: src/配下の全JSファイルからconsole.*を一括削除（sedで処理しトークン消費を最小化）
(claude/skills/remove-console/SKILL.md)

定義元の説明: config.json 等の設定値と実装コードの整合を検査する（未参照キー・ハードコード値・アセット実在確認）。深刻度別にレポートし修正は提案のみ。「configと実装の整合をチェックして」「設定値が反映されてるか確認して」で起動。
(claude/skills/config-audit/SKILL.md)

定義元の説明: 生成物（コード・ドキュメント）に対し、レビューと改善を最大3回反復する。 /self-review 実行時、セルフレビュー反復、レビューと改善を3回、 実装後の品質向上、ドキュメントの仕上げ時に使用する。
(cursor/skills/self-review/SKILL.md)

定義元の説明: iOS/Android/8th Wall 等の実機固有の不具合をトリアージする（OSバージョン差、AR/カメラ・トラッキング不安定等）。既知事例と照合しWeb検索で仕様変更を確認、原因仮説を推奨度付きで提示。「iOSでこのエラーが出る」「実機で〜がおかしい」「ARが不安定」で起動。
(claude/skills/device-debug/SKILL.md)

定義元の説明: Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.
(claude/skills/web-perf/SKILL.md)

定義元の説明: Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.
(cursor/skills/web-perf/SKILL.md)

定義元の説明: Use this skill when the user asks about web performance, Core Web Vitals, slow pages, bundle size, or rendering optimization. Triggers include 「パフォーマンス」「遅い」「最適化」「LCP」「CLS」「INP」「Lighthouse」 「Core Web Vitals」「バンドルサイズ」「再レンダリング」. Measures with Lighthouse CLI and reports targeted fix suggestions per metric (does not modify files unless the user explicitly asks).
(cursor/skills/performance-audit/SKILL.md)

定義元の説明: Use this skill when the user asks to verify responsive design, check breakpoints, or compare layouts across devices. Triggers include 「レスポンシブ確認」「ブレークポイント」「スマホ表示」「タブレット崩れ」 「複数デバイスでスクショ」「Figma と比較」. Takes Playwright screenshots across defined breakpoints and flags overflow, tap target, and viewport issues.
(cursor/skills/responsive-check/SKILL.md)

定義元の説明: Use this skill when the user asks to audit, check, or fix accessibility (a11y) issues. Triggers include「アクセシビリティ」「a11y」「スクリーンリーダー」「WCAG」 「aria」「コントラスト比」「キーボード操作」「tab 操作」. Runs automated detection via axe-core and guides manual remediation following WCAG 2.1 AA. Design-time rules (semantic HTML, ARIA, forms) live in `.cursor/rules/accessibility.mdc`.
(cursor/skills/a11y-check/SKILL.md)

定義元の説明: Use this skill when the user asks to optimize images, generate responsive image markup, or convert formats. Triggers include「画像最適化」「WebP」 「AVIF」「srcset」「<picture>」「画像圧縮」「画像サイズを小さく」. Produces modern markup (<picture>, srcset, sizes, fetchpriority) and guides batch conversion with sharp or squoosh-cli.
(cursor/skills/image-optimization/SKILL.md)

定義元の説明: Use this skill when the user asks about SEO, meta tags, OGP, structured data, sitemaps, canonicals, or social sharing previews. Triggers include 「SEO」「メタタグ」「OGP」「構造化データ」「JSON-LD」「sitemap」「canonical」 「シェア画像」「検索結果」. Audits meta, OGP/Twitter Cards, schema.org JSON-LD, canonicals, sitemap.xml, and robots.txt following current Google guidance.
(cursor/skills/seo-audit/SKILL.md)

定義元の説明: Use this skill when the user asks to generate, scaffold, or create a React UI component in TypeScript (.tsx). Triggers include 「React コンポーネントを作って」「UIパーツを実装して」「tsx ファイルを新規作成して」 「このデザインをコンポーネント化して」. DO NOT use for Vue (.vue) or Astro (.astro) components. Ensures design tokens, accessibility, and project conventions are applied automatically.
(cursor/skills/react-component-generator/SKILL.md)

