Overview CLI FAQ

Agent Skills 排行榜 · 关键词 + 语义搜索

按 / 聚焦搜索框
正在使用 AI 进行语义搜索...
23,096
总 Skills
59.4M
总安装量
2,536
贡献者
# Skill 仓库 描述 安装量
3051 csv-data-summarizer coffeefuelbump/csv-data-summarizer-claude-skill
CSV Data Summarizer This Skill analyzes CSV files and provides comprehensive summaries with statistical insights and visualizations. When to Use This Skill Claude should use this Skill whenever the user: Uploads or references a CSV file Asks to summarize, analyze, or visualize tabular data Requests insights from CSV data Wants to understand data structure and quality How It Works ⚠️ CRITICAL BEHAVIOR REQUIREMENT ⚠️ DO NOT ASK THE USER WHAT THEY WANT TO DO WITH THE DATA. DO NOT OFFER OPTIONS...
 1.6K
3052 seo-audit brightdata/skills
SEO Audit You are an expert in search engine optimization. Your goal is to identify SEO issues and provide actionable recommendations to improve organic search performance. Initial Assessment Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task. Before auditing, understand: Site ...
 1.6K
3053 flowstudio-power-automate-debug github/awesome-copilot
Power Automate Debugging with FlowStudio MCP A step-by-step diagnostic process for investigating failing Power Automate cloud flows through the FlowStudio MCP server. Prerequisite : A FlowStudio MCP server must be reachable with a valid JWT. See the flowstudio-power-automate-mcp skill for connection setup. Subscribe at https://mcp.flowstudio.app Source of Truth Always call tools/list first to confirm available tool names and their parameter schemas. Tool names and parameters may change between s...
 1.6K
3054 figma-create-design-system-rules figma/mcp-server-guide
Create Design System Rules Overview This skill helps you generate custom design system rules tailored to your project's specific needs. These rules guide AI coding agents to produce consistent, high-quality code when implementing Figma designs, ensuring that your team's conventions, component patterns, and architectural decisions are followed automatically. Supported Rule Files Agent Rule File Claude Code CLAUDE.md Codex CLI AGENTS.md Cursor .cursor/rules/figma-design-system.mdc What Are Design ...
 1.6K
3055 liquid-theme-a11y benjaminsehl/liquid-skills
Accessibility for Shopify Liquid Themes Core Principle Every interactive component must work with keyboard only, screen readers, and reduced-motion preferences. Start with semantic HTML — add ARIA only when native semantics are insufficient. Decision Table: Which Pattern? Component HTML Element ARIA Pattern Reference Expandable content <details>/<summary> None needed Accordion Modal/dialog <dialog> aria-modal="true" Modal Tooltip/popup [popover] attribute role="tooltip" fallback Tooltip Dropdown...
 1.6K
3056 chrome-cdp pasky/chrome-cdp-skill
Chrome CDP Lightweight Chrome DevTools Protocol CLI. Connects directly via WebSocket — no Puppeteer, works with 100+ tabs, instant connection. Prerequisites Chrome with remote debugging enabled: open chrome://inspect/remote-debugging and toggle the switch Node.js 22+ (uses built-in WebSocket) Commands All commands use scripts/cdp.mjs . The <target> is a unique targetId prefix from list ; copy the full prefix shown in the list output (for example 6BE827FA ). The CLI rejects ambiguous prefixes. Li...
 1.6K
3057 agency-agents-ai-specialists aradotso/trending-skills
🎭 Agency Agents — AI Specialist Personalities Skill by ara.so — Daily 2026 Skills collection. A curated collection of 50+ specialized AI agent personalities for Claude Code, Cursor, Aider, Windsurf, Copilot, and more. Each agent has deep domain expertise, a distinct personality, defined workflows, and measurable deliverables — covering engineering, design, marketing, sales, paid media, and beyond. Installation Prerequisites git clone https://github.com/msitarzewski/agency-agents.git cd agency-ag...
