发现 Skills

Use when implementing any feature or bugfix, before writing implementation code

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Use when selling electronics, IoT devices, consumer appliances, battery-powered products, or radio-equipped devices in any market, checking CE/FCC/UKCA requirements, EMC/safety/radio testing, RoHS, WEEE, battery regulations, or the EU Cyber Resilience Act

Manages Git workflows including branching, commits, and pull requests. Use when working with Git, creating commits, opening PRs, managing branches, resolving conflicts, or when asked about version control best practices.

デイリーノート夜用アシスタント（更新）

Use when the user asks to "review this skill", "analyze skill quality", "skill version update", "整理 skills", "skill governance", or wants a repeatable keep/disable/archive loop built from real skill failures instead of abstract best practices.

Implement and debug layout-aware components that respond to their container's dimensions rather than the viewport size.

End-to-end architecture capture. Takes a context dump and/or conversation, produces an architecture map, inferences document, changelog, agent brief, and opportunity analysis. Orchestrates tml-extract, tml-interview, tml-infer, tml-map, tml-so-what, and tml-hygiene in one seamless experience. The user sees one flow; the skills compose underneath. This is the primary entry point — invoke this skill, not the sub-skills directly.

Detects potential memory leaks in Zig code by checking allocation/deallocation patterns, defer statements, and test cleanup. Use when reviewing code changes, writing new code with allocations, or debugging memory issues.

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

DDD strategic-design expert that guides users through identifying Bounded Contexts and splitting Aggregates. Uses a Plan Mode Q&A to collect domain information and ultimately generates Markdown design documents.

This skill generates classes for scrcpy CLI arguments. Use it when adding support for new scrcpy CLI arguments to the app.

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient. Integrations: shadcn/ui MCP for component search and examples.

Search home-manager configuration options. Use this when looking up home-manager options, checking available settings, or understanding option types and default values.

Diagnose or 排查 why a `/rag-recall/api/search/keyword` request did not recall an expected doc or FAQ in sit, uat, or prod. Use when the user wants to 排查 keyword 检索漏召回, provides a full keyword request or an existing requestId plus target docId/faqId values, and expects end-to-end troubleshooting through a Playwright-attached browser session, `trace/recordInfo`, ELK `traceTargetIds` logs, and ES ranking or `_explain` checks. Also use when the user asks to fabricate a live keyword request with `traceTargetIds` and then investigate the resulting requestId.

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro).

Display HTML content on connected Clawdbot nodes (Mac app, iOS, Android).

Extract text, tables, and structured data from documents using prebuilt and custom models.

Expert in browser automation using Playwright, Puppeteer, and Selenium. Specializes in UI testing, web scraping, form automation, and automated workflows.

Advanced filesystem operations for AI agents. Comprehensive file and directory operations with intelligent filtering, searching, and batch processing capabilities.

Browser automation that maintains page state across script executions. Write small, focused scripts to accomplish tasks incrementally. Once you've proven out part of a workflow and there is repeate...

Run **Firecrawl** web crawling and extraction directly from Claude Code. Scrape individual pages, crawl entire sites, extract structured data with AI, batch process URL lists, and map website structure...