本文件給 **AI 編碼代理**與 **自動化流程** 使用：如何在儲存庫內安全地修改、測試與回報，而不破壞擴充與 MCP 之間的契約。終端使用者請讀 [README.md](../../README.md)；架構細節請讀 [PROJECT.md](../../PROJECT.md)。
Skills（SKILL.md）は、AIエージェント（Claude Code、Cursor、Codexなど）に特定の能力を追加するための設定ファイルです。
詳しく見る →本文件給 **AI 編碼代理**與 **自動化流程** 使用：如何在儲存庫內安全地修改、測試與回報，而不破壞擴充與 MCP 之間的契約。終端使用者請讀 [README.md](../../README.md)；架構細節請讀 [PROJECT.md](../../PROJECT.md)。
Laravel Sail環境用のPlaywrightブラウザ自動化スキル。http://localhost:80を固定ベースURLとし、routes/web.phpとresources/views/を事前解析してから正確なE2Eテストを作成します。テスト成功後はtests/e2e/に自動保存。ページのテスト、フォームの入力、スクリーンショットの撮影、レスポンシブデザインの確認、UXの検証、ログインフローのテスト、リンクのチェック、あらゆるブラウザタスクの自動化に使用します。
AIフィードバックループ最適化スキル。プロンプト→出力→評価→改善の反復サイクルを自動化。段階的改善、A/Bテスト、収束判定、ベスト出力選択で最高品質の結果を生成。
FlutterアプリのE2Eテストとモバイル自動化の知見。Maestro、Mobile MCP、Dart MCPを使用したテスト作成・実行時に使用。
LME顧客にカテゴリー状況に基づいたパーソナライズメッセージを自動送信。スプレッドシート読み込み→カテゴリー分析→LME送信を完全自動化。
繰り返し作業の自動化スクリプト生成スキル。Shell、Python、PowerShell、Node.jsスクリプトを生成。ファイル操作、データ処理、API連携、CI/CD、バックアップ、監視、レポート生成を自動化。
ブラウザ拡張機能の開発を支援するスキル。Chrome (Manifest V3) と Firefox に対応したブラウザ拡張を設計・実装する。以下の状況で使用: (1) ユーザーが「ブラウザ拡張を作って」「Chrome拡張を実装して」「Firefox拡張を開発して」と依頼した時、(2) ユーザーが明示的に「/browser-ext-creator」を実行した時、(3) 特定のウェブサイトの機能拡張や自動化を求められた時、(4) content script、background script、popup UIなどの拡張機能コンポーネントの実装が必要な時
Pandocでドキュメント変換（md→docx/pptx等）を自動化する。納品形式の変換が必要な時に使う。
AI開発のベストプラクティスを体系化した10ステップの自動化ワークフローを実行します。
バグ修正統合スキル（原因調査→修正→テスト→レビュー→QA→PR作成の全工程自動化）
Google Apps Script開発スキル。GAS作成、スプレッドシート自動化、Google API連携時に使用。
git addとgit commitを自動化し、変更内容に基づいて適切なコミットメッセージを生成します。ユーザーがコミットを作成したい時、変更をコミットしたい時に使用します。
新機能開発統合スキル - 要件分析からPR作成まで、新機能開発の全工程を自動化します。analyze-requirements、develop-backend、develop-frontend、review-architecture、qa-check、create-prの各専門スキルを適切な順序で呼び出し、完全な機能開発を実現します。品質基準（テストカバレッジ80%以上、Lint/ビルド成功）を満たすまで自動的にレビュー・修正を繰り返します。
> **目的**：讓 LLM 以標準化工具介面開發與調試本專案（app.js, index.html, server_qwen.py），可在 Ubuntu 終端啟動服務、自動化瀏覽器測試、讀取 F12 Console/Network 錯誤、模擬 UI 互動、自動修復 Bug 並記錄開發進度。
You are Session Scribe, a specialized Claude skill for observing and documenting Claude Code development sessions.
DFS graph crawler + full frontend audit. Playwright crawls the live app as a graph (pages=nodes, links=edges), DFS from entry, audits EVERY reachable node: multi-breakpoint screenshots (320/768/1440/1920px), WCAG 2.1 AA (axe-core), state verification (loading/error/empty/success), dark mode, interactive states, performance (LCP/CLS/FCP), visual regression, console errors, API validation, hydration. Auth support (storageState), CI mode (exit 1 on CRITICAL, text-only), max-pages cap, crawl failure recovery. Auto-detects 7 frameworks: Next.js, Vite/React, Vue/Nuxt, SvelteKit, Astro, Remix, Angular. Actions: test, crawl, audit, screenshot, verify, scan, regress, diff. Outputs: HTML graph report, topology map, per-node pass/fail, severity-rated issues.
AI video production workflow using Remotion. Use when creating videos, short films, commercials, or motion graphics. Triggers on requests to make promotional videos, product demos, social media videos, animated explainers, or any programmatic video content. Produces polished motion graphics, not slideshows.
This skill should be used when debugging web applications, diagnosing page errors, inspecting console output, or capturing screenshots of pages. It provides Chrome DevTools Protocol (CDP) automation via the chromectl.py script for collaborative or automated browser debugging.
Launch Claude Code async in background with automatic delivery to Telegram/WhatsApp. Use for coding, refactoring, codebase research, deep research, comprehensive investigations, multi-source reports, file generation, and complex multi-step automations. NOT for quick one-off questions or real-time interactive tasks. Includes strict thread-safe routing + E2E operator validation workflow.
Create precise, programmatic animations for technical blogs, educational content, and concept visualization using Manim Community Edition (ManimCE).
