[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"pack-detail-windsurf-first-day-es":3,"seo:pack:windsurf-first-day:es":102},{"code":4,"message":5,"data":6},200,"操作成功",{"pack":7},{"slug":8,"icon":9,"tone":10,"status":11,"status_label":12,"title":13,"description":14,"items":15,"install_cmd":101},"windsurf-first-day","🏄","#0EA5E9","new","Nuevo · esta semana","Kit del Primer Día con Windsurf","¿Acabas de cambiar a Windsurf de Codeium? Diez elementos para poner Cascade en marcha, supercomplete afinado y los MCP correctos conectados desde el primer día.",[16,28,36,44,54,64,71,78,85,94],{"id":17,"uuid":18,"slug":19,"title":20,"description":21,"author_name":22,"view_count":23,"vote_count":24,"lang_type":25,"type":26,"type_label":27},673,"f2cfae6c-6321-496d-833d-5a5c77567712","windsurf-ai-ide-cascade-agentic-flows-f2cfae6c","Windsurf — AI IDE with Cascade Agentic Flows","AI-powered IDE by Codeium with Cascade multi-step agentic editing. Free tier includes Claude and GPT-4 access. VS Code-based with flows for complex refactoring tasks. 6,000+ stars.","Skill Factory",110,0,"en","skill","Skill",{"id":29,"uuid":30,"slug":31,"title":32,"description":33,"author_name":34,"view_count":35,"vote_count":24,"lang_type":25,"type":26,"type_label":27},517,"c3338e8d-2ef8-4d72-8d2a-43e7518555fd","lnai-unified-ai-config-claude-cursor-copilot-more-c3338e8d","lnai — Unified AI Config for Claude, Cursor, Copilot & More","Define AI tool configs once in a .ai\u002F directory and auto-sync to Claude Code, Cursor, GitHub Copilot, Gemini CLI, Codex, and Windsurf native formats.","AI Open Source",171,{"id":37,"uuid":38,"slug":39,"title":40,"description":41,"author_name":42,"view_count":43,"vote_count":24,"lang_type":25,"type":26,"type_label":27},3134,"ddb121a1-a9a0-4151-920e-e787fc206927","agents-md-open-format-for-coding-agent-instructions","AGENTS.md — Open Format for Coding Agent Instructions","AGENTS.md defines a predictable instruction file for coding agents: dev env tips, tests, PR rules, and repo context. Drop it at repo root.","Prompt Lab",77,{"id":45,"uuid":46,"slug":47,"title":48,"description":49,"author_name":50,"view_count":51,"vote_count":24,"lang_type":25,"type":52,"type_label":53},3798,"4323a51e-d760-5437-87f1-813720527be3","agentrules-multi-provider-agents-md-generator","agentrules — Multi-Provider AGENTS.md Generator","agentrules generates AGENTS.md via a six-phase analysis pipeline; verified 117★. Install with `pip install -U agentrules`, then run `agentrules analyze`.","Script Depot",5,"script","Script",{"id":55,"uuid":56,"slug":57,"title":58,"description":59,"author_name":60,"view_count":61,"vote_count":24,"lang_type":25,"type":62,"type_label":63},42,"8a28360d-6eef-449d-9857-d8b388a05f34","mcp-reference-servers-official-collection-8a28360d","MCP Reference Servers — Official Collection","Official MCP reference server implementations by Anthropic: filesystem, git, memory, fetch, sequential thinking, and more. The starting point for MCP development.","MCP Hub",127,"mcp","MCP",{"id":65,"uuid":66,"slug":67,"title":68,"description":69,"author_name":60,"view_count":70,"vote_count":24,"lang_type":25,"type":62,"type_label":63},3059,"7f3a756c-8ec2-4b20-8ad6-99bfc5155af3","playwright-mcp-browser-automation-server","Playwright MCP — Browser Automation Server","Playwright MCP is an MCP server for browser automation via Playwright snapshots. Add via npx in Claude Code\u002FCodex to run deterministic actions.",148,{"id":72,"uuid":73,"slug":74,"title":75,"description":76,"author_name":60,"view_count":77,"vote_count":24,"lang_type":25,"type":62,"type_label":63},3064,"f18b31dd-84c6-45c8-8a8f-1db8e92f2bd7","desktop-commander-mcp-local-terminal-files","Desktop Commander MCP — Local Terminal + Files","Desktop Commander MCP gives agents controlled local terminal + filesystem tools (including PDF\u002FDOCX\u002FExcel). Install via npx and verify by listing