 1.6K
3058 clawhub-skill-vetting hugomrtz/skill-vetting-clawhub
ClawHub Skill Vetting Overview Apply a strict, security‑first vetting workflow before installing any ClawHub skill. Prioritize code review, permission scope, domain listing, and risk scoring. Workflow Source check — author reputation, stars/downloads, last update, reviews. Code review (MANDATORY) — scan all files for exfiltration, secrets access, eval/exec , obfuscation. Permission scope — files, commands, network; confirm minimal scope. Recent activity — detect suspicious bursts. Community chec...
 1.6K
3059 streamdown vercel/streamdown
Streamdown Streaming-optimized React Markdown renderer. Drop-in replacement for react-markdown with built-in streaming support, security, and interactive controls. Quick Setup 1. Install npm install streamdown Optional plugins (install only what's needed): npm install @streamdown/code @streamdown/mermaid @streamdown/math @streamdown/cjk 2. Configure Tailwind CSS (Required) This is the most commonly missed step. Streamdown uses Tailwind for styling and the dist files must be scanned. Tailwind v4 ...
 1.6K
3060 nx-plugins nrwl/nx-ai-agents-config
Finding and Installing new plugins List plugins: pnpm nx list Install plugins pnpm nx add <plugin> . Example: pnpm nx add @nx/react .
 1.6K
3061 nuxt-seo onmax/nuxt-skills
Nuxt SEO npx nuxi module add @nuxtjs/seo When to Use Working with: SEO configuration (site URL, name, indexability) Robots.txt and sitemap.xml generation Dynamic OG image generation JSON-LD structured data (schema.org) Breadcrumbs and canonical URLs Usage Pattern Progressive loading - only read what you need: Configuring site? → references/site-config.md Setting up robots/sitemap? → references/crawlability.md Generating OG images? → references/og-image.md Adding JSON-LD? → references/schema...
 1.6K
3062 release tobi/qmd
Release Workflow This skill provides a systematic workflow for creating and publishing releases for the linear-cli project. It handles changelog management, version bumping, testing, and tagging. When to Use Use this skill when preparing to release a new version of linear-cli. The workflow ensures all changes are documented, tests pass, and versions are properly tagged before publishing. Prerequisites Ensure the following tools are available: changelog skill for changelog management svbump for v...
 1.6K
3063 business-analytics-reporter ailabs-393/ai-labs-claude-skills
Business Analytics Reporter Overview Generate comprehensive business performance reports that analyze sales and revenue data, identify areas where the business is lacking, interpret what the statistics indicate, and provide actionable improvement strategies. The skill uses data-driven analysis to detect weak areas and recommends specific strategies backed by business frameworks. When to Use This Skill Invoke this skill when users request: "Analyze my business data and tell me where we're lac...
 1.6K
3064 giving-presentations refoundai/lenny-skills
Giving Presentations Help the user create and deliver compelling presentations using techniques from 19 product leaders. How to Help When the user asks for help with presentations: Understand the context - Ask about the audience, the stakes, the format (keynote, board meeting, all-hands), and how much time they have Start with narrative, not slides - Help them identify the one thing they want the audience to remember before touching slide software Structure for engagement - Guide them to use con...
 1.6K
3065 dotnet-10-csharp-14 mhagrelius/dotfiles
.NET 10 & C 14 Best Practices .NET 10 (LTS, Nov 2025) with C 14. Covers minimal APIs, not MVC. Official docs: .NET 10 | C 14 | ASP.NET Core 10 Detail Files File Topics csharp-14.md Extension blocks, field keyword, null-conditional assignment minimal-apis.md Validation, TypedResults, filters, modular monolith, vertical slices security.md JWT auth, CORS, rate limiting, OpenAPI security, middleware order infrastructure.md Options, resilience, channels, health checks, caching, Serilog, EF Core, k...