Android Accessibility Service security analysis and pentesting. Use this skill whenever the user mentions Android security testing, accessibility service abuse, RAT detection, malware analysis, ClayRat, PlayPraetor, overlay phishing, credential harvesting, or any Android app security assessment involving AccessibilityService APIs. This skill helps detect malicious accessibility services, analyze abuse patterns, and harden apps against accessibility-based attacks.
>-
Direnv environment management for automatic per-project shell configuration. Use when setting up .envrc files, configuring project-specific environment variables, or integrating direnv with development tools like nix, asdf, pyenv, or nvm.
Systematic web application debugging using Chrome DevTools MCP and Playwright MCP with intelligent validation and app-specific context discovery. Use for debugging web apps, APIs, authentication flows, and UI issues.
Apply when creating or editing INFO, SPEC, IMPL, TEST, FIX documents, or STRUT plans
Scan lyrics for pronunciation risks, prevent Suno mispronunciations
Use when expanding a README-based dApp description into a full specification with user stories and acceptance criteria.
Terraform and OpenTofu infrastructure as code — module design, state management, multi-environment setups, remote backends, secrets management, CI/CD integration. NOT for Pulumi, CDK, Ansible,
**Owner:** QA
Use this skill whenever the user wants to design, run, or refine Cloudflare D1 schema management, migrations, and data seeding for dev/staging/production environments, especially in conjunction with Hono/Workers apps.
scripts/
Convert markdown planning documents to Overseer tasks via MCP codemode. Use when converting plans, specs, or design docs to trackable task hierarchies.
>
Analyze your Claude Code session logs to improve prompt quality, optimize tool usage, and become a better AI-native engineer.
Elite copywriting skill combining legendary frameworks from Eugene Schwartz, Gary Halbert, and modern conversion experts. Use for persuasive copy across all formats - sales letters, landing pages, emails, ads, VSLs. Specializes in audience awareness matching, psychological persuasion, conversion optimization, and AI-augmented workflows.
Run config-driven k6 load tests against any web application.
A CLI tool built in Rust that wraps every Google Workspace API into composable commands with structured JSON output. It dynamically builds its command structure from Google's Discovery Service, so it
Application Lifecycle Management for Power Platform. Use when: setting up CI/CD pipelines, GitHub Actions, solution deployment, environment variables, connection references, managed solutions, Power Platform Pipelines, pac solution sync, deployment settings.
Orchestrates Aspire distributed applications using the Aspire CLI for running, debugging, and managing distributed apps. USE FOR: aspire start, aspire stop, start aspire app, aspire describe, list aspire integrations, debug aspire issues, view aspire logs, add aspire resource, aspire dashboard, update aspire apphost. DO NOT USE FOR: non-Aspire .NET apps (use dotnet CLI), container-only deployments (use docker/podman), Azure deployment after local testing (use azure-deploy skill). INVOKES: Aspire CLI commands (aspire start, aspire describe, aspire otel logs, aspire docs search, aspire add), bash. FOR SINGLE OPERATIONS: Use Aspire CLI commands directly for quick resource status or doc lookups.
Use when running e2e tests, debugging test failures, or fixing flaky tests. Covers failure taxonomy, fix rules, and workflow. Never changes source code logic or API without spec backing.
Use when checking deployment health, investigating errors, reading logs, or working with Tiltfiles. Queries Tilt resource status, logs, and manages dev environments.
Interactive guided tour of all available AI coding skills with live demos. Walks through headline capabilities, offers try-it-now demos, discovers repo-specific tools, and provides a cheat sheet reference. Triggers on what can you do, show skills, skill tour, available tools, capabilities, what skills.
Expert command-line interface development including argument parsing, subcommands, interactive prompts, and CLI best practices
Expert BMAD (Breakthrough Method for Agile AI-Driven Development) implementation including role-based agent specialization, structured workflows, living artifacts, and scale-adaptive processes
Hugo template development skill for InfluxData docs-v2. Enforces proper build and runtime testing to catch template errors that build-only validation misses.
The GMSH Agent is a specialized AI module for finite element mesh generation and manipulation. It provides automated mesh generation, quality assessment, optimization, and integration with engineer...
Systematisch Dart-Treffer-Videos und Ground-Truth-Daten aufnehmen, um die Single-Cam Dart-Erkennung zu verbessern.
Generate concise, well-structured feature requirement documents for the Programming Stories Dashboard project. Use this skill whenever the user wants to plan, spec out, define, or document a new feature, enhancement, or change to the Programming Stories Dashboard — including changes to HackerNewsScraperService, ProgrammingStoriesApi, the Kafka pipeline, filtering logic, API endpoints, the in-memory store, or the Angular frontend integration. Trigger when the user says things like 'I want to add...', 'let's build...', 'I'm thinking of a feature...', 'write up requirements for...', or 'help me spec out...'. The output is a focused requirements doc purpose-built for handing to Claude Code in Plan mode.
MoAI-ADK's foundational principles - TRUST 5, SPEC-First TDD, delegation patterns, token optimization, progressive disclosure, modular architecture, agent catalog, command reference, and execution rules for building AI-powered development workflows
Run Playwright smoke tests for Denser blog application. Executes 15 tests (SMOKE-01 to SMOKE-15) against configurable environment (production, dev, or localhost) with retry support (max 3 attempts per failing test). Supports headed (visible browser) and headless modes. Collects artifacts (screenshots, trace.zip) on failures and generates HTML report. Use when testing blog functionality, verifying deployments, checking UI/API consistency, or when user requests smoke tests, playwright tests, or blog testing.