Most popular Claude skills · page 57

Agent skills for Claude Code, Claude.ai and other agents, ranked by popularity: GitHub stars, forks, and how many curated lists and repos include them.

3,968 skills · showing 2689–2736

  1. 2689Enterprise Architectrafalr100/enterprise-architect-skillOperate as a world-class Enterprise Architect (FAANG / top-tier consulting calibre) grounded in TOGAF, Zachman, and modern EA practice. Opens with discovery — asks the clarifying questions that materially change the architecture before producing any deliverable. Activates when the user asks for enterprise-architecture work — target architectures, reference architectures, architecture patterns, standards, principles, capability maps, technology strategy, roadmaps, trade-off analysis, architecture decision records, governance, or audience-tiered architecture presentations (C-level/board, solutio7
  2. 2690Gamma Watermark Removergammaremover/gamma-watermark-remover-skillRemove the "Made with Gamma" watermark from PDF and PPTX files exported from Gamma.app. Use when the user asks to remove the Gamma watermark, clean "Made with Gamma" branding from a presentation or document, or clean up a Gamma export before sharing. Works on files the user created; structural and lossless.12
  3. 2691Gingiris Aso GrowthGingiris/gingiris-aso-growth🇺🇸 ASO & Mobile App Growth Playbook 2026 — Complete App Store Optimization guide. ASO keyword ranking, App Store & Google Play listing optimization, app cold start, UGC creator operations, TikTok/Instagram/YouTube Shorts marketing, AI-matrix content scaling, mobile user acquisition. 🇨🇳 ASO 增长与 App 冷启动权威指南 — 从应用商店优化到 UGC 运营、多平台内容策略、AI 矩阵号的完整实操手册。 🇯🇵 ASO&アプリコールドスタート成長ガイド — App Store最適化からUGC運営、マルチプラットフォーム戦略、AIマトリックスまで。 🇰🇷 ASO 및 앱 콜드 스타트 성장 플레이북 — 앱스토어 최적화부터 UGC 운영, 멀티플랫폼 전략, AI 매트릭스까지. Triggers: "ASO" | "App Store Optimization" | "ASO keywords" | "App Store ranking" | "Google Play optimiz12
  4. 2692Interview Transcript OrganizerAiYuSherry/interview-transcript-organizer将面试/访谈录音转写文本整理为规范 Word 文档,含面试复盘表。输出三版文档:面试总复盘(复盘表格)、问题总结(精简 Q&A)、完整记录(完整回答)。格式:中文楷体英文新罗马,问题蓝色加粗,回答黑色左对齐。自动按 `N-公司名面试 - YYYYMMDD/` 路径保存。12
  5. 2693Ironloopedouard-claude/ironloopVerification-first software engineering harness with 5 layers (spec → gen → test → sim → pentest). Use when generating, reviewing, or planning code with AI agents, especially for Rust projects, new feature work, legacy migrations, or any task where code correctness must be guaranteed. Activates on phrases like "build a", "implement", "refactor", "review this code", "migrate from", "add tests for", or when the user describes a coding task with correctness or security requirements.10
  6. 2694Linkly Quote Cardslogog782-cmyk/linkly-quote-cardsLinkly 金句卡 v2「双色印刷版」——把 Linkly 分类笔记里的金句印成双墨编辑印刷卡(halftone 网点影像+文字压图+活字落款)。当用户说 出金句卡、金句卡 no.XX、金句海报、金句配图、印刷金句卡、双色金句卡、给这句话出张卡 时使用本 skill。生图唯一走 ~/飞书/imagegen/gen.py(Seedream),逐字校验硬门。旧纸 zine 风为 v1 已归档版式,仅点名"zine 版/旧纸版"才复刻。12
  7. 2695Material Design 3gdlbo/material-skillDesign, implement, or review Material 3 and Material 3 Expressive interfaces for Android Compose, Android Views, Wear OS, and the web. Use for Material Design, M3, Material You, adaptive Material layouts, Material-focused Android UI modernization, or Material web component work; do not apply it to a non-Material design unless the user asks to adopt Material12