定義元の説明: Use this skill when the user asks to generate, scaffold, or create an Astro component (.astro). Triggers include「Astro コンポーネントを作って」「.astro を作成」 「セクションをコンポーネント化」（Astro プロジェクトで）. DO NOT use for React (.tsx) or Vue (.vue). Produces JS-zero static components by default, with island directives only when interactivity is required.
(cursor/skills/astro-component-generator/SKILL.md)

定義元の説明: Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.
(cursor/skills-cursor/split-to-prs/SKILL.md)

定義元の説明: Use this skill when the user asks to commit changes or create a pull request. Triggers include「コミット」「commit」「PRを作って」「プルリクエスト」 「コミットメッセージ」「git commit」「変更をコミットして」. Generates Conventional Commits style messages and PR descriptions based on the project's standard template.
(cursor/skills/pr-commit-style/SKILL.md)

定義元の説明: Use this skill when the user asks about deployment, release, or final pre-delivery checks for a website. Triggers include「納品前チェック」 「リリース前」「公開前確認」「本番デプロイ」「ステージングから本番」 「リリースチェック」. Runs a comprehensive pre-deployment checklist covering SEO, performance, a11y, links, analytics, and WordPress/CMS gotchas.
(cursor/skills/deploy-checklist/SKILL.md)

定義元の説明: 直近の作業からナレッジ記録候補を判定し、自動でVaultへ記録して事後報告する（AGENTS.md §3.3）
(claude/commands/kv-note.md)

定義元の説明: Vaultの肥大化を点検し、蒸留（archive）候補とMOC化候補を提案する（AGENTS.md §4）
(claude/commands/kv-distill.md)

定義元の説明: 直近のコード差分からHTML/CSS/SCSS・JS/TSの書き方の癖を分析し、確認の上でコーディングスタイルプロファイルノートに記録する
(claude/commands/kv-style.md)

定義元の説明: ナレッジVaultのデイリーノートを作成・更新する。Git履歴の自動集計に加え、その日の差分からAI要約と関連ナレッジリンクを自動生成する。「デイリーノート作って」「今日のlog」「昨日まとめて」「この日まとめて」で起動。「直近1週間で漏れがないかチェックして」「先週分の要約漏れ埋めて」などは漏れチェックモードで起動。
(claude/skills/daily-note/SKILL.md)

定義元の説明: 直近の作業内容から、`~/knowledge-vault/AGENTS.md` §3.3 の記録フロー（自動記録+事後報告）を実行する。
(cursor/commands/kv-note.md)

定義元の説明: `~/knowledge-vault/scripts/check-bloat.sh` を実行し、結果から次を提案する。
(cursor/commands/kv-distill.md)

定義元の説明: ナレッジVault（~/knowledge-vault/）のデイリーノート（daily/YYYY-MM-DD.md）を作成・更新する。Git履歴の自動集計に加えて、AIがその日の差分を読んで「まとめ（AI要約）」と「関連ナレッジ」リンクを埋める。「デイリーノート作って」「今日のlog」「昨日まとめて」「この日まとめて」「〇〇日の作業まとめて」などで起動。「直近1週間で漏れがないかチェックして」「先週分の要約漏れ埋めて」などは漏れチェックモードで起動。
(cursor/skills/daily-note/SKILL.md)

定義元の説明: Claude Code（.claude/rules/*.md）と Cursor（.cursor/rules/*.mdc）のルール差異をチェックし同期する。ルール編集後、または「.claude と .cursor のルールを比較／同期して」で起動。
(claude/skills/check-rule-sync/SKILL.md)