tools.",60,{"id":79,"uuid":80,"slug":81,"title":82,"description":83,"author_name":60,"view_count":84,"vote_count":24,"lang_type":25,"type":62,"type_label":63},803,"85eacf96-3b2b-43f5-ad6f-fd4413ad0b69","git-mcp-version-control-server-ai-agents-85eacf96","Git MCP — Version Control Server for AI Agents","MCP server that gives AI agents full Git capabilities. Git MCP enables Claude Code and Cursor to manage repositories, branches, commits, diffs, and history via tool calls.",180,{"id":86,"uuid":87,"slug":88,"title":89,"description":90,"author_name":42,"view_count":91,"vote_count":24,"lang_type":25,"type":92,"type_label":93},507,"7d697443-cf7f-4e71-8fd7-45431e5ff685","awesome-ai-system-prompts-32-tool-prompts-revealed-7d697443","Awesome AI System Prompts — 32+ Tool Prompts Revealed","Curated collection of extracted system prompts from 32+ production AI tools including ChatGPT, Claude, Cursor, v0, Manus, Devin, Windsurf, and Perplexity. MIT license, 5,700+ stars.",214,"prompt","Prompt",{"id":95,"uuid":96,"slug":97,"title":98,"description":99,"author_name":42,"view_count":100,"vote_count":24,"lang_type":25,"type":92,"type_label":93},644,"59436371-30d6-4a51-9f9b-1b1986873728","ai-coding-agents-compared-2026-landscape-guide-59436371","AI Coding Agents Compared — 2026 Landscape Guide","Comprehensive comparison of AI coding agents in 2026: Claude Code, Codex CLI, Gemini CLI, Cursor, Windsurf, Aider, and more. Features, pricing, model support, and use case recommendations.",317,"tokrepo install pack\u002Fwindsurf-first-day",{"pageType":103,"pageKey":8,"locale":25,"title":104,"metaDescription":105,"h1":106,"tldr":107,"bodyMarkdown":108,"faq":109,"schema":125,"internalLinks":131,"citations":144,"wordCount":157,"generatedAt":158},"pack","Windsurf First-Day Kit — 10 Picks to Get Cascade Flowing Day One","Switching to Codeium Windsurf? Ten opinionated picks: the IDE itself, a unified rules file for AGENTS.md\u002F.windsurfrules, four MCP servers (Git, Playwright, Desktop Commander, official reference), the leaked Cascade system prompt, and a 2026 landscape map. Install in order — you're shipping by lunch.","Windsurf First-Day Kit — Cascade, Supercomplete & the Right MCPs From Day One","Ten picks in install order: the Windsurf IDE, a multi-tool rules generator so your AGENTS.md\u002F.windsurfrules\u002F.cursorrules stay in sync, the AGENTS.md spec itself, four MCP servers you'll actually use (official reference, Git, Playwright, Desktop Commander), the leaked Cascade system prompt so you know what the agent thinks, and a 2026 landscape map so you stop second-guessing your tool choice. Honest disclaimer: the catalog is thin on Windsurf-specific assets — most picks here are editor-agnostic skills that work because Windsurf is a VS Code fork.","## What's in this pack\n\nYou installed Codeium Windsurf, opened Cascade for the first time, and now you're hunting for the equivalent of a `.cursorrules` file, a sensible MCP starter set, and someone honest enough to say which parts of the marketing video are real on day one. That's this pack.\n\n**Honest disclaimer up front:** the public asset catalog is **thin on Windsurf-specific skills** today. Most agent-skill production is happening around Claude Code and Cursor. The good news: Windsurf is a **VS Code fork**, and Cascade reads instructions from a `.windsurfrules` file plus the open **`AGENTS.md`** convention — so most editor-agnostic skills, MCP servers, and prompt patterns drop in without modification. Where a pick is editor-agnostic, we say so.\n\nWho this is for: a developer migrating from VS Code+Copilot, Cursor, or Claude Code who wants Cascade producing real diffs on a real repo by the end of the first afternoon — not someone evaluating IDEs for a team rollout.