  8. 2696Modern Pptlainshao/modern-ppt生成现代分享/投屏风格的单文件网页 PPT(横向翻页·专业极简风·干净排版·3 套可切配色)。当用户要做线下分享、演讲、发布会的网页 deck,或提到「modern ppt」「做个分享 PPT」「投屏 deck」「网页 PPT」「把这段做成 slides」时使用。内置 12 个版式 + 交互动效(count-up / Chart.js 图表) + 3 套配色(默认安全橙,可切明亮蓝/柔和粉)+ 一套排版硬规范(单一 body 字号 token、标题靠分隔线、正文不上色、底部安全区等),产出一致、可直接投屏放映。12
  9. 2697NetopsCon-Benksl/NetOpsRoute authorized VPS networking and proxy work to onboarding, read-only scanning, building, repair, or fleet management. Use for VPS access, 3x-ui/Xray/VLESS Reality/Hysteria2, DNS/TUN/routing failures, node performance, or ongoing multi-VPS operations. 典型中文请求:VPS 连不上、节点慢或掉线、搭建或修改节点、面板打不开、多台 VPS 统一维护。12
  10. 2698Orcarouter ToolsContinuum-AI-Corp/orcarouter-tools-skillsDiscover, inspect and run pay-per-call tools (web search, scraping, data enrichment, and more) AS an OrcaRouter agent, billed to the workspace wallet with the agent's own budget applied. Use when a task needs an external capability the agent does not have — a web search, a company lookup, a page scrape — and the workspace has enabled the OrcaRouter Tool Router (the /v1/tools HTTP endpoints).12
  11. 2699Patent Filing QcLeonardHope/Claude-Skill-for-Patent-Filing-Quality-ControlComprehensive quality control for U.S. patent application filing documents. Use when the user asks to QC, check, validate, or review patent filing documents before submission to the USPTO. Performs 70+ automated and manual checks across specification, drawings, ADS, declaration, assignment, and power of attorney documents. Detects cross-document inconsistencies, formatting issues, missing required fields, and common errors.12
  12. 2700Re WorkstationSUNYT772/RE-Workstation用于逆向分析(APK、二进制、JS、iOS、固件、托管与编译语言)、Web/API、安全研究、补丁与版本差分、恶意代码、LLM与agent安全、供应链、CTF、经验检索、技术报告和图表。任务命中时提供专项知识与排版参考。10
  13. 2701Rust Elegantfuqiuluo/rust-elegantRust 优雅开发规范,必须在以下场景触发:为 Rust 项目写代码、review Rust 代码、设计 Rust 项目结构、处理 Rust 错误类型时。覆盖命名、注释规范、枚举设计、trait 抽象、项目结构、错误处理、所有权、迭代器、宏、内存分配、match 穷尽性、unsafe 等所有 Rust 惯用法。只要任务涉及写或修改 Rust 代码,必须读取此 skill。12
  14. 2702Ship PageZooeyii/ship-page-skillCreate stunning, interactive landing pages for products, startups, and side projects — zero dependencies, single HTML file. Use this skill whenever the user wants to build a landing page, product page, launch page, marketing page, or any promotional web page for their app, tool, SaaS, open-source project, or personal brand. Also triggers when users say "I need a website for my product", "help me launch", "make a page for my app", or want to convert a README into a visual landing page. Works great for Product Hunt launches, GitHub project pages, and indie hacker ship days.12
  15. 2703Taxue Halftonetaxueseek/taxue-halftone半调海报:用限墨+网点把任意主题做成有结构、有质感、可复用的艺术封面。支持多种印刷语言(半调/孔版/双色/木刻/蓝晒/蓝染/复印机、1-bit 剪影、撕纸拼贴),按风格给出一致又有特色的封面。六项不变式出图前先定:纸色、墨色角色、叠印方式、印刷机制、主体走向、字图音量。触发词:半调海报、艺术封面、网点、孔版、双色、Riso、duotone、木刻、蓝晒、蓝染、蓝染海报、物影、蓝晒物影、反俗套蓝染、复印机美学、不完美印刷拼贴、撕纸拼贴、编辑型印刷拼贴、有意不完美、点阵解构、丝网海报、剪纸、窗花、中式剪纸、网点剪纸、经典致敬、风格模仿、致敬、名画、艺术流派、年代美学、视觉风格转译、波普、波点、圆点场、点画、视错觉、扁平矢量图形、艺术展览海报、平台封面(B站/小红书/抖音/公众号/头像/超宽)、主题结构印刷封面、限墨封面。不用于:全彩实拍、UI、图表、模板拼贴。12
  16. 2704Travel PlannerSquirrelSong5/travel-planner-skill面向中国大陆行程的旅行规划、行前复核与临场调整 Skill。使用地图、官方渠道、OTA、目的地攻略和餐饮指南等实时信息,生成并校验包含路线、餐饮、预算、预订状态、Plan B 和安全提醒的对话版攻略与响应式单文件 HTML。Use when the user asks to plan, optimize, review, update, recheck, or publish a domestic trip itinerary, including requests based on flight, train, hotel, attraction, restaurant, weather, safety, or route details.12