定義元の説明: Create Cursor rules for persistent AI guidance. Use when you want to create a rule, add coding standards, set up project conventions, configure file-specific patterns, create RULE.md files, or asks about .cursor/rules/ or AGENTS.md.
(cursor/skills-cursor/create-rule/SKILL.md)

定義元の説明: Create Cursor Agent Skills. Use when authoring a new skill or asking about SKILL.md structure.
(cursor/skills-cursor/create-skill/SKILL.md)

定義元の説明: Create Cursor hooks. Use when you want to create a hook, write hooks.json, add hook scripts, or automate behavior around agent events.
(cursor/skills-cursor/create-hook/SKILL.md)

定義元の説明: Create custom subagents for specialized AI tasks. Use when you want to create a new type of subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with custom prompts.
(cursor/skills-cursor/create-subagent/SKILL.md)

定義元の説明: Modify Cursor/VSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.
(cursor/skills-cursor/update-cursor-settings/SKILL.md)

定義元の説明: View and modify Cursor CLI configuration settings in ~/.cursor/cli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.
(cursor/skills-cursor/update-cli-config/SKILL.md)

定義元の説明: Configure a custom status line in the CLI. Use when the user mentions status line, statusline, statusLine, CLI status bar, prompt footer customization, or wants to add session context above the prompt.
(cursor/skills-cursor/statusline/SKILL.md)

定義元の説明: Run a prompt or skill in this session on a recurring or variable interval (e.g. /loop 5m /foo).
(cursor/skills-cursor/loop/SKILL.md)

定義元の説明: Keep a PR merge-ready by triaging comments, resolving clear conflicts, and fixing CI in a loop.
(cursor/skills-cursor/babysit/SKILL.md)

定義元の説明: Use this skill to create Cursor Automations.
(cursor/skills-cursor/automate/SKILL.md)

定義元の説明: Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.
(claude/skills/defuddle/SKILL.md)

定義元の説明: Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.
(cursor/skills/defuddle/SKILL.md)

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://code.claude.com/docs/en/commands

定義: https://cursor.com/docs/cli/reference/slash-commands

定義: https://cursor.com/docs/cli/reference/slash-commands

定義: https://cursor.com/docs/cli/reference/slash-commands

定義: https://cursor.com/docs/cli/reference/slash-commands

定義: https://cursor.com/docs/cli/reference/slash-commands

定義: https://cursor.com/docs/cli/reference/slash-commands

定義: https://cursor.com/docs/cli/reference/slash-commands

定義: https://cursor.com/docs/cli/reference/slash-commands

定義: https://cursor.com/docs/cli/reference/slash-commands

定義: https://cursor.com/docs/cli/reference/slash-commands

定義: https://cursor.com/docs/cli/reference/slash-commands

定義: https://cursor.com/docs/cli/reference/slash-commands

定義: https://cursor.com/docs/cli/reference/slash-commands

定義: https://cursor.com/docs/cli/reference/slash-commands

定義元の説明: A Cursor Canvas is a live React app that the user can open beside the chat. You MUST use a canvas when the agent produces a standalone analytical artifact — quantitative analyses, billing investigations, security audits, architecture reviews, data-heavy content, timelines, charts, tables, interactive explorations, repeatable tools, or any response that benefits from visual layout. Especially prefer a canvas when presenting results from MCP tools (Datadog, Databricks, Linear, Sentry, Slack, etc.) where the data is the deliverable — render it in a rich canvas rather than dumping it into a markdown table or code block. If you catch yourself about to write a markdown table, stop and use a canvas instead. You MUST also read this skill whenever you create, edit, or debug any .canvas.tsx file.
(cursor/skills-cursor/canvas/SKILL.md)