 1.6K
3066 baidu-search countbot-ai/countbot
百度 AI 搜索 基于百度千帆平台的 AI 搜索服务，支持多种搜索模式。 配置 编辑 skills/baidu-search/scripts/config.json ，填写 API Key： { "api_key" : "bce-v3/YOUR_API_KEY_HERE" } API Key 从 百度千帆平台 获取。 命令行调用 网页搜索（默认） python3 skills/baidu-search/scripts/search.py "搜索关键词" JSON 输出（推荐 AI 使用） python3 skills/baidu-search/scripts/search.py "人工智能最新进展" --json 限制结果数 python3 skills/baidu-search/scripts/search.py "Python教程" --limit 5 站点过滤 python3 skills/baidu-search/scripts/search.py "天气预报" --sites weather.com.cn 时间过滤（week/month/semiyear/year）...
 1.6K
3067 godot-best-practices jwynia/agent-skills
Godot 4.x GDScript Best Practices Guide AI agents in writing high-quality GDScript code for Godot 4.x. This skill provides coding standards, architecture patterns, and templates for game development. When to Use This Skill Use this skill when: Generating new GDScript code Creating or organizing Godot scenes Designing game architecture and node hierarchies Implementing state machines, object pools, or save systems Answering questions about GDScript patterns or Godot conventions Reviewing GDSc...
 1.6K
3068 active-research actionbook/actionbook
Active Research Analyze any topic, domain, or paper and generate a beautiful HTML report using Actionbook Browser — featuring SPA-aware navigation, network idle detection, batch operations, and intelligent page analysis. Enhanced Browser Capabilities Capability Description Page load wait wait-idle — monitors fetch/XHR until network settles SPA content wait-fn — wait for JS conditions before extracting Page understanding snapshot --filter interactive --max-tokens N — focused, budget-friendly Popu...
 1.6K
3069 chrome-extension-development mindrally/skills
Chrome Extension Development You are an expert Chrome extension developer, proficient in JavaScript/TypeScript, browser extension APIs, and web development. Code Style and Structure Write clear, modular TypeScript code with proper type definitions Follow functional programming patterns; avoid classes Use descriptive variable names (e.g., isLoading, hasPermission) Structure files logically: popup, background, content scripts, utils Implement proper error handling and logging Document code with ...
 1.6K
3070 swiftui-uikit-interop dpearson2699/swift-ios-skills
SwiftUI-UIKit Interop Bridge UIKit and SwiftUI in both directions. Wrap UIKit views and view controllers for use in SwiftUI, embed SwiftUI views inside UIKit screens, and synchronize state across the boundary. Targets iOS 26+ with Swift 6.2 patterns; notes backward-compatible to iOS 16 unless stated otherwise. See references/representable-recipes.md for complete wrapping recipes and references/hosting-migration.md for UIKit-to-SwiftUI migration patterns. Contents UIViewRepresentable Protocol UIV...
 1.6K
3071 wordpress-router wordpress/agent-skills
WordPress Router When to use Use this skill at the start of most WordPress tasks to: identify what kind of WordPress codebase this is (plugin vs theme vs block theme vs WP core checkout vs full site), pick the right workflow and guardrails, delegate to the most relevant domain skill(s). Inputs required Repo root (current working directory). The user’s intent (what they want changed) and any constraints (WP version targets, WP.com specifics, release requirements). Procedure Run the project triage...
 1.6K
3072 swiftdata dpearson2699/swift-ios-skills
SwiftData Persist, query, and manage structured data in iOS 26+ apps using SwiftData with Swift 6.2. Contents Model Definition ModelContainer Setup CRUD Operations @Query in SwiftUI Predicate FetchDescriptor Schema Versioning and Migration Concurrency (@ModelActor) SwiftUI Integration Common Mistakes Review Checklist References Model Definition Apply @Model to a class (not struct). Generates PersistentModel , Observable , Sendable . @Model class Trip { var name : String var destination : String ...
 1.6K
3073 swift-concurrency dpearson2699/swift-ios-skills
Swift Concurrency Fast Path Before proposing a fix: Analyze Package.swift or .pbxproj to determine Swift language mode, strict concurrency level, default isolation, and upcoming features. Do this always, not only for migration work. Capture the exact diagnostic and offending symbol. Determine the isolation boundary: @MainActor , custom actor, actor instance isolation, or nonisolated . Confirm whether the code is UI-bound or intended to run off the main actor. Project settings that change concurr...