  17. 2705VaultAnYejun/blind-vaultStore and use the user's API keys, passwords, tokens, and credentials WITHOUT ever seeing their values. Trigger whenever the user mentions an API key, token, password, credential, login, secret, or .env file; wants to store or rotate one; or a command needs auth / fails with 401/403/"missing key". Values live in the macOS Keychain; the agent only ever reads a pointer manifest.12
  18. 2706Webmanzjkal/webman-skillExpert skill for the webman framework (a long-lived, in-memory PHP framework based on workerman). Covers routing, controllers, middleware, database/Redis, custom processes, timers, coroutines (v2), plugin development, and guarding against memory leaks and cross-request state pollution under the resident process model. Use when the project has start.php, config/process.php, or support/bootstrap.php, or when the user mentions webman, workerman, 常驻内存 PHP, 协程 PHP, or long-lived/in-memory PHP.12
  19. 2707Zotero Searchurschrei/zotero_search_skillSearch the user's local Zotero library, find related papers via Semantic Scholar, and discover citations/references. **Claude Code only** - this skill requires a local Zotero instance and access to a port on localhost. Use when the user asks to search their Zotero library, find papers on a topic, explore citations of a paper, or find related literature. Supports cross-referencing Semantic Scholar results against the local library.12
  20. 2708Apple Liquid GlassxenitV1/liquid-glass-skillApple's Liquid Glass design language (iOS 26 / macOS 26 HIG) made buildable on any platform: the content/chrome two-layer model, regular vs clear glass, real refraction (content bending at the rim), the rim light, type scales, system colours, component shapes, and Reduce Motion/Transparency/Increase Contrast fallbacks. Ships a CSS token file and a refraction script for the web, plus routes for SwiftUI/UIKit, Android Compose (Haze), Flutter, Electron, Tauri, Windows and Linux. Use when building or reviewing any UI that should look Apple-made or "liquid glass": "iOS style", "macOS style", "Liqui11
  21. 2709Course Helperxxxhhhccc458/course-helper课程学习资料整理与习题解答方法:把讲义、课件、PDF 整理成复习大纲,解答习题,生成公式速查表与易错辨析;并维护跨会话的教学交接文档(学习进度)、管理项目提示词库、按模块拆分项目资料档案(B 层)。当用户在课程学习类项目中要求整理讲义或课件、编写或续写复习大纲、讲解课程概念、解答作业题(HW/习题)、续写学习进度或教学交接文档、登记常用提示词时使用。不适用于纯代码工程项目。13
  22. 2710DestinyscoutScofy0123/Destiny-job-scoutBOSS直聘岗位监控雷达。通过 opencli 抓取 BOSS 直聘高薪岗位数据,支持多关键词并行搜索、薪资过滤、结构化 JSON 输出。当用户需要监控招聘市场、追踪特定岗位趋势、做薪资调研时使用。11
  23. 2711Ea Skilljzl-maker/EA-SKILL嵌入式 AI 开发管家,支持 Keil/CubeMX 与 ESP32 的 ESP-IDF/PlatformIO/Arduino 工程。当用户要求嵌入式功能开发、外设接入、编译烧录、串口/JTAG/RTT 调试、固件验证、测试生成或芯片文档解析时使用。10
  24. 2712Extract Youtube TranscriptRtemm/claude-skillsUse this skill when the user wants to extract audio from a YouTube video and transcribe it. Triggers include: 'extract transcript from youtube', 'transcribe this video', 'get transcript from YouTube', 'extract audio and transcribe', or any message that includes a YouTube URL and asks for a transcript or transcription.13
  25. 2713Faster WhisperThePlasmak/faster-whisperLocal speech-to-text using faster-whisper. 4-6x faster than OpenAI Whisper with identical accuracy; GPU acceleration enables ~20x realtime transcription. SRT/VTT/TTML/CSV subtitles, speaker diarization, URL/YouTube input, batch processing with ETA, transcript search, chapter detection, per-file language map.10