\n\n## Install in this order\n\n1. **Windsurf — AI IDE with Cascade Agentic Flows** *(the IDE itself)* — Install Codeium's IDE first, sign in with your account, and verify the free tier gives you Claude + GPT-4 access for Cascade. Confirm Cascade can do a multi-step edit on a throwaway file before installing anything else. If this part is broken, none of the following picks matter.\n2. **AGENTS.md — Open Format for Coding Agent Instructions** *(editor-agnostic spec)* — Read the spec before you write a single rule. AGENTS.md is the cross-tool convention (Cursor, Windsurf, Claude Code, Aider, Codex CLI all read it or interop with it). Knowing the spec means you stop writing tool-specific rules from scratch every time you switch tools.\n3. **agentrules — Multi-Provider AGENTS.md Generator** *(editor-agnostic generator)* — Generate `.windsurfrules` + `AGENTS.md` + `.cursorrules` + `CLAUDE.md` from one source. Pays for itself the first time you try Windsurf on a project that already has a `.cursorrules`. Don't hand-maintain four files.\n4. **lnai — Unified AI Config for Claude, Cursor, Copilot & More** *(editor-agnostic config)* — The other half of #3. Where agentrules generates rule files, lnai unifies provider configuration (which model, which keys, which defaults) across the AI coding tools you use side-by-side. Stops you from juggling four `~\u002F.config\u002F` directories.\n5. **MCP Reference Servers — Official Collection** *(editor-agnostic MCP)* — Windsurf supports MCP. Before installing niche third-party servers, scan the official reference (filesystem, fetch, git, memory, sequential-thinking, time, etc.). Most teams find 60% of what they need here without hunting Smithery.\n6. **Git MCP — Version Control Server for AI Agents** *(editor-agnostic MCP)* — Specifically the Git MCP. Windsurf's Cascade can read your repo but the MCP server gives it structured access to commit history, blame, branch state, and diffs without parsing shell output. Single highest-leverage MCP for code work.\n7. **Desktop Commander MCP — Local Terminal + Files** *(editor-agnostic MCP)* — Lets Cascade run shell commands and edit files outside the open workspace. Necessary when you want \"upgrade my Node version\" or \"check disk usage,\" which Cascade alone can't do. Treat as you'd treat a junior dev with sudo — useful, scope tightly.\n8. **Playwright MCP — Browser Automation Server** *(editor-agnostic MCP)* — Cascade can drive a browser. Verify the change you just made actually renders, fill forms, capture screenshots, scrape live state. Pairs especially well with Cascade's multi-step flows because the browser step usually reveals the bug the code review missed.\n9. **Awesome AI System Prompts — 32+ Tool Prompts Revealed** *(reference, includes Cascade's prompt)* — Read Windsurf's actual leaked Cascade system prompt before you write yours. Knowing what the agent already believes about itself prevents you from writing rules that contradict its baseline behavior. Treat this as the manual for \"why is Cascade doing X.\"\n10. **AI Coding Agents Compared — 2026 Landscape Guide** *(reference)* — Final orientation pick. Once you've got Cascade working, you'll wonder \"should I be using Claude Code or Cursor for this task instead?\" This is the honest landscape map. Cheaper than five Twitter threads.\n\n## How they fit together\n\n```\nWindsurf IDE (#1)\n   │\n   └─ Cascade reads .windsurfrules + AGENTS.md\n         │\nAGENTS.md spec (#2) ── agentrules (#3) ── lnai (#4)\n   │                       │                  │\n   └─ one source ──────────┴──────────────────┘\n         ├─ .windsurfrules (Windsurf)\n         ├─ AGENTS.md (cross-tool)\n         ├─ .cursorrules (Cursor, if you keep it)\n         └─ CLAUDE.md (Claude Code, if you keep it)\n         │\nMCP layer:\n   ├─ MCP Reference Servers (#5)  ← scan first\n   ├─ Git MCP (#6)                ← daily driver\n   ├─ Desktop Commander (#7)      ← shell + files outside workspace\n   └─ Playwright MCP (#8)         ← verify in a real browser\n         │\nReference shelf:\n   ├─ Awesome AI System Prompts (#9)  ← what Cascade actually thinks\n   └─ AI Coding Agents Compared (#10) ← when to reach for another tool\n```\n\nThe **agentrules + AGENTS.md + Git MCP** trio is the load-bearing wall. Everything else is decoration without those three. If you only have 30 minutes after installing Windsurf itself, do #3 + #2 + #6 and call it a day.