 1.6K
3074 pwa-development alinaqi/claude-bootstrap
PWA Development Skill Load with: base.md Purpose: Build Progressive Web Apps that work offline, install like native apps, and deliver fast, reliable experiences across all devices. Core PWA Requirements ┌─────────────────────────────────────────────────────────────────┐ │ THE THREE PILLARS OF PWA │ │ ───────────────────────────────────────────────────────────── │ │ │ │ 1. HTTPS ...
 1.6K
3075 storekit dpearson2699/swift-ios-skills
StoreKit 2 In-App Purchases and Subscriptions Implement in-app purchases, subscriptions, and paywalls using StoreKit 2 on iOS 26+. Use only the modern Product , Transaction , StoreView , and SubscriptionStoreView APIs. Never use the deprecated original StoreKit ( SKProduct , SKPaymentQueue , SKStoreReviewController ). Contents Product Types Loading Products Purchase Flow Transaction.updates Listener Entitlement Checking SubscriptionStoreView (iOS 17+) StoreView (iOS 17+) Subscription Status Chec...
 1.6K
3076 apple-on-device-ai dpearson2699/swift-ios-skills
On-Device AI for Apple Platforms Guide for selecting, deploying, and optimizing on-device ML models. Covers Apple Foundation Models, Core ML, MLX Swift, and llama.cpp. Contents Framework Selection Router Apple Foundation Models Overview Core ML Overview MLX Swift Overview Multi-Backend Architecture Performance Best Practices Common Mistakes Review Checklist References Framework Selection Router Use this decision tree to pick the right framework for your use case. Apple Foundation Models When to ...
 1.6K
3077 release-it wondelai/skills
Release It! Framework Framework for designing, deploying, and operating production-ready software systems. Based on a fundamental truth: the software that passes QA is not the software that survives production. Production is a hostile environment -- and your system must be built to expect and handle failure at every level. Core Principle Every system will eventually be pushed beyond its design limits. The question is not whether failures will happen, but whether your system degrades gracefully o...
 1.6K
3078 novel-architect junaid18183/novel-architect-skills
A comprehensive skill for literary fiction writers that transforms vague story ideas into structured novel projects through patient, emotionally-attentive dialogue. Core Philosophy Reflection before construction. Emotional truth before narrative logic. This skill: - Works through conversation first, writing only after understanding is complete - Proposes content section-by-section, waiting for approval at each step - Stores approved sections in memory, writing files only when complete - ...
 1.6K
3079 novel-writer-cn yangsonhung/awesome-agent-skills
小说写作助手 专业的小说创作支持，涵盖构思、规划、写作到修改的全流程。 何时使用 当用户提出以下需求时使用本技能： 从想法或类型出发，新建小说 基于已有章节进行续写 设计角色（主角、反派、配角）与角色弧线 构建世界观（势力、规则、魔法体系、时代背景） 对已有内容做润色、重写或节奏优化 不要使用 以下场景不应使用本技能： 非创作类事实问答（如百科、实时资讯查询） 法律、医疗、金融等专业建议 抄袭或要求复制受版权保护作品风格的请求 违反平台安全规则的有害内容请求 使用说明 先判断任务类型（新建、续写、角色、世界观、修改）。 先问最少必要信息，再开始输出。 按本文件对应流程章节执行。 优先复用 references/ 与 assets/templates/ 中的材料。 保持视角、语气、角色动机与上下文一致。 输出前做一次情节连贯性与语言质量自检。 工作流程 第一步：确定需求类型 根据用户请求识别任务类型： 任务类型 用户示例 操作 新小说创作 "帮我写一部科幻小说" 进入 新建小说流程 章节续写 "给这个故事续写一章" 进入 续写流程 角色设计 "设计一个反派角色" 进入 角色设计流程 世界...
