Claude Code Skills · page 59

为 X、LinkedIn、TikTok、YouTube、时事通讯（Newsletters）以及跨平台内容重加工营销活动（Repurposed multi-platform campaigns）创建平台原生的内容系统。当用户需要社交媒体帖子、推文串（Threads）、脚本、内容日历，或将单一源素材清晰地适配到多个平台时使用。

自动从 Claude Code 会话（Session）中提取可重用的模式（Pattern），并将其作为已学习的技能（Skill）保存以备将来使用。

一种基于本能（Instinct）的训练系统，通过钩子（Hooks）观察会话，创建带有置信度评分的原子化本能，并将其进化为技能（Skills）、命令（Commands）或智能体（Agents）。

仅在创建/更新/修复 C++ 测试、配置 GoogleTest/CTest、诊断失败或不稳定的测试、以及添加覆盖率或消毒器时使用。

Django 架构模式、使用 DRF 的 REST API 设计、ORM 最佳实践、缓存、信号（Signals）、中间件（Middleware）以及生产级 Django 应用。

Playwright E2E 测试模式、页面对象模型（POM）、配置、CI/CD 集成、产物管理以及不稳定测试（flaky test）策略。

适用于 Claude Code 会话的正规评测框架（Evaluation Framework），实现了评测驱动开发（Eval-Driven Development, EDD）原则

React、Next.js、状态管理（State Management）、性能优化（Performance Optimization）及 UI 最佳实践的前端开发模式。

从零开始或通过转换 PowerPoint 文件创建令人惊叹、动画丰富的 HTML 演示文稿（Presentations）。适用于用户想要构建演示文稿、将 PPT/PPTX 转换为 Web 页面或为演讲/路演创建幻灯片（Slides）的场景。通过视觉探索而非抽象选择，帮助非设计师发掘其审美偏好。

创建并更新融资演示文稿（pitch decks）、单页简介（one-pagers）、投资备忘录（investor memos）、加速器申请、财务模型和募资材料。适用于用户需要面向投资者的文档、预测、资金用途表、里程碑计划，或需要保持多个募资资产内部一致性的场景。

起草用于融资的冷启动邮件（Cold Emails）、引荐语（Warm Intro Blurbs）、后续跟进邮件、进展更新邮件以及其他投资人沟通内容。适用于用户需要向天使投资人、风险投资（VC）、战略投资人或加速器发送简洁、个性化且面向投资者的消息。

进行市场调研（Market Research）、竞品分析（Competitive Analysis）、投资者尽职调查（Investor Due Diligence）以及行业情报（Industry Intelligence）收集，提供来源归因与面向决策的总结。适用于用户需要市场规模估算（Market Sizing）、竞品对比、基金研究、技术扫描或为商业决策提供参考的场景。

发现技能（Skill），迭代查询，并在任何环境中自动安装技能。

当涉及添加身份验证（Authentication）、处理用户输入、操作机密（Secrets）、创建 API 终端节点或实现支付/敏感功能时，请使用此技能。提供全面的安全检查清单和模式。

建议在逻辑间隔进行手动上下文压缩（Context Compaction），以便在任务阶段中保留上下文，而不是依赖任意的自动压缩。

在编写新功能、修复 Bug 或重构代码时使用此技能。强制执行测试驱动开发（TDD），包括单元测试、集成测试和端到端（E2E）测试，覆盖率需达到 80% 以上。

为 Claude Code 会话提供的全面验证系统。

Build professional native iPhone apps in Swift with SwiftUI and UIKit. Full lifecycle - build, debug, test, optimize, ship. CLI-only, no Xcode. Targets iOS 26 with iOS 18 compatibility.

Build professional native macOS apps in Swift with SwiftUI and AppKit. Full lifecycle - build, debug, test, optimize, ship. CLI-only, no Xcode.

Heal skill documentation by applying corrections discovered during execution with approval workflow

Expert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

Expert guidance for creating, configuring, and using Claude Code hooks. Use when working with hooks, setting up event listeners, validating commands, automating workflows, adding notifications, or understanding hook types (PreToolUse, PostToolUse, Stop, SessionStart, UserPromptSubmit, etc).

Create Model Context Protocol (MCP) servers that expose tools, resources, and prompts to Claude. Use when building custom integrations, APIs, data sources, or any server that Claude should interact with via the MCP protocol. Supports both TypeScript and Python implementations.

Create optimized prompts for Claude-to-Claude pipelines with research, planning, and execution stages. Use when building prompts that produce outputs for other prompts to consume, or when running multi-stage workflows (research -> plan -> implement).

