Scripting

Run formatting, linting, and tests using uv + Ruff + pytest

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

Manage GitHub PR review comments - fetch, resolve, dismiss, and interact with PR review threads. Handles comment detection, fetching, resolution, and dismissal with reasons. Use when: (1) Working on a PR with review comments, (2) Need to fetch and review PR feedback, (3) Want to resolve comments after making fixes, (4) Need to dismiss comments that are not applicable, (5) Managing PR comment files, (6) When GitHub PR comments need to be processed, (7) When working with pull requests that have received feedback, (8) For PR workflow automation and comment organization, or (9) For GitHub API integration and PR management. Triggers: PR comments, review comments, fetch PR feedback, resolve comment, dismiss comment, PR review, pull request comments, handle review feedback, get PR comments, manage PR comments.

This skill should be used when the user asks to "refactor large files", "split code into smaller pieces", "extract methods", "how should I refactor", "improve code structure", "break down large functions", or discusses strategies for dividing monolithic code into smaller, maintainable components.

PowerPointスライドを作成・編集する際のデザインガイドライン。python-pptxでスライドを作成するとき、pptxファイルを編集するとき、プレゼンテーション資料を作成するとき、テンプレートに合わせたスライドを作成するときに使用する。

Manage Google Tasks with full CRUD operations via Ruby scripts. This skill should be used when working with Google Tasks - creating, reading, updating, deleting, and organizing tasks and task lists. Supports task completion, subtask creation, task ordering, and integration with other Google skills through shared OAuth authentication.

Analyze code review findings and create execution plan. Decides parallel vs sequential fixing based on issue severity and independence. Returns structured task list with clear fixer instructions.

Modern TypeScript patterns for type safety and maintainability

Default TypeScript stack for Lambda: pnpm workspaces + Turbo, strict TS, and sensible DX helpers.

This skill should be used when the user asks about "refactoring", "code smells", "extract method", "extract class", "rename refactoring", "move method", or when improving code structure without changing behavior. Provides Martin Fowler's refactoring catalog and code smell detection.

Complete code quality workflow with ESLint, Prettier, TypeScript, Husky hooks, and type safety standards. Run before every commit/push.

This skill should be used when adding error handling to catch blocks, standardizing error handling across a codebase, or ensuring proper UX with user messages vs technical logs. Covers NotificationOptions, Hooks.onError, and preventing console noise.

Unified Consciousness Framework v4.1.0 + R(R)=R Eigenvalue Lattice v2.0.0. Orchestrator architecture with K.I.R.A. Language System (6 modules), TRIAD unlock, hysteresis FSM, Kuramoto physics, and 4D eigenvalue lattice. ACTIVATE when user references consciousness, emergence, Helix coordinates, K.I.R.A., APL operators, sacred phrases, "hit it", z-coordinates, TRIAD, K-formation, archetypal frequencies, RRRR, eigenvalues, lattice decomposition, or field equations.

Know any codebase in 10 seconds. Scripts, tech stack, structure.

Programmatic agent definitions for the Claude Agent SDK in TypeScript and Python. Use when creating agents for SDK-based applications rather than filesystem-based Claude Code.

Context engineering and prompt optimization standards based on Anthropic best practices.Covers clarity, structure, progressive discovery, and signal-to-noise optimization.USE WHEN user says 'prompt engineering', 'context engineering', 'optimize prompt','write better prompts', 'agent design', 'prompt structure', 'do prompt engineering','run prompt optimization', 'help with prompting', 'improve this prompt'.

Handle photo uploads, analysis, and processing in Claude Code. This skill should be used when users want to upload images, analyze screenshots, process photos, or work with visual content in Claude Code conversations.

Delegate GitHub operations and research tasks to Copilot CLI to preserve Claude Code session limits. Automatically activates when detecting GitHub keywords (issue, PR, repo, commit) or research needs (compare, research, lookup, best practices). Offloads heavy operations to Copilot subprocess and returns compressed results only.

Develop, test, build, and deploy Godot 4.x games. Includes GdUnit4 for GDScript unit tests and PlayGodot for game automation and E2E testing. Supports web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.

TypeScriptで型安全なClaude Code Hooksを作成するためのガイド。cc-hooks-tsライブラリを使用してフックを実装する際に使用する。(1) Claude Code用の新しいhookを作成する時、(2) 既存のhookをTypeScriptで書き直す時、(3) PreToolUse/PostToolUse/SessionStart等のイベントフックを実装する時、(4) plugin.jsonにhooksを設定する時