 1.6K
3080 swift-testing dpearson2699/swift-ios-skills
Swift Testing Swift Testing is the modern testing framework for Swift (Xcode 16+, Swift 6+). Prefer it over XCTest for all new unit tests. Use XCTest only for UI tests, performance benchmarks, and snapshot tests. Contents Basic Tests @Test Traits expect and require @Suite and Test Organization Known Issues Additional Patterns Parameterized Tests In Depth Tags and Suites In Depth Async Testing Patterns Traits In Depth Common Mistakes Test Attachments Exit Testing Review Checklist MCP Integration ...
 1.6K
3081 swiftui-navigation dpearson2699/swift-ios-skills
SwiftUI Navigation Navigation patterns for SwiftUI apps targeting iOS 26+ with Swift 6.2. Covers push navigation, multi-column layouts, sheet presentation, tab architecture, and deep linking. Patterns are backward-compatible to iOS 17 unless noted. Contents NavigationStack (Push Navigation) NavigationSplitView (Multi-Column) Sheet Presentation Tab-Based Navigation Deep Links Common Mistakes Review Checklist References NavigationStack (Push Navigation) Use NavigationStack with a NavigationPath bi...
 1.6K
3082 widgetkit dpearson2699/swift-ios-skills
WidgetKit and ActivityKit Build home screen widgets, Lock Screen widgets, Live Activities, Dynamic Island presentations, Control Center controls, and StandBy surfaces for iOS 26+. See references/widgetkit-advanced.md for timeline strategies, push-based updates, Xcode setup, and advanced patterns. Contents Workflow Widget Protocol and WidgetBundle Configuration Types TimelineProvider AppIntentTimelineProvider Widget Families Interactive Widgets (iOS 17+) Live Activities and Dynamic Island Control...
 1.6K
3083 swift-charts dpearson2699/swift-ios-skills
Swift Charts Build data visualizations with Swift Charts targeting iOS 26+. Compose marks inside a Chart container, configure axes and scales with view modifiers, and use vectorized plots for large datasets. See references/charts-patterns.md for extended patterns, accessibility, and theming guidance. Contents Workflow Chart Container Mark Types Axis Customization Scale Configuration Foreground Style and Encoding Selection (iOS 17+) Scrollable Charts (iOS 17+) Annotations Legend Vectorized Plots ...
 1.6K
3084 executive resume writer paramchoudhary/resumeskills
Use this skill when the user: - Is applying for C-suite, VP, or Director roles - Has 15+ years of experience in senior leadership - Needs to emphasize strategic leadership over tactical skills - Mentions: "executive resume", "C-suite", "VP resume", "senior leadership", "board", "executive search" Core Capabilities - Write resumes for C-suite and VP-level positions - Emphasize strategic leadership and business transformation - Showcase P&L responsibility and organizational impact - Bala...
 1.6K
3085 agentwallet frames-engineering/skills
AgentWallet AgentWallet provides server wallets for AI agents. Wallets are provisioned after email OTP verification. All signing happens server-side and is policy-controlled. TL;DR - Quick Reference FIRST: Check if already connected by reading ~/.agentwallet/config.json . If file exists with apiToken , you're connected - DO NOT ask user for email. Need to connect (no config file)? Ask user for email → POST to /api/connect/start → user enters OTP → POST to /api/connect/complete → save API token. ...
 1.6K
3086 swiftui-layout-components dpearson2699/swift-ios-skills
SwiftUI Layout & Components Layout and component patterns for SwiftUI apps targeting iOS 26+ with Swift 6.2. Covers stack and grid layouts, list patterns, scroll views, forms, controls, search, and overlays. Patterns are backward-compatible to iOS 17 unless noted. Contents Layout Fundamentals Grid Layouts List Patterns ScrollView Form and Controls Searchable Overlay and Presentation Common Mistakes Review Checklist References Layout Fundamentals Standard Stacks Use VStack , HStack , and ZStack f...
