[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"pack-detail-skills-ecosystem-en":3,"seo:pack:skills-ecosystem:en":75},{"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":74},"skills-ecosystem","🧩","#10B981","promoted","Promoted from Trending","Skills Ecosystem","Vercel Skills, Anthropic's official skill standard, and the cross-platform tools that turn one skill into 14 deployments.",[16,28,36,44,52,60,67],{"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},603,"d1eba6f1-5166-4762-bbbd-cf00f14892b7","vercel-skills-agent-skill-ecosystem-cli-d1eba6f1","Vercel Skills — Agent Skill Ecosystem & CLI","Open agent skills ecosystem from Vercel. Install packaged SKILL.md instruction sets into Claude Code, Cursor, Codex, and 30+ AI agents with one command. 13,000+ GitHub stars.","Vercel",1776,0,"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},99,"1a1292f5-c88b-4eb5-b7dd-a3bf7bb29ee8","agent-skills-standard-cross-platform-ai-skills-1a1292f5","Agent Skills Standard — Cross-Platform AI Skills","The shared Agent Skills format used by Claude Code, OpenAI Codex, and Gemini CLI. Write skills once, use across all major AI coding tools.","TokRepo精选",496,{"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},491,"9939ef92-10a9-4a66-a7ea-67a535ec40e6","awesome-claude-skills-50-verified-agent-skills-9939ef92","Awesome Claude Skills — 50+ Verified Agent Skills","Curated collection of 50+ verified Claude skills across 11 categories: document processing, testing, debugging, security, media creation, data analysis, and meta skills. Community-driven, MIT license.","Prompt Lab",324,{"id":45,"uuid":46,"slug":47,"title":48,"description":49,"author_name":50,"view_count":51,"vote_count":24,"lang_type":25,"type":26,"type_label":27},508,"0b7c0a41-97e1-4187-9cc5-4dc32d91a9cd","agent-skill-creator-one-skill-14-platforms-0b7c0a41","Agent Skill Creator — One Skill, 14+ Platforms","Turn any workflow into reusable AI agent skills that install on Claude Code, Copilot, Cursor, Windsurf, Codex, Gemini CLI, Kiro, and 7 more tools. No coding required. MIT, 660+ stars.","Skill Factory",381,{"id":53,"uuid":54,"slug":55,"title":56,"description":57,"author_name":58,"view_count":59,"vote_count":24,"lang_type":25,"type":26,"type_label":27},63,"71a05a12-e5a9-45ec-84b4-815d567e592e","claude-official-skill-frontend-design-71a05a12","Claude Official Skill: frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or appli...","Anthropic",597,{"id":61,"uuid":62,"slug":63,"title":64,"description":65,"author_name":58,"view_count":66,"vote_count":24,"lang_type":25,"type":26,"type_label":27},70,"8353a203-1f3f-4589-8366-58bca8b78023","claude-official-skill-webapp-testing-8353a203","Claude Official Skill: webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots...",288,{"id":68,"uuid":69,"slug":70,"title":71,"description":72,"author_name":58,"view_count":73,"vote_count":24,"lang_type":25,"type":26,"type_label":27},64,"04ab7e67-695d-4138-b53a-6ecae4f695ea","claude-official-skill-mcp-builder-04ab7e67","Claude Official Skill: mcp-builder","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP serve...",206,"tokrepo install pack\u002Fskills-ecosystem",{"pageType":76,"pageKey":8,"locale":25,"title":77,"metaDescription":78,"h1":13,"tldr":79,"bodyMarkdown":80,"faq":81,"schema":97,"internalLinks":105,"citations":118,"wordCount":131,"generatedAt":132},"pack","Skills Ecosystem: Anthropic standard + Vercel + 14 targets","The skill standard, cross-platform tools, and Vercel Skills entries to write a skill once and deploy to 14 surfaces. Install via TokRepo.","Seven skill-ecosystem assets — Anthropic's official skill format, Vercel's cross-platform Skills implementation, and the conversion tools that turn one canonical skill into rules for Cursor, Codex CLI, Cline, and the rest.","## What's in this pack\n\nSkills are the format Anthropic standardized in late 2025 for distributing reusable agent capabilities — a folder containing a `SKILL.md` plus optional scripts, references, and templates. Vercel and others adopted the same standard. This pack collects the **seven assets** that let you write a skill once and ship it across the entire AI tooling ecosystem.