Tony-Claude-Code-Skills

Build autonomous AI agents with Claude Agent SDK. TypeScript v0.2.96 | Python v0.1.56. Covers: query(), hooks, subagents, MCP, permissions, sandbox, structured outputs, and sessions. Use when: building AI agents, configuring MCP servers, setting up permissions/hooks, using structured outputs, troubleshooting SDK errors, or working with subagents.

Xiaolai's Claude tools collection. Use when user types /xiaolai. Routes to: (1) claude-agent-sdk — Agent SDK reference for building autonomous AI agents, or (2) nlpm — Natural-Language Programming Manager for scanning, scoring, and fixing NL artifacts.

Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this". (gstack)

OpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex". (gstack) Voice triggers (speech-to-text aliases): "code x", "code ex", "get another opinion".

记录和跟踪个人重大决策。当用户说"记决策"、"记个决策"、"决策跟踪"、"回填"、"decision",或描述一个刚做的/正在考虑的重大决策(创业/事业/财务/人生)并希望系统化记录与复盘时使用。自动四层拆解(原始信息/决策事实/假设推断/结果验证),生成 2 个文件,维护索引与行为模式库,并在记新决策时用历史教训主动拦截。

Fast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this". (gstack)

Restore working context saved earlier by /context-save. Loads the most recent saved state (across all branches by default) so you can pick up where you left off — even across Conductor workspace handoffs. Use when asked to "resume", "restore context", "where was I", or "pick up where I left off". Pair with /context-save. Formerly /checkpoint resume — renamed because Claude Code treats /checkpoint as a native rewind alias in current environments. (gstack)

Save working context. Captures git state, decisions made, and remaining work so any future session can pick up without losing a beat. Use when asked to "save progress", "save state", "context save", or "save my work". Pair with /context-restore to resume later. Formerly /checkpoint — renamed because Claude Code treats /checkpoint as a native rewind alias in current environments, which was shadowing this skill. (gstack)

Read-only queue dashboard for workspace-aware ship. Shows which VERSION slots are currently claimed by open PRs, which sibling Conductor workspaces have WIP work likely to ship soon, and what slot /ship would pick next. No mutations — just a snapshot. Use when asked to "landing report", "what's in the queue", "show me open PRs", or "which version do I claim next". (gstack)

Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. One command from zero to "gbrain is running, and this agent can call it." Use when: "setup gbrain", "connect gbrain", "start gbrain", "install gbrain", "configure gbrain for this machine". (gstack)

Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)

Create professional, dark-themed architecture diagrams as standalone HTML files with SVG graphics. Use when the user asks for system architecture diagrams, infrastructure diagrams, cloud architecture visualizations, security diagrams, network topology diagrams, or any technical diagram showing system components and their relationships.

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.

Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.

花叔Design——用HTML做高保真原型、交互Demo、幻灯片、动画、设计变体探索+设计方向顾问+专家评审。根据任务embody对应专家（UX/动画师/幻灯片设计师/原型师），避免web design tropes。触发词：做原型、交互原型、HTML演示、动画Demo、设计变体、hi-fi设计、UI mockup、prototype、做个HTML页面、做个可视化、app原型、iOS原型、导出MP4/GIF、60fps视频、设计风格、设计方向、配色方案、推荐风格、选个风格、做个好看的、评审、好不好看、review this design、带解说的动画、解说视频、长视频科普、voiceover、narration、5分钟讲清楚什么是XX。需求模糊时进设计方向顾问（三套逻辑并行出3版真实视觉，HTML原生40种风格库网页20+PPT20为弹药）；另含品牌资产协议、反AI slop、Junior工作流、Tweaks变体、动画→MP4/GIF导出、带解说长视频pipeline、5维评审。

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.

Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured surfaces, image-led composition, tasteful custom iconography, and clean phone mockup framing. By default, screens should be shown inside a subtle premium iPhone or similar phone mockup with a visible frame, while the main focus stays on the app content itself. This skill generates images only. It does not write code.

Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate.

Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.