  26. 2714Feature MarkerViniciuscarvalho/Feature-markerSkill-first run-through feature workflow for Claude, Codex, and Gemini. Use when the user asks to implement a feature through PRD, TechSpec, Tasks, verification, local commit, and branch handoff. The npm package installs skill files only; the LLM skill performs the workflow.11
  27. 2715Fortune Tellingsolplum/high-confidence-mingli-skill高置信度命理对话伴侣——八字/紫微斗数/七政四余三盘互译,内置三套确定性排盘引擎(Meeus 定气八字 / iztro 紫微 / 自研恒星制七政),解读以典籍考证为准(references 查表、论断挂出处)。运势查询、推算推演、共鸣溯源、通用知识、详批解读五模式自动识别。斯多葛收束,每次自校准。触发词:今日运势、本月运势、今年运势、X月运势、感情运、事业运、财运、健康运、刷到/看到命理内容、算一下/推演、命理概念问答、详批、批一命、帮我详细看命盘。11
  28. 2716Midnight CompactADAvault/midnight-skillWrite, test, and deploy Compact smart contracts for Midnight. Use when writing privacy-preserving contracts, ZK circuits, shielded tokens, or any on-chain Midnight code. Triggers on: Midnight, Compact, smart contract, zero-knowledge, ZK, shielded, circuit, witness, ledger, proof server, DUST, NIGHT, disclose, Zswap. Covers Compact language syntax, privacy model, circuit patterns, testing, security best practices, SDK integration, and wallet connectivity.10
  29. 2717Multi SearchNex-ZMH/Agent-websearch-skill智能多引擎搜索,自动检测网络环境并按优先级切换:DuckDuckGo -> Tavily -> Bing API -> Bing爬虫。支持自动配额管理和网络缓存。Invoke when user needs web search with automatic engine selection and network adaptation.11
  30. 2718Notebooklm Course Builderhmj1026/notebooklm-course-builder以條件式瀏覽器自動化或 14 階段嚮導建構 NotebookLM 課程教材。適用於:(1) 將課程大綱轉為包含來源引用、逐節講義、Quiz 與 Study Guide 的完整課程;(2) 規劃 Notebook 與研究分群、來源審核、Coverage 分析;(3) 自動操作 NotebookLM 或延續既有建置進度。13
  31. 2719Patton Protocolvladimirrott/patton-protocolCoordinate bounded coding-agent missions when independent delegation improves the task.13
  32. 2720Planners Quali BoxthePlannerIvan/planners-quali-box面向社媒笔记、评论、搜索词、开放题、访谈摘录、品牌与竞品内容的定性分析工具箱。先检查数据结构与证据能力,向用户说明推荐方法、方法步骤、预期信息和边界并取得确认,再在消费者洞察、情感定位、沟通策略、品类颠覆、文化结构、消费任务与价值链、品牌关系或品牌社群路线中选择一个主方法,按需加载最多两个辅助镜头,交付来源清楚、可追溯的 Markdown 分析报告与单文件 HTML。适用于用户要求从不同规模、结构和证据角色的材料中选择合适方法、提炼洞察、比较品牌或形成策略判断;不要求用户预先懂方法或替模型做路由。13
  33. 2721Poster Grid InspectorYgria/poster-grid-inspectorAnalyze a poster or layout design image to detect its underlying grid system and export grid guide overlays. Use when the user wants to (1) identify the layout grid of a poster/design image (Swiss modular, N-column, asymmetric, baseline, golden ratio, rule of thirds, diagonal, radial, freeform, etc.), (2) get detected layout elements, keylines, and alignment notes, or (3) export the detected grid as an SVG overlay file or CSS Grid / Tailwind code. By default, use the host model's native multimodal vision capability; do not upload the image or call an external API.13
  34. 2722Procedural LandscapesCK42BB/procedural-landscapes-threejsGenerate procedural 3D landscapes and terrain in Three.js using WebGPU compute shaders with automatic WebGL2 fallback. Covers heightmap generation via FBM noise, ridged multifractal, and domain warping; chunked LOD terrain meshes; slope-based multi-material texturing; procedural water planes; atmospheric sky rendering; and instanced vegetation scattering. Use when building terrain generators, open-world environments, landscape visualizers, flight simulators, or any 3D scene requiring procedural ground surfaces. Triggers: "procedural terrain", "landscape generator", "heightmap", "terrain mesh",11