 1.6K
3087 swiftui-liquid-glass dpearson2699/swift-ios-skills
SwiftUI Liquid Glass Overview Use this skill to build or review SwiftUI features that fully align with the iOS 26+ Liquid Glass API. Prioritize native APIs (glassEffect, GlassEffectContainer, glass button styles) and Apple design guidance. Keep usage consistent, interactive where needed, and performance aware. Workflow Decision Tree Choose the path that matches the request: 1) Review an existing feature Inspect where Liquid Glass should be used and where it should not. Verify correct modifie...
 1.6K
3088 career changer translator paramchoudhary/resumeskills
Use this skill when the user: - Is switching careers or industries - Wants to translate their experience for a new field - Needs help identifying transferable skills - Mentions: "career change", "switching careers", "new industry", "transferable skills", "pivot" Core Capabilities - Identify transferable skills across industries - Translate experience into new industry language - Reframe achievements for target roles - Bridge skill gaps strategically - Position career changes positivel...
 1.6K
3089 humanize humanizerai/agent-skills
Humanize AI Text Transform AI-generated content into natural, human-like writing using the HumanizerAI API. How It Works When the user invokes /humanize , you should: Parse $ARGUMENTS for text and optional --intensity flag Call the HumanizerAI API to humanize the text Present the humanized text with before/after scores Show remaining credits Parsing Arguments The user may provide: Just text: /humanize [their text] With intensity: /humanize --intensity aggressive [their text] Default intensity is...
 1.6K
3090 engineering-advanced-skills alirezarezvani/claude-skills
Engineering Advanced Skills (POWERFUL Tier) 25 advanced engineering skills for complex architecture, automation, and platform operations. Quick Start Claude Code /read engineering/agent-designer/SKILL.md Codex CLI npx agent-skills-cli add alirezarezvani/claude-skills/engineering Skills Overview Skill Folder Focus Agent Designer agent-designer/ Multi-agent architecture patterns Agent Workflow Designer agent-workflow-designer/ Workflow orchestration API Design Reviewer api-design-reviewer/ REST/Gr...
 1.6K
3091 offer comparison analyzer paramchoudhary/resumeskills
Use this skill when the user: - Has multiple job offers to compare - Needs to evaluate total compensation - Wants to make a data-driven job decision - Is weighing different opportunities - Mentions: "compare offers", "multiple offers", "which job", "offer comparison", "deciding between jobs" Core Capabilities - Compare total compensation across offers - Evaluate non-monetary factors - Create weighted decision frameworks - Calculate true offer value - Identify hidden costs and benefit...
 1.6K
3092 excel analysis davila7/claude-code-templates
Excel Analysis Quick start Read Excel files with pandas: import pandas as pd Read Excel file df = pd . read_excel ( "data.xlsx" , sheet_name = "Sheet1" ) Display first few rows print ( df . head ( ) ) Basic statistics print ( df . describe ( ) ) Reading multiple sheets Process all sheets in a workbook: import pandas as pd Read all sheets excel_file = pd . ExcelFile ( "workbook.xlsx" ) for sheet_name in excel_file . sheet_names : df = pd . read_excel ( excel_file , sheet_name = sheet_name ) p...
 1.6K
3093 typescript-e2e-testing bmad-labs/skills
E2E Testing Skill E2E testing validates complete workflows from user perspective, using real infrastructure via Docker. Workflows For comprehensive step-by-step guidance, use the appropriate workflow: Workflow When to Use Setup E2E Test Setting up E2E infrastructure for a new or existing project Writing E2E Test Creating new E2E test cases with proper GWT pattern Review E2E Test Reviewing existing tests for quality and correctness Running E2E Test Executing tests with proper verification Deb...
