Explore skills

Save and restore session state for continuity across Claude Code sessions. Captures tasks, changed files, context, and decisions. Use when ending a session, preserving progress, or running /checkpointing.

Generate distinctive, production-grade frontend UI code that avoids generic AI aesthetics. Follows opinionated design principles for unique visual identity. Use when building web UIs, components, or running /frontend-design.

Generate implementation code from design documents by delegating to OpenAI Codex. Use when you have specs ready and want to auto-generate source code, or when running /implement.

Generate a requirements document with user stories, acceptance criteria, and constraints. Use when defining features, writing specs, or running /requirements before implementation.

Conduct technical research using Gemini CLI, producing comparison reports with recommendations and code examples. Use when evaluating technologies, comparing libraries, or running /research.

Run code review against design documents, checking acceptance criteria, security, performance, and test coverage. Use when reviewing implementation quality or running /review.

Entry point for the Signal Prospecting Kit. Deep onboarding: researches the user's company from their domain, captures ICP, stack, and voice. Routes to /profile for market research. Triggers: /start, first run, "help me set up". Reads: ./gtm/ (all files). Writes: ./gtm/company.md, ./gtm/icp.md, ./gtm/voice.md. Standalone: yes.

Analyze entire codebases using Gemini CLI's 1M token context. Generates architecture reports covering structure, security, performance, and improvement roadmaps. Use when auditing code quality or running /analyze.

Generate OpenAPI 3.0 specification documents with endpoints, schemas, and security definitions. Use when designing REST APIs, creating API docs, or running /api.

Generate native-quality iOS/macOS mockup PNGs using SwiftUI Preview rendering. Use when designing Apple platform UIs, creating native app mockups, or running /mockup-swift.

編輯現有 skill 的內部結構。精確修改 gotchas、scoring、forcing questions 等特定部分。 Trigger: 用戶說「改這個 skill」、「調 scoring」、「加 gotcha」、「改 forcing question」。 Do NOT use when: 要新增 skill（用 /skill-gen）。 Do NOT use when: 要整體升級（用 /domain-upgrade）。 Do NOT use when: 要改 skill 串接（用 /workflow-edit）。 上游：用戶指定的 skill + 修改意圖。 下游：/skill-check review。 產出：修改後的 skill 檔案。

This skill should be used when the user asks about "seat map", "seatmap", "seat selection", "best seat", "window seat", "aisle seat", "legroom", "exit row", "seat availability", "airplane seats", "flight seats", "seat pitch", "seat review", "bulkhead", "quiet zone", mentions specific flight numbers (e.g. QF1, BA178, AA716), or wants to check, compare, or find seats on a flight.