  35. 2723Rails LLM Integrationnagstler/rails-llm-integrationProduction-grade LLM integration patterns for Ruby on Rails applications. USE THIS SKILL when the user needs to: integrate OpenAI, Claude, or any LLM API into a Rails app; use ruby_llm gem or langchain-rb gem in Rails; build AI-powered features in Rails; manage prompts as templates; route between LLM models for cost optimization; run LLM calls as background jobs; set up Braintrust evals; use LiteLLM or Portkey as a proxy; track LLM costs; test AI features; audit LLM usage patterns; build RAG pipelines in Rails with langchain-rb; add classification, summarization, extraction, or generation feat13
  36. 2724Slizdeckpedroanze/slizdeckGenera decks de slides HTML animados a partir de un design system propio — enfocado en pitch decks de startup (minimalista, poco texto, mucha imagen/gráfica), pero también sirve para charlas, demos y recaps de evento. Arquitectura deck-stage 1920×1080 con navegación por teclado, pensado para presentar en vivo. Trae cinco style packs listos (terminal oscuro, blanco puro, color dominante, denso en datos, editorial), cada uno con paleta, tipografía y reglas de composición validadas contra contraste WCAG y clichés visuales de IA. El design system se define de forma guiada —elegir un pack, inyectar13
  37. 2725Stop Slop Zhleeguooooo/stop-slop-zh写、起草、生成、润色任何面向人读的中文文章或段落时,都要用本 Skill——公众号、博客、知乎、小红书、技术文档、技术方案、设计文档、README、公文、学术摘要、产品文案、复盘、提案、新闻稿、邮件。无论是从零写新稿,还是改稿、审稿,只要在产出中文长文,写完、定稿、交付、发布前都必须调用它过一遍:它识别并消除中文 AI 写作的典型痕迹——套话、排比三件套、名词化、抽象主语、金句收尾、总分总八股、标点指纹、标题套路、评级悬念开头、转述腔——让文本读起来像有人在说话,而不是 AI 在生成。简言之:只要这次任务的产物里有一段是要给人读的中文,就触发本 Skill。11
  38. 2726Thesis Writeribrahim-kukash/thesis-writerWrite publication-quality MSc/PhD thesis chapters that pass examiner scrutiny and AI detection tools. Use when writing thesis chapters, sections, or paragraphs. Also scans existing text for AI patterns and fixes them. Triggers: 'write my thesis', 'write chapter', 'literature review', 'write methodology', 'write results', 'write discussion', 'thesis writing', 'academic writing', 'fix AI writing in thesis', 'scan thesis for AI', 'prepare for viva'. NOT for general content writing (use content-production). NOT for humanizing non-academic text (use humanizer). NOT for presentations (use pptx).13
  39. 2727Think Like Mekakha13/think-like-mePersonal engineering rules and reasoning patterns the user has curated over time. Consult BEFORE writing, modifying, debugging, or designing any technical feature — rules often cover domain-specific gotchas (e.g., mobile audio timers need background mode) that generic answers miss. Also triggers on `/learn-this`, "learn this", "remember this", or `/new-rule` to capture new rules, and on detected corrections to previously proposed code.13
  40. 2728Wangziru Analysischrislitality-svg/wangziru-analysis-skill给定选题或已有文稿,用王自如的思考方式写口播、改口播,或把思考顺序讲给用户。先判断这题是立规矩、讲经历还是回一句别人的话,再决定用哪些论证装置。不用于统计播放量,不冒充本人。10
  41. 2729Yi Shi Wei JianGreatXiaoRY/LearnFromHistory-skillUse when the user says 请用/使用/调用 以史为鉴 skill, yi-shi-wei-jian, 借古鉴今, 历史类比, 中国历史案例, or 沙盘推演. Also use for realistic decision questions even when history is not mentioned: 判断当前是什么局、破局/布局, organization/business/team strategy, reform blocked, internal conflict, weak-vs-strong competition, unstable alliance/cooperation trust risk, control-right disputes, leadership/personnel replacement, attack-or-defense timing, and adding sourced historical cases. Output 【局面判断】【历史参照】【关键变量】【可选路径】【沙盘推演】【借鉴原则】【边界提醒】.11