\n\n## Tradeoffs you'll hit (Windsurf vs Cursor specifically; Cascade vs Composer)\n\n- **Windsurf vs Cursor** — Cursor has the bigger asset ecosystem (more `.cursorrules` examples, more YouTube content, more skills explicitly built for it). Windsurf has **Cascade**, which is closer to \"agent that plans + executes multi-file edits on its own\" than Cursor's Composer (which is more \"chat that proposes a diff for one task at a time\"). If you want a coding partner that drives, Windsurf wins; if you want a fast assistant that responds, Cursor still wins. Picks #3 and #4 explicitly let you run both side-by-side without maintaining duplicate config.\n- **Cascade vs Composer** — Composer is **interactive-first** (you stay in the loop on every step). Cascade is **autonomous-first** (it plans, executes, recovers from errors, then surfaces a summary). Cascade is more capable on greenfield refactors. Composer is safer on production codebases where you want to approve each change. Don't fight Cascade's autonomy — give it a tight `.windsurfrules` (via #3) and let it run.\n- **Supercomplete vs Copilot autocomplete** — Supercomplete predicts multi-line edits, including deletes and refactors of nearby code, not just the next token. Higher hit rate on intent, but more jarring when wrong. Disable it for the first hour while you get used to Cascade; turn it on once your rules file is solid.\n- **MCP via Windsurf vs MCP via Claude Desktop** — Windsurf's MCP integration is newer and quieter about errors. If a server fails to start, you might see no UI feedback. Always test new MCP servers in Claude Desktop or the MCP Inspector first; install in Windsurf only after you've confirmed they work standalone.\n\n## Common pitfalls\n\n- **Hand-writing `.windsurfrules` and `.cursorrules` separately** — Don't. Use #3 (agentrules) from day one. Even if you think you'll only use Windsurf, you'll evaluate Claude Code or Cursor within 6 months and wish you had the generator already in place.\n- **Installing 10 MCP servers at once** — Same trap as Claude Code: too many MCPs = slower agent + worse tool selection. Stick to #5–#8 for week one. Only add a server when you hit a specific gap.\n- **Forgetting Cascade has memory** — Cascade tracks per-project memories. If you change your `.windsurfrules` and Cascade still behaves the old way, clear the project memory — it's caching the previous instruction set.\n- **Trusting the leaked system prompt as gospel** — #9 is invaluable, but vendors update system prompts silently. Treat it as \"what Cascade believed last month,\" not \"what Cascade believes now.\" Re-check quarterly.\n- **Skipping the landscape map (#10) because you already picked Windsurf** — You picked Windsurf for *this* project. Six months from now, a different task will fit Claude Code or a CLI agent better. Knowing the landscape isn't a sign of indecision — it's how you avoid forcing every task into the one IDE you happen to have open.",[110,113,116,119,122],{"q":111,"a":112},"Is the Windsurf-specific asset pool really that thin, or are you just not searching hard?","Genuinely thin as of writing. A keyword search for 'windsurf' on TokRepo returns one Windsurf-tagged asset; 'cascade' returns one. The broader VS Code \u002F agent-skill ecosystem is large, but very few skills are tagged for Windsurf specifically. That's why this pack leans on editor-agnostic picks: AGENTS.md, MCP servers, unified rule generators. If you wanted a 'Cursor first day kit,' it'd be ten Cursor-native picks; here, eight of the ten are tool-agnostic by