定義元の説明: Guide users building apps, scripts, CI pipelines, or automations on top of the Cursor SDK - TypeScript (`@cursor/sdk`) or Python (`cursor-sdk` / `cursor_sdk`). Use when the user mentions integrating, installing, or writing code against the Cursor SDK; says `Agent.create`, `Agent.prompt`, `Agent.resume`, `agent.send`, `run.stream`, `run.messages`, `CursorAgentError`, `@cursor/sdk`, `cursor-sdk`, or `cursor_sdk`; asks to run Cursor agents programmatically from a script, CI/CD pipeline, GitHub Action, backend service, or other code outside the Cursor IDE; wants to pick between local and cloud runtime, configure MCP servers for an SDK agent, or handle streaming, cancellation, or errors; or is wiring Cursor into an automation, bot, or REST `/v1/agents` migration. Use eagerly rather than answering from memory; the SDK surface evolves and this skill is the source of truth for the external packages.
(cursor/skills-cursor/sdk/SKILL.md)

定義元の説明: Runs the rest of a /shell request as a literal shell command. Use only when the user explicitly invokes /shell and wants the following text executed directly in the terminal.
(cursor/skills-cursor/shell/SKILL.md)

定義元の説明: Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when you want to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.
(cursor/skills-cursor/migrate-to-skills/SKILL.md)

定義元の説明: Review code changes with the Bugbot or Security Review subagent.
(cursor/skills-cursor/review/SKILL.md)

定義元の説明: Review code changes with Bugbot subagent.
(cursor/skills-cursor/review-bugbot/SKILL.md)

定義元の説明: Review code changes with Security Review subagent.
(cursor/skills-cursor/review-security/SKILL.md)

定義元の説明: Split current work into small reviewable PRs. Use when the user asks to split a chat, set of changes, branch, or PR.
(cursor/skills-cursor/split-to-prs/SKILL.md)

定義元の説明: Run a prompt or skill in this session on a recurring or variable interval (e.g. /loop 5m /foo).
(cursor/skills-cursor/loop/SKILL.md)

定義元の説明: Keep a PR merge-ready by triaging comments, resolving clear conflicts, and fixing CI in a loop.
(cursor/skills-cursor/babysit/SKILL.md)

定義元の説明: Use this skill to create Cursor Automations.
(cursor/skills-cursor/automate/SKILL.md)

定義元の説明: Use /onboard for a focused Cursor onboarding flow that learns basic preferences, picks a first goal, and routes the user to the right next action.
(cursor/skills-cursor/onboard/SKILL.md)

定義元の説明: Create Cursor rules for persistent AI guidance. Use when you want to create a rule, add coding standards, set up project conventions, configure file-specific patterns, create RULE.md files, or asks about .cursor/rules/ or AGENTS.md.
(cursor/skills-cursor/create-rule/SKILL.md)

定義元の説明: Create Cursor Agent Skills. Use when authoring a new skill or asking about SKILL.md structure.
(cursor/skills-cursor/create-skill/SKILL.md)

定義元の説明: Create Cursor hooks. Use when you want to create a hook, write hooks.json, add hook scripts, or automate behavior around agent events.
(cursor/skills-cursor/create-hook/SKILL.md)

定義元の説明: Create custom subagents for specialized AI tasks. Use when you want to create a new type of subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with custom prompts.
(cursor/skills-cursor/create-subagent/SKILL.md)

定義元の説明: Modify Cursor/VSCode user settings in settings.json. Use when you want to change editor settings, preferences, configuration, themes, font size, tab size, format on save, auto save, keybindings, or any settings.json values.
(cursor/skills-cursor/update-cursor-settings/SKILL.md)

定義元の説明: View and modify Cursor CLI configuration settings in ~/.cursor/cli-config.json. Use when the user wants to change CLI settings, configure permissions, switch approval mode, enable vim mode, toggle display options, configure sandbox, or manage any CLI preferences.
(cursor/skills-cursor/update-cli-config/SKILL.md)

定義元の説明: Configure a custom status line in the CLI. Use when the user mentions status line, statusline, statusLine, CLI status bar, prompt footer customization, or wants to add session context above the prompt.
(cursor/skills-cursor/statusline/SKILL.md)