扮演刘小排（Raphael AI 创始人，2024 年 AI 编程一人公司近千万营收，深海圈/SCAI 孵化器主理人）作为你的 1-on-1 产品教练。当用户提到 "刘小排"、"小排老师"、"扮演刘小排"、"找小排聊聊"、"小排怎么看"、"liuxiaopai 教练"、"AI 出海"、"MicroSaaS"、"一人公司"、"独立开发"、"出海产品"、"Raphael"、"翻石头"、"需求倒推"、"Idea to Business"、"我有个 AI 产品想法"、"我想做出海" 等任一触发词时,自动进入刘小排教练模式 — 用他的口吻、思考框架（产品三段论 / 需求填空题 / 翻石头原则 / 北极星指标 / 5% 成功率 / make something people love）、生财圈友式的真诚与降维打击,给用户做端到端教练指导。交互式引导（关键决策点给选项卡片）+ 实时联网核验（案例/榜单/竞品/工具栈），既不靠用户硬打字、也不靠过时记忆。**不与 liuxiaopai-design 重叠(那是泼冷水审讯,本 skill 是建设性教练)；不与 liuxiaopai-product 重叠(那是自动扫源工具,本 skill 是人本教练对话)。** 三者协作:methodology 教你怎么想 → product 扫到候选 → design 把它逼到墙角。只要用户带着「做不做某个 AI 产品 / 出海 / 副业 SaaS 怎么破局 / 做出来没人用 / 有人用不赚钱 / 一个人忙不过来 / 连试几个都失败」这类一人公司困惑来找指导,即便没说出上面任何关键词,也应进入本 skill 当教练,不要 undertrigger。

Generate professional SVG logos and high-end showcase images. Use when the user wants to: (1) Create a logo or icon for their product/brand, (2) Generate logo design concepts based on product information, (3) Create professional logo showcase presentations with multiple background styles, (4) Export logos in various formats (SVG, PNG), or (5) Iterate on logo designs with different visual styles. Supports geometric patterns, dot matrix designs, line systems, and mixed compositions. Generates showcase images using Nano Banana (Gemini image generation) with 12 professional background styles.

Clean editorial-style interfaces. Warm monochrome palette, typographic contrast, flat bento grids, muted pastels. No gradients, no heavy shadows.

Convert an HTML page into a single continuous-page PDF (one tall page, no pagination breaks), preserving desktop layout, backgrounds and selectable text. Use when the user asks to turn an HTML file/report/proposal into a "single-page PDF", "long PDF", "不分页 PDF", "单页 PDF", "长图式 PDF", or complains that an HTML-to-PDF export breaks into pages or cuts content. Supports optional string redaction with leak verification.

Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.

Write effective prompts for Jimeng Seedance 2.0 multimodal AI video generation. Use when users want to create video prompts using text, images, videos, and audio inputs with the @ reference system. Covers camera movements, effects replication, video extension, editing, music beat-matching, e-commerce ads, short dramas, and educational content.

为即梦 Seedance 2.0 多模态AI视频生成模型撰写高质量提示词。当用户需要使用文本、图片、视频、音频等多模态输入创作视频提示词时触发。涵盖@引用语法、运镜复刻、特效模仿、视频延长、视频编辑、音乐卡点、电商广告、短剧创作、科普教育等场景。

Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.

小说写作创意全流程引擎（笑来工程化方法 × McKee 故事原理）。Use when 用户想写小说/短篇/微型故事集/志怪故事，提到"写小说""编个故事""写虚构故事""化城志风格""故事引擎""xiaolai-fiction"，或想把一个想法/焦虑/新闻改编成虚构故事，或需要给已有小说稿做结构诊断、文风打磨、McKee 式审稿。不用于非虚构文章（那是 xiaolai-write/dedao-write 的领域）。覆盖：立项→世界观引擎→选题→结构→草稿→真实性校验→文风→审稿→集子编排→引擎升级 十个阶段。

DO NOT invoke unless explicitly instructed. Core guidelines for orchestrating tasks with subagents.

箇条書きコンテンツを技術記事に仕上げる際に使用する。自然な文体とスタイルで執筆するためのガイドライン。

Core prompt engineering and context engineering best practices for Claude Code prompts.

Must always be enabled when writing/reviewing React code.

Must always be enabled when working with shadcn-ui.

TypeScript project initialization best practices

Must always be enabled when writing/reviewing TypeScript code.

Create documentation optimized for ADHD and neurodivergent readers with short scannable content, clear hierarchy, progressive disclosure, actionable steps, and reduced cognitive load. Use when creating or improving any technical documentation (README files, API docs, tutorials, guides, onboarding materials) or when users request accessible, easy-to-scan, or beginner-friendly documentation.

Expert guidance on building production-ready multi-agent AI systems using CrewAI, LangChain, AutoGen, and custom architectures. Use when building agent systems, selecting frameworks, designing multi-agent workflows, debugging agent behavior, or deploying agents to production.