design.",{"q":114,"a":115},"Which three would you install if I only have 30 minutes?","AGENTS.md (#2), agentrules (#3), and Git MCP (#6). AGENTS.md gives you the cross-tool spec; agentrules generates the right `.windsurfrules` from one source so you're not maintaining four files; Git MCP gives Cascade structured access to your repo's history. The other seven are upgrades you can layer in over the next week. These three turn Windsurf from 'installed IDE' into 'agent that knows your codebase.'",{"q":117,"a":118},"Why install agentrules (#3) AND lnai (#4) — aren't they the same?","Different layers. agentrules generates rule *content* (`.windsurfrules`, `AGENTS.md`, `.cursorrules`, `CLAUDE.md`) from one source — it solves the 'four files, same content' problem. lnai unifies *provider configuration* (which model, which API keys, which defaults) across the AI coding tools you run side-by-side — it solves the 'four config dirs, same secrets' problem. If you only use Windsurf and only ever will, you can skip #4. Most people running Windsurf also touch Claude Code or Cursor at least weekly, and that's where lnai pays off.",{"q":120,"a":121},"Will MCP servers from the Claude Code ecosystem actually work in Windsurf?","Yes, with one caveat. MCP is a protocol, not a Claude-specific thing — any MCP server that runs as a stdio process works in Windsurf. The caveat: Windsurf's MCP integration is newer than Claude Desktop's, and error reporting is quieter. If a server doesn't appear in Cascade, debug it with the MCP Inspector or Claude Desktop first, then bring the working config into Windsurf. The four MCPs in this pack (#5-#8) are battle-tested across all three clients.",{"q":123,"a":124},"Should I uninstall Cursor or Claude Code if I'm switching to Windsurf?","No. The 2026 landscape (#10 covers this honestly) is that no single AI coding tool wins every task. Cascade is excellent for autonomous multi-file refactors. Claude Code is excellent for terminal-driven, repo-spanning work. Cursor is excellent for tight Composer-style chat-edit loops. Keep all three installed, let agentrules (#3) keep their config in sync, and reach for whichever fits the task. Forcing every workflow into one IDE is how you end up frustrated.",{"@context":126,"@type":127,"name":128,"description":129,"numberOfItems":130,"inLanguage":25},"https:\u002F\u002Fschema.org","ItemList","Windsurf First-Day Kit","Ten opinionated picks for a developer switching to Codeium Windsurf — the IDE, a unified rules generator, the AGENTS.md spec, four MCP servers, the leaked Cascade system prompt, and a 2026 landscape map.",10,[132,136,140],{"url":133,"anchor":134,"reason":135},"\u002Fen\u002Ftopics\u002Fai-code-editor-showdown","AI Code Editor Showdown pack","Compare Windsurf head-to-head with Cursor, VS Code+Copilot, and Zed",{"url":137,"anchor":138,"reason":139},"\u002Fen\u002Ftopics","Browse other topic packs","Adjacent packs include Claude Code Onboarding, MCP Server Stack, and Agent Skill Hubs",{"url":141,"anchor":142,"reason":143},"\u002Fen\u002Fai-tools-for\u002Fcoding","AI tools for coding","See how Windsurf and Cascade compare to Claude Code, Cursor, and other coding agents",[145,149,153],{"claim":146,"source_name":147,"source_url":148},"Windsurf is Codeium's AI-powered IDE built on a VS Code fork with Cascade multi-step agentic editing","Codeium \u002F Windsurf official site","https:\u002F\u002Fcodeium.com\u002Fwindsurf",{"claim":150,"source_name":151,"source_url":152},"AGENTS.md is an open format for coding agent instructions adopted across multiple tools","agents.md specification","https:\u002F\u002Fagents.md\u002F",{"claim":154,"source_name":155,"source_url":156},"MCP (Model Context Protocol) is an open protocol that any compatible client, including Windsurf, can use to load external tool servers","Model Context Protocol docs","https:\u002F\u002Fmodelcontextprotocol.io\u002F",1306,"2026-05-22T00:00:00Z"]