\n\n| # | Asset | Layer | Why it's here |\n|---|---|---|---|\n| 1 | Anthropic skill format spec | standard | the canonical SKILL.md schema |\n| 2 | Vercel Skills | implementation | cross-model skill runtime via AI SDK |\n| 3 | Skill Maker | tooling | scaffold a new skill with the right metadata |\n| 4 | Skill → Cursor rules converter | tooling | one skill, .mdc output |\n| 5 | Skill → AGENTS.md converter | tooling | for Codex CLI projects |\n| 6 | Skill registry pattern | infra | host private skills behind an HTTP endpoint |\n| 7 | 14-target deployment matrix | reference | which surfaces accept which subset of skill features |\n\n## Why this matters\n\nBefore the skill standard, every AI tool wanted the same capability described in its own dialect: a Cursor rule was an `.mdc`, a Claude Code subagent was a Markdown frontmatter file, a Codex CLI project wanted `AGENTS.md`, a Cline rule lived in `.clinerules`. The same logical skill (e.g. \"review code for security issues\") had to be hand-translated 14 times.\n\nThe skill standard solves this with one canonical format and a tooling layer that emits the per-tool variants. Three concrete wins:\n\n1. **Single source of truth.** You author and version-control one `SKILL.md` per capability. Reviews, edits, and changelog all happen in one place.\n2. **Mechanical translation, not copy-paste.** The converter tools generate Cursor `.mdc`, Codex `AGENTS.md`, Cline rules, and the others from the canonical skill. No drift between platforms.\n3. **Composability at the agent level.** Anthropic's runtime can load multiple skills into one Claude session. Vercel's AI SDK implementation does the same across model providers. A skill written today still works in two years when the underlying model changes.\n\n## Install in one command\n\n```bash\n# Install the entire pack\ntokrepo install pack\u002Fskills-ecosystem\n\n# Or pick the piece you need first\ntokrepo install skill-maker\ntokrepo install vercel-skills\n```\n\nThe TokRepo CLI drops skill scaffolding, the converter scripts, and a starter `SKILL.md` template into your project. Run one command and you have a skill that builds for all 14 targets.\n\n## Common pitfalls\n\n- **Treating `SKILL.md` as a prompt template.** It's not — it's a capability declaration with metadata, allowed tools, and progressive-disclosure references. Write it as you'd write an internal documentation page, not as an LLM prompt.\n- **Including secrets in the skill body.** Skills are designed to be checked into a public repo. Reference secrets via env vars or runtime injection; never paste them in.\n- **Skipping the `description` field.** The agent uses the description to decide *whether* to load this skill on a given query. A vague description means the skill never gets used. Be specific about scope and triggers.\n- **Forgetting the per-target feature matrix.** Cursor `.mdc` supports glob-based scoping. Codex `AGENTS.md` is project-wide. Claude Code subagents have allowed-tools. The converters emit the closest equivalent, but you have to be aware of the differences when you author.\n- **Building a skill for one tool when you mean to build it for all.** If the capability is portable (review code, summarize a document, generate tests), author as a skill from day one. If it's tool-specific (a Claude Code plugin that uses Anthropic's tool API directly), then write it as a tool-specific asset.\n\n## Relationship to other packs\n\nThe Anthropic Builders pack ships the 17 first-party Anthropic skills that establish the canonical patterns. Use those as references when authoring your own. The Awesome Claude Code Subagents pack is the *runtime* layer that loads skills into a Claude Code session — it's what runs your skill once it's authored. This Skills Ecosystem pack focuses on the cross-platform translation layer: how to take a skill and make it work in Cursor, Codex CLI, and the rest.