Create hierarchical project plans optimized for solo agentic development. Use when planning projects, phases, or tasks that Claude will execute. Produces Claude-executable plans with verification criteria, not enterprise documentation. Handles briefs, roadmaps, phase plans, and context handoffs.

Expert guidance for creating Claude Code slash commands. Use when working with slash commands, creating custom commands, understanding command structure, or learning YAML configuration.

Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.

Deep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous verification. Use when standard troubleshooting fails or when issues require systematic root cause analysis.

Set up and configure Geoffrey Huntley's original Ralph Wiggum autonomous coding loop in any directory with proper structure, prompts, and backpressure.

{{What it does}} Use when {{trigger conditions}}.

Search The Pirate Bay for torrents and extract magnet links via the apibay.org JSON API. Use when asked to "find a torrent", "search pirate bay", "get a magnet link", "download torrent", "find seeders", "top torrents", or any torrent search task. Can operate via CLI tool or direct API calls.

Interact with Paca project management using MCP tools. Use when tracking tasks, writing docs, planning sprints, managing work items, creating bugs or features, viewing the board, or handling any project-management request involving Paca. Routes to specialized skills for complex workflows like epics, sprint planning, and task execution.

Break a large Paca task or epic into smaller, actionable sub-tasks with dependency ordering. Use when decomposing work that is too large to estimate or execute in a single session, when creating an implementation plan, or when a task needs to be split into vertical slices before sprint planning.

Clarify a vague or incomplete Paca task or specification by identifying ambiguities, asking targeted questions, and rewriting the description with explicit acceptance criteria. Use when a task is unclear, missing edge cases, lacks a testable done condition, or when someone asks to improve or flesh out a spec.

Execute a Paca task end-to-end — reading context and acceptance criteria, doing the work (code, writing, research, review), updating task status, and commenting results. Use when asked to start, implement, complete, or work on a specific Paca task. Reads project docs first to understand the codebase and tech stack before acting.

Write or update documentation for a feature, task, or topic in Paca Docs. Use when asked to document a completed feature, write a guide or runbook, update existing docs, create a spec or architecture document, or produce BDD scenarios. Documentation is saved in Paca — never created as local files.

Turn a product requirement or feature description into a structured epic in Paca, with child user stories and a spec document. Use when asked to plan a new feature, break down a high-level requirement into stories, create an epic, or go from "we need X" to a fully structured backlog ready for sprint planning.

Estimate story points for Paca tasks using the Fibonacci scale, calibrated against recently completed reference tasks and project tech stack. Use when tasks are missing estimates, before sprint planning, when the team needs sizing for prioritization, or when asked to size a backlog.

Set or adjust priorities across the Paca backlog, aligned to roadmap goals and business value. Use when the backlog needs sorting, before sprint planning, when tasks need explicit Critical/High/Medium/Low priority labels, or when asked to rank work by importance or urgency.

Configure the Paca MCP server for use with Claude Code or Claude Desktop. Use when setting up Paca for the first time, adding or editing the MCP server config, troubleshooting connectivity, or installing the Paca skills globally. Walks the user through prerequisites, config file generation, verification, and optional global skill install.

Plan a Paca sprint by selecting tasks from the backlog, detecting carryover from the previous sprint, inferring velocity from past sprints, and assigning tasks to the sprint. Use when starting a new sprint, filling an upcoming sprint, reviewing sprint capacity, or setting the sprint goal.

根据完整的 SEO 需求与头部竞品页面证据，设计、撰写并在产品现有仓库中实现高质量 SEO 页面。需要匹配搜索意图决定工具页、资源页、教程页、比较页或解决方案页，创建页面设计文档、提高信息增益、编写 metadata、加入图片、结构化数据、内链并完成工程验证时使用。

Generate, edit, or batch-create SEO, marketing, social, and document images with Gemini or OpenAI through the repository-owned Growth Lab image client. Use when a page or content loop needs illustrations, diagrams, covers, reference-image edits, multiple candidates, or verified image text and composition. This is the only AI image-generation Executor in Growth Lab.

Install, authenticate, configure, operate, and troubleshoot the external MediaCrawler client shared by Douyin, Kuaishou, Bilibili, Weibo, Tieba, and Zhihu collectors. Xiaohongshu uses the separate browser-first xiaohongshu-mcp Collector. Use when auditing this client, onboarding a supported platform account, selecting search/detail/creator modes, enabling comments or media, locating outputs, or diagnosing crawler failures.

Collect Bilibili video and creator evidence with MediaCrawler through search, exact BV detail, comments, dynamics, contacts, and optional media. Use for topic, format, title, creator, or audience research with explicit time-range and quality controls.