  42. 2730ZuitiSilentFleetKK/zuiti-skill你的专属嘴替——把任何难回、憋屈、不知道怎么开口的消息丢进来,它先翻译对方的潜台词和关系风险,再给你三档可以直接发出去的回复(体面版 / 绵里藏针版 / 掀桌版),最后附长期策略和发送建议。适用于老板画饼甩锅、挽留话术、试用期拖延转正、甲方压价改需求、差评勒索、贬低专业价值、亲戚催婚、份子钱攀比、伴侣阴阳怪气、冷战甩锅、暧昧不表态、前任深夜试探、同事夹枪带棒、抢功、邻居噪音投诉、陌生人网络阴阳怪气、群聊道德绑架、砍价链接死缠烂打、二手交易纠纷、微商杀熟推销等一切"这条我该怎么回"的场景。只要用户贴出一段别人发来的消息、抱怨"不知道怎么回""被噎住了""这话什么意思""帮我回一下""想怼又不好直接怼",或者说"嘴替""帮我组织语言""这条消息",都应主动使用本 skill。也支持蒸馏用户本人的说话风格,生成"你的专属嘴替",让回复读起来就像用户自己发的。13
  43. 2731Auditor Estrategico Juridicopizaniadv/auditor-estrategico-juridicoCamada estratégico-auditorial que precede a redação de peças no contencioso brasileiro. O advogado alimenta o caso; a skill classifica fatos, monta a matriz probatória, hierarquiza teses, antecipa o adversário, controla a jurisprudência em tripla camada e calibra a firmeza do tom pela solidez real de cada tese. Entrega dois produtos separados: o Relatório Estratégico Interno (uso exclusivo do advogado, com fraquezas, riscos e cenários) e o Dossiê de Redação (apenas material processualmente aproveitável, pronto para alimentar a peça). Opera em regime completo, abreviado ou de primeiro uso. Disp9
  44. 2732Aham PptAham-AIAPP/aham-ppt把材料做成方案级、汇报级的 PPT。用户说「帮我做PPT」「做演示文稿」「做一个汇报」「根据这份资料做PPT」 「做客户方案PPT」「制作幻灯片」时触发,只有一句话需求也触发。 八个阶段:受众与规范 → 材料解析 → 论点提炼 → 叙事骨架 → 页面规划 → 样页确认 → 逐页设计 → 质检交付。 页面写成 HTML 幻灯片,网页预览确认后导出可编辑 PPTX。10
  45. 2733B3sty Skillb3sty191/b3sty-skillb3sty rules for implementing, reviewing, debugging, refactoring, or optimizing RedM/FiveM Lua resources. Use for FXServer manifests, client/server Lua, natives/entities, native invocation from docs (hashes, InvokeNative, marshalling, RDR3 structs), events/callbacks/exports/NUI, NUI/browser-UI bridge (SendNUIMessage, RegisterNUICallback, SetNuiFocus), NUI XSS/player-string rendering, OneSync/entity networking (net IDs, ownership, routing buckets, broadcasts), built-in client events (weaponDamageEvent, explosionEvent), anti-cheat/event-security hardening (give-item/give-money dupe prevention, Re10
  46. 2734Figma Annotations Strategysaralobo/skill-figma-annotationsGenerate strategic Figma annotations via MCP based on PRs, tickets, or user descriptions. Use when the user wants to document a screen, flow, or component for Figma, or mentions "figma annotations", "annotation strategy".10
  47. 2735Grok Bot Gatewaydimpurr/grok-bot-gatewayAn official-webhook-only gateway to all your Grok Bots. Use this when a coding agent or script needs to list a Grok Bot team, read a Bot's transcript or message a Bot, or when a Grok Bot user wants to host that gateway; it detects which side you're on and guides you. Callers (Claude Code, Codex, scripts) use the grokgw client; hosts create the gateway Bot, its webhook routine and a host config. Getting results back is optional and goes over a return path you choose (none by default).10
  48. 2736Lead Research BriefLuispitik/lead-research-briefInvestiga un lead comercial B2B, mapea sus procesos operativos AS-IS y genera el backlog de una app a medida. Entrega 3 artefactos (resumen en chat + HTML interactivo + Word) y opcionalmente una demo-app funcional con datos sintéticos y branding del cliente (Fase 6). USAR SIEMPRE cuando el usuario diga "investiga este lead", "haz el brief de", "prepara la propuesta para", "genera el mapa de procesos de", "brief_investigacion", o proporcione un formulario de lead con organización, sector o problema.10