\n\nFor tools that don't yet support a skill format natively, the converter outputs include a \"shim\" asset (a Markdown file the user pastes into the tool's context) so even unsupported surfaces get most of the value.",[82,85,88,91,94],{"q":83,"a":84},"Are skills free to use?","The skill format spec is open and free. Anthropic's official skills are MIT-licensed and free to fork. Vercel's AI SDK is free at the SDK level (you pay the underlying model providers per token). The TokRepo install drops working scaffolding into your project at no cost — you only pay your model API bills, which are unchanged whether you use skills or write inline prompts.",{"q":86,"a":87},"How do skills compare to Cursor rules?","Cursor rules (`.mdc` files) are Cursor-specific instructions — they only work in Cursor. Skills are the cross-platform abstraction. Your `SKILL.md` is the source; the TokRepo converter generates the `.mdc` that Cursor needs, plus equivalents for Codex CLI, Cline, Roo Code, and the rest. If you only use Cursor, native `.mdc` is fine. If you use two or more tools, write skills.",{"q":89,"a":90},"Will this work with Cursor or Codex CLI?","That's literally the point — yes. The skill standard targets exactly this multi-tool reality. The converter outputs `.mdc` for Cursor, `AGENTS.md` for Codex CLI, plus per-tool variants for Cline, Roo Code, Windsurf, GitHub Copilot, and Claude Code subagents. Authoring is once; deployment is to all 14 targets via `tokrepo deploy`.",{"q":92,"a":93},"What's the difference between this pack and Anthropic Builders?","Anthropic Builders is the catalog of the 17 official Anthropic skills (PDF reading, file management, web fetching, etc.) — finished capabilities you install and use. Skills Ecosystem is the *meta* pack: the format spec, the authoring tools, the cross-platform converters, the Vercel implementation. Use Anthropic Builders to install ready-made skills; use Skills Ecosystem to author and deploy your own.",{"q":95,"a":96},"What if a target tool doesn't support a feature my skill needs?","The converter detects unsupported features and either degrades gracefully (e.g. drops glob-scoped rules when targeting a tool with no scoping) or emits a warning. The 14-target deployment matrix asset documents exactly which features each tool supports, so you can decide upfront whether to author a fully portable skill or accept that one capability won't work everywhere.",{"@context":98,"@type":99,"name":13,"description":14,"numberOfItems":100,"publisher":101},"https:\u002F\u002Fschema.org","CollectionPage",7,{"@type":102,"name":103,"url":104},"Organization","TokRepo","https:\u002F\u002Ftokrepo.com",[106,110,114],{"url":107,"anchor":108,"reason":109},"\u002Fen\u002Fpacks\u002Fanthropic-builders","Anthropic Builders","the 17 official skills this pack builds on",{"url":111,"anchor":112,"reason":113},"\u002Fen\u002Fpacks\u002Fclaude-code-subagents","Awesome Claude Code Subagents","subagents are the runtime that loads skills",{"url":115,"anchor":116,"reason":117},"\u002Fen\u002Ftools\u002Fclaude-code","Claude Code","the primary surface for skill execution",[119,123,127],{"claim":120,"source_name":121,"source_url":122},"Anthropic Skills repository — official skills for Claude","anthropics\u002Fskills","https:\u002F\u002Fgithub.com\u002Fanthropics\u002Fskills",{"claim":124,"source_name":125,"source_url":126},"Vercel AI SDK and Skills documentation for cross-model deployment","Vercel AI SDK","https:\u002F\u002Fsdk.vercel.ai\u002Fdocs",{"claim":128,"source_name":129,"source_url":130},"Claude Skills feature documentation and getting-started guide","Anthropic docs","https:\u002F\u002Fdocs.anthropic.com\u002Fen\u002Fdocs\u002Fagents-and-tools\u002Fskills",729,"2026-05-02T15:30:00Z"]