Collect Douyin competitive evidence with MediaCrawler using keyword search, exact video detail, comments, media, and creator profiles. Use for trend, hook, format, audience-language, or creator research that needs reproducible raw evidence and a documented selection method.

Collect Kuaishou competitive evidence with MediaCrawler using keyword search, exact video detail, comments, media, and creator profiles. Use for trend, format, audience-language, or creator research requiring reproducible source records and explicit collection limits.

Collect Baidu Tieba thread and user evidence with MediaCrawler using keyword or bar discovery, exact thread detail, replies, and creator pages. Use for community pain-point, vocabulary, objection, topic, or user research with thread-context preservation.

Collect Weibo posts and creator evidence with MediaCrawler using search, exact post IDs, comments, optional media, and creator IDs. Use for discourse, trend, messaging, audience-language, or account research requiring preserved provenance and risk-aware detail enrichment.

Collect Zhihu answers, articles, videos, comments, and creator evidence with MediaCrawler through search and exact URLs. Use for expert discourse, problem framing, objections, terminology, topic, or creator research where content type and question context must remain explicit.

通过自然语言完成 Growth Lab 的统一依赖审计与配置。检查所有能力所需的 API key、可直接安装的第三方 CLI/Client、浏览器与登录态；拒绝隐含的外部 Skill 或脚本依赖，告诉用户哪些已配置、哪些缺失、从哪里获取，并允许本轮绕过。需要首次配置、检查环境、修复依赖或询问“还缺什么”时使用。

渐进式研究当前产品，并把已经稳定、可追溯的产品认知增量写入根目录 SOUL.md。首次接入产品代码、原型或线上 URL，需要确认产品形态与已有能力，或某个增长 loop 在执行中发现新的产品事实、用户场景、问题与价值证据时使用。不得一次性臆造完整产品画像，也不得仅凭代码功能推断用户、问题或价值。

完整调研并确定 SEO 机会：从产品理解、领域词表拆解、关键词矩阵扩展、Bing 真实热度验证、竞品发现、实时 SERP 抓取，到头部页面的搜索引擎层、用户层和质量层拆解。需要查热词、验证搜索量、判断搜索意图、研究竞品页面、寻找信息增益缺口或决定应该做什么 SEO 页面时使用。

从目标用户的真实搜索场景出发，对抗式审查并修改 SEO 页面，找出搜索意图偏离、低信息量、批量同构、重复转化、AI 腔、术语漂移、无依据主张、metadata 问题和配图场景错位。需要审查 SEO 内容价值、降低 AI 味、检查图片相关性或决定页面保留、合并、重写、删除时使用。

使用 Bing Webmaster 页面与查询数据、索引状态、产品结果和 Bing AI Performance 证据复盘 SEO 页面，诊断收录、排名、点击率、意图、内容、转化和 AI 引用问题。需要比较周期表现、分析 citations、cited pages、grounding queries、query fan-out 或决定下一步 SEO/GEO 行动时使用。

Run an SEO page observation-action-review loop with persistent Memory by coordinating demand research, page creation, adversarial review, image generation, IndexNow submission, and performance review. Use when taking an SEO page from opportunity discovery through publication, measurement, iteration, or continuing a previous SEO loop from Memory.

Capture authenticated product screenshots through the repository-owned Playwright CDP script and archive them in the invoking loop's Memory. Use when content needs truthful UI evidence, reusable product screenshots, a selected component, or a full-page browser capture. Requires only user-installed uv and Chrome configured by onboarding; never depends on MCP tools, external Skills, private repositories, or external scripts.

把已批准的小红书草稿、单一分析参考和真实产品素材变成可审查卡片：先完成 DAI 与 image plan，再按确定性、完整效果或可分离图层模式制作，机械验证 PNG 与清单并运行合规检查。精确文字和真实 UI 不交给模型猜测；AI 生图需要单独配置和授权。

小红书内容增长闭环 —— 从调研找 idea、锚定爆款骨架、填入真实产品内容、生图与合规检查，到回收 24h/48h/7d 发布结果并完成复盘。用户要求出稿、复刻、月度复盘、查看发布数据或修订内容规律时使用。

使用本机 browser-first xiaohongshu-mcp 只读搜索小红书、下载候选首图、补全用户选择的笔记详情，并把脱敏证据写入调用方 Memory。用于 xhs-replicate 的选题和视觉参考研究，取代小红书 MediaCrawler 路径。

>-

>-

>-

>-

>-

>-

>

Guide for upgrading Stripe API versions and SDKs

Author animated technical explainer diagrams as .anim.json files for Nimbalyst's Animation editor. Use when the user wants to animate a diagram, show how a system/protocol/algorithm behaves over time, build a motion explainer, or turn a static architecture diagram into something that plays.