 1.5K
3094 story-long-write worldwonderer/oh-story-claudecode
story-long-write：长篇网文写作 你是网络小说创作教练。你的任务是帮用户从零开始写一本长篇网络小说，从选题确认到大纲搭建再到正文输出。 核心信念：网文写作是工程，不是灵感。 靠灵感写不了 200 万字，靠工程可以。 核心哲学 原则 1：大纲是地图，不是牢笼 大纲告诉你方向，但具体走哪条路可以灵活调整。没有大纲的长篇 100% 会崩，大纲太细的长篇会失去弹性。目标是「粗到能看见全局，细到能坐下就写」。 原则 2：日更是底线，质量是上限 网文是连载艺术。日更的节奏感比单章的完美更重要。一个稳定日更 4000 字的作者，比一个三天打鱼两天晒网但每章 8000 字的作者走得更远。 原则 3：爽点密度决定存亡 长篇网文的核心指标是追读率。追读率由爽点密度决定——不是每章都有爽点，而是每 3000-5000 字必须有一个让读者「爽」的情绪节点。 原则 4：先写 30 章，再谈其他的 很多新人卡在「准备」阶段没完没了。大纲不需要完美，设定不需要详尽，写 30 章（约 12 万字）自然会发现问题和方向。30 章之前不要改大纲。 写作流程 Phase 1：确认选题方向 如果用户已有方向 →...
 1.5K
3095 story-long-analyze worldwonderer/oh-story-claudecode
story-long-analyze：长篇网文拆文 你是网络小说结构分析师。 核心信念：看懂别人的爆款，才能写出自己的爆款。 Phase 1：确认拆解对象 + 路由 问用户： 「你要拆哪本书？（书名+平台）你想重点看什么？（黄金三章/整体结构/某个具体章节）」 如果没有明确目标，按题材或用户想写的类型推荐 2-3 本对标作品。 路由决策 用户提供文本文件路径？ ├─ 是 → 深度模式（Phase 2B） └─ 否 → 用户说「深度拆解/完整拆解/系统拆解」？ ├─ 是 → 深度模式（Phase 2B） └─ 否 → 快速模式（Phase 2-4） Phase 2-4：快速模式 按 output-templates.md 中的模板输出： Phase 2 ：黄金三章逐章拆解。按 output-templates.md 1.1 模板输出第一章，第二三章按 1.2 说明追加关注点。 Phase 3 ：整体结构拆解。按 output-templates.md 1.3 输出故事线分析、人物架构、节奏地图。 Phase 4 ：输出拆文报告。按 output-templates.md 1.4 模板输出...
 1.5K
3096 story-short-analyze worldwonderer/oh-story-claudecode
story-short-analyze：短篇网文拆文 你是短篇小说结构分析师。 核心信念：短篇的本质是情绪炸弹。拆文就是拆弹——看它用什么引信、什么火药、什么时间引爆。 Phase 1：确认拆解对象 + 题材路由 问用户： 「你要拆哪篇？（标题+平台/来源）想重点看什么？（整体结构/反转设计/情绪曲线/开头技巧）」 题材路由 用户提到具体题材（追妻/重生/虐文/...）？ ├─ 是 → 加载 genre-frameworks-unified.md 对应题材的「短篇视角」章节 └─ 否 → 使用通用模板（Phase 2-6） 题材识别关键词参考： 追妻火葬场 / 渣男后悔 → 追妻 重生复仇 / 前世今生 → 重生复仇 死后视角 / 灵魂旁观 → 死人文学 小三 / 出轨 / 知三当三 → 小三 世情 / 现实 / 婆媳 → 世情 仙侠 / 修仙 / 门派 → 仙侠 Phase 2-6：拆文流程 按 output-templates.md 中的模板输出： Phase 2 ：全篇结构拆解。按 output-templates.md Phase 2 输出结构划分和基本信息。 Phase 3 ...
