发现 Skills

../../../commands/tdd.md

Generate test fixture factories for your models. Builder pattern and static factories for zero-boilerplate test data. Use when tests need sample data setup.

This skill should be used when the user asks to "implement", "build", "create", "add feature", "develop", "design", "architect", "plan", "structure", "refactor", "improve", "optimize", "review", "fix", "solve", "handle", "debug", or discusses implementation strategies. Apply cognitive load principles to ALL development work as a cornerstone principle.

Understand and design for users' preference for current state over change. Use when planning migrations, introducing new features, designing defaults, or overcoming resistance to product adoption.

Guide to transform prototypes into robust, distributable Python packages using the src/ layout, a hybrid paradigm, and strict configuration management.

Autonomous AI image campaign content generator. Processes pending photos via Ming-flash-omni-2.0 (cleanup + style editing), creates side-by-side comparison images and GIF showcases, then auto-generates tweet text using AI. Use for requests like "run campaign", "process pending images", "generate tweet content", or "create showcase from results".

Control Apple Music on macOS via the `clawtunes` CLI (play songs/albums/playlists, control playback, volume, shuffle, repeat, search, catalog lookup, AirPlay, and playlist management). Use when a user asks to play music, search for songs, control audio playback, or manage Apple Music settings.

Advanced report generation specialist, supporting multi-format output, data visualization, and interactive report creation.

Task implementation skill for spec-driven workflows. Reads specifications, identifies the next actionable tasks, and creates detailed execution plans. Use when ready to implement a task from an existing spec — bridges the gap between planning and coding.

Generates structured blog post outlines with SEO-optimized headings, key points, and content flow. Use when planning blog content, creating editorial calendars, or structuring long-form articles. Supports multiple content formats and audience targeting.

Create GitHub issues with TDD principles and proper labels

Language-independent testing knowledge: test strategy selection, test pyramid, mocking philosophy, fixture and test data patterns, test isolation, coverage approach, property-based testing, and naming conventions. Use when deciding test strategy, choosing between unit and integration and e2e tests, designing mocking boundaries, architecting fixtures, evaluating test coverage philosophy, or assessing property-based testing applicability. Also activates for test architecture, testing methodology, test pyramid, and test isolation questions.

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->

<!-- AUTO-GENERATED by export-skills.py — DO NOT EDIT -->

Next.js App Router architecture workflow. Navigates server vs client components, caching tiers, and Server Actions.

Use this skill when the user needs to automatically remediate blocker findings from a public-repo safety review before commit or push. Apply it when requests involve removing, redacting, neutralizing, or excluding secrets, private data, internal-only material, or other public red-list content from a pending changeset. Do not use it for generic code review, broad security hardening, or non-publication-related refactoring.

Automates and ensures reliable release workflows with automatic version bump based on commit history, mandatory lint/build/test execution before release, and safe tag creation and push.

F5 Framework workflow commands for AI-assisted development

Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.

Run an independent external code review using the Gemini CLI on staged changes or branch diffs. Use for second-opinion reviews, external validation before merge, or when the user explicitly asks for Gemini feedback.

Builds production-quality UIs. Use when building or modifying user-facing interfaces. Use when creating components, implementing layouts, managing state, or when the output needs to look and feel production-quality rather than AI-generated.

C++ テストの作成/更新/修正、GoogleTest/CTest の設定、失敗またはフレーキーなテストの診断、カバレッジ/サニタイザーの追加時にのみ使用します。