Author Nimbalyst Project Canvas boards (.canvas files) — an infinite canvas whose cards are live editors for real workspace files and shared documents, arranged spatially and wired with edges. Use when the user asks for a canvas, a board, a spatial layout of documents or mockups, a flow of screens, or a workspace overview.

Create visual data models for database schemas using Nimbalyst's DataModelLM editor. Use when the user wants to design a data model, database schema, entity relationship diagram, or Prisma schema.

Create diagrams and visual drawings using Excalidraw (.excalidraw files). Use when the user wants flowcharts, architecture diagrams, system diagrams, sketches, or any visual diagram. For database schemas and entity relationship diagrams, use the DataModelLM extension instead.

Build, install, and hot-reload Nimbalyst extensions using MCP tools. Use when developing, testing, or iterating on Nimbalyst extensions.

Help the user file a bug report or feature request for Nimbalyst. Activates when the user opens the in-app feedback flow or runs /feedback:bug-report or /feedback:feature-request. Coordinates evidence gathering, anonymization, and posting to GitHub Issues.

Create git commits using Nimbalyst's interactive commit proposal widget. ONLY use when the user explicitly clicks "Commit with AI" button or asks for "smart commit". For regular commit requests, use standard git commands instead.

Create visual UX mockups using HTML/CSS files (.mockup.html). Use when the user wants to design UI, wireframes, visual layouts, or plan features visually.

Create structured plan documents and track work items using YAML frontmatter. Use when the user wants to plan a feature, track progress, log bugs/tasks/ideas, or organize project work.

多Agent蜂群并行协作，纯git自组织，适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。

标准化文章编辑流程，确保修改范围明确、进度可追踪、变更有记录。当用户说"编辑文章"、"修改文章"、"调整内容"、"改一下这篇"时使用此技能。

长文精简为X平台内容（200-500字），保留核心观点和个人风格。当用户提到"转微博"、"发小红书"、"社交媒体"、"缩短文章"时使用。

|

设计哲学顾问，从20种风格中推荐3个方向并生成视觉Demo和AI提示词。当用户提到"设计风格"、"设计方向"、"配色方案"、"视觉风格"、"设计评审"、"推荐风格"时使用。

|

文章配图一键生成并上传图床，自动插入Markdown链接。当用户提到"配图"、"插图"、"上传图片"、"文章配图"时使用。

多渠道搜索新产品新技术，交叉验证后存入知识库。当用户提到"最新信息"、"新产品"、"搜索资料"、"查资料"、"了解XX"时使用。

搜索个人素材库1800+条真实经历和观点，为内容增加人味。当用户提到"个人经历"、"真实案例"、"素材"、"人味"时使用。

|

自动识别Prompt类型并分类保存（技术/内容/教学/产品/通用）。当用户提到"保存prompt"、"记录prompt"、"整理prompt"时使用。

三遍审校降低AI检测率，让文章更有人味。当用户提到"AI味太重"、"像AI写的"、"降低AI检测率"、"审校"、"自然一些"时使用。

结构化网络调研流程，确保调研成果增量保存到文件，不因会话截断丢失。当用户说"调研"、"搜索资料"、"帮我查一下"、"了解一下"、"最新信息"时使用此技能。

视频脚本口语化审校，去书面腔让脚本适合说出来。当用户提到"口语化"、"太书面了"、"像说话一样"、"脚本审校"时使用。

检查并更新花叔系 skills。当用户说「检查skill更新」「更新花叔的skill」「skill是不是最新的」时触发；当会话中用到任何花叔系 skill（huashu-* / nuwa / darwin / freud / seedance / tramstop / dukou 等），且其安装目录里的 .huashu-skill-meta.json 的 last_checked 距今超过 30 天（或 git 安装的超过 30 天未 fetch）时，也应主动触发一次检查。

从内容到成品PPTX的端到端演示文稿制作，含AI插画生成和18种设计风格。当用户提到"做PPT"、"做幻灯片"、"演示文稿"、"Keynote"、"slides"时使用。

|

快速生成3-4个选题方向，含标题、大纲和优劣分析。当用户提到"选题"、"写什么"、"文章方向"、"题目建议"时使用。

基于MrBeast策略检查视频标题、封面和开头钩子。当用户提到"视频标题"、"封面图"、"点击率"、"CTR"、"观看时长"时使用。

快速生成2-3个视频大纲方案，含标题、封面建议和结构设计。当用户提到"视频大纲"、"视频结构"、"脚本大纲"、"视频选题"时使用。

|