 1.5K
3097 story-deslop worldwonderer/oh-story-claudecode
story-deslop：网文去AI味 你是网文润色专家。你的任务是帮用户把AI味浓重的网文文本改写自然，让文字读起来像人写的。 核心信念：AI写的不是不好，是太好了——好到假。人写东西有毛边、有口语、有跳跃，AI写的太圆滑、太工整、太正确。 核心哲学 原则 1：不是改错，是改味 AI味不是语法错误，不需要"修正"。AI味是一种风格问题——过于书面化、过于对仗工整、过于面面俱到。去AI味的本质是把文字从"完美"拉回"真实"。 原则 2：改最少，效果最大 去AI味不是重写。目标是改最少的字，让整段文字的"味"变过来。能改一个词就不改一句，能删一句就不重写一段。 原则 3：保留作者意图 去AI味只改"怎么说"，不改"说什么"。剧情、人设、情节走向一概不动。如果原文有逻辑问题，那不是去AI味的活。 真人写作基准 去AI味需要知道"人味"是什么样的。以下是从大量热门网文中提炼的人类写作特征，作为对比基准： 真人写作特征（与AI对比） 维度 真人写法 AI写法 段落长度 1-3句为主，偶尔1句独占1行 每段4-6句，整齐均匀 对话标签 60%+无标签，用动作替代"说" 几乎每句都有"说道/问道"...
 1.5K
3098 story-short-write worldwonderer/oh-story-claudecode
story-short-write：短篇网文写作 你是短篇网文创作教练。你的任务是帮用户从构思到成稿写出一篇完整的短篇小说。 核心信念：短篇写的是情绪，不是故事。读者记住的永远是情绪，不是剧情。 核心哲学 原则 1：先定情绪，再定故事 写短篇之前，先想清楚你想让读者体验什么情绪。是意难平的遗憾？是反转的震撼？是虐完之后的治愈？情绪定了，故事自然就有了方向。 原则 2：一个反转撑起一篇短篇 短篇不需要复杂的世界观和多线叙事。一个强有力的反转就够了。所有铺垫都为这个反转服务，所有情绪都为这个反转蓄力。 原则 3：删到不能再删为止 短篇的第一稿一定太长。好短篇是删出来的，不是写出来的。每句话都要回答：这句话删了会影响读者体验吗？如果不影响，删。 原则 4：开头决定生死，结尾决定传播 开头 3 句话决定读者看不看，结尾决定读者转不转。中间写得再好，开头不行没人看；中间写得再好，结尾不行没人传。 写作流程 Phase 1：确定情绪目标 问用户： 「你想让读者读完什么感觉？有没有想写的题材方向或灵感？」 如果用户有明确想法 → 直接进入 Phase 2。 如果用户只有模糊想法 → 帮用户做情绪选择...
 1.5K
3099 karpathy-guidelines multica-ai/andrej-karpathy-skills
Karpathy Guidelines Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls. Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment. 1. Think Before Coding Don't assume. Don't hide confusion. Surface tradeoffs. Before implementing: State your assumptions explicitly. If uncertain, ask. If multiple interpretations exist, present them - don't pick silently. If a simpler approach exists, say so...
 1.5K
3100 story-long-scan worldwonderer/oh-story-claudecode
story-long-scan：长篇网文扫榜 你是网络小说市场分析师。你的任务是帮用户看清长篇网文市场的真实格局，找到值得进入的题材方向。 核心信念：数据不会说谎，但数据需要正确解读。 排行榜上的书不代表你能写，但排行榜上反复出现的模式代表市场需求。 核心哲学 原则 1：扫榜不是看排名，是看模式 排名每天都在变，但模式不会。你扫榜要找的是：哪些题材反复出现、哪些设定被反复验证、哪些套路读者买账。一本书上榜可能是运气，十个同类题材上榜就是趋势。 原则 2：流量型平台和付费型平台看的东西不同 番茄看的是流量和完读率，起点看的是订阅和追读，晋江看的是收藏和积分。不同平台的成功标准不同，扫榜方法也不同。 原则 3：扫榜的目的是找到你能写的爆款题材 不是什么火写什么，而是什么火且你能驾驭就写什么。扫完榜要做可行性判断，不是照搬。 扫榜流程 Phase 1：确认平台和方向 问用户： 「你想看哪个平台？（起点/番茄/晋江/其他）有没有关注的题材方向？」 关键判断： 用户已有方向 → 针对该方向做深度扫榜 用户没有方向 → 做全榜概览 + 找趋势 用户想跨平台比较 → 做平台对比分析 Phase 1....
 1.5K