覆盖 16 家厂商（11 家模型原生厂商 + 5 家聚合推理云）的 API、CLI、MCP Server、Agent Skills 四层开发者接入面，并对 7 个官方技能仓库（103 个 SKILL.md）做了本地源码级剖析。
五句话讲完整个格局。
recommend_model / get_pricing 先行）llms.txt，与平台元数据同源不漂移atlas_get_balance / atlas_get_model_costs）✓ = 官方提供 · △ = 仅社区/部分提供 · ✗ = 没有。点击表头可横向滚动查看。
| 厂商 | REST API | 官方 CLI | 官方 MCP | 官方 Skills | 官方 SDK | 异步模式 | 视频单价（约） |
|---|---|---|---|---|---|---|---|
| Higgsfieldhiggsfield.ai | 官方api.higgsfield.ai · 预付费 | npm CLIOAuth 登录 | 托管mcp.higgsfield.ai/mcp | 9 个1.1k★ · 带 evals | Py + TS | request_id + webhook | $0.04–0.21/s⚠ 双轨计费 |
| Runwayrunwayml.com | 官方credits 计价 | 无 | ×2托管 OAuth + API-key 版 | 11 个脚本驱动 | Py + Node | task + 签名 webhook | $0.05–0.28/s |
| Lumalumalabs.ai | 官方Dream Machine / Luma API | Go CLIluma-agents-cli | 官方luma-api-mcp | 无有 llm-info 页 | Py + JS | poll + callback | ~$0.10–0.30/s |
| OpenAI Sora 2platform.openai.com | 官方/v1/videos | Go CLIopenai/openai-cli | 无仅 MCPKit 蓝图 | 目录无视频 | 全家桶 | poll / video.completed webhook | $0.10–0.50/s |
| Google Veo 3.1Gemini API / Vertex | 双通道predictLongRunning | 无专用gcloud 泛用 | 平台级 previewaiplatform /mcp/* | 无 | 全家桶 | LRO 轮询 | $0.05–0.60/s |
| Pikapika.art | 走 fal 分发2025-12 起 | 无 | 无 | 无 | 无 | fal 的 | ~$0.04–0.09/s |
| Kling 快手kling.ai | 官方JWT 短令牌 | 无 | 仅社区⚠ 走转售商 API | 仅社区 | 仅社区 | task_id 轮询 | $0.04–0.11/s |
| MiniMax 海螺minimax.io | 官方video_generation | 无 | 官方Py + JS 双实现 | 无 | 官方 | task_id 轮询 | ~$0.08–0.28/条 |
| 字节 Seedance火山 Ark / BytePlus | 官方英文文档最全 | 无 | 官方无视频社区补位 | 仅社区 | 官方 | task_id 轮询 | ~$0.02–0.04/s |
| Vidu 生数platform.vidu.com | 官方r2v 是差异化 | 无 | 官方vidu-mcp · 很年轻 | 无 | 官方 | task_id 轮询 | ~$0.04–0.12/s |
| 阿里 WanDashScope 百炼 | 官方header 异步 | 无 | 无 | 无 | 官方 | header 异步 + 轮询 | ¥0.14–0.70/s✦ 开源权重 |
| 平台 | API 特性 | 官方 CLI | 官方 MCP | 官方 Skills | 官方 SDK | 差异化定位 |
|---|---|---|---|---|---|---|
| fal.aifal.ai | queue + SSE 状态流 + webhook + Realtime WS | ×2fal(Py 全生命周期) + genmedia | 11 工具mcp.fal.ai/mcp | 17 个官方社区 org · 243★ | 6 语言Py/JS/Swift/Java/Dart/Terraform | llms.txt 全覆盖 · fal Agent 产品 |
| AtlasCloudatlascloud.ai | prediction 轮询 + webhook + OpenAI 兼容 LLM | atlas (Go)brew/npm · cost/wait 子命令 | 14 工具动态 schema 校验 | 3+25 recipes双语 · 含方法论 skill | 明示不做 | 成本感知工具 · 宣称低于官方价 68% |
| Replicatereplicate.com | prediction 轮询 + webhook | Go CLIbrew | 托管 + npm含 code-mode 沙箱 | 无 | 官方 | 托管几乎全部主流视频模型 |
| Runware / WaveSpeed | 统一 REST | 有 | 有 | 有 | 有 | 单一 run 工具统一图/视/音/3D |
Agent 要生成一段视频，实际会穿过三层。价值分配正在向上层（生态）和中层（聚合）迁移。
Coding agent（Claude Code / Codex / Cursor）不直接读 API 文档，而是通过 MCP 工具和 SKILL.md 行动。官方技能目录里没有视频 skill，这一层完全由厂商三件套 + 社区注册表（skills.sh、glama）填充。
统一 queue/prediction 抽象 + 模型目录 + 计费。价值点：智能路由、成本工具、动态 schema 校验、跨模型对比。AtlasCloud MCP 是 glama 注册表视频类周下载第一（289 npm/wk）。
独占能力是护城河（Sora 的物理仿真、Veo 的原生音频、Vidu 的参考生视频、Kling 的运动质量），但 agent 时代的"默认路由权"正在流失给聚合层——Higgsfield 和 Runway 自家技能的默认视频模型都是字节的 Seedance。
每家的 agent 接入策略是一个完整的世界观。
fal（Py，部署 serverless）+ genmedia（agent-first，init 直接装 .claude/skills/）fal 包是无关项目；官方 skills 在 fal-ai-community orgatlas CLI（Go）+ atlascloud-mcp（14 工具）+ 3 skills / 25 recipesatlas_get_balance/atlas_get_model_costs 成本感知uv run scripts/generate_video.py，frontmatter 白名单 Bash(uv run *)对 7 个本地仓库源码级深读后的核心发现：每家把 SKILL.md 做成了完全不同的东西。
「所有其他 skill 都通过 genmedia 命令执行，不直接调 HTTP API」。6 条 Critical Rules：agent 读输出必带 --json、永不编造 endpoint ID、自定义参数前必查 schema、下载用 --download 不用 curl。
run "<prompt>" 自动分类模态；index.json 带 SHA256 防篡改325 行的行为规范：用用户语言回复、不暴露原始 ID/JSON、不预先估价、一次只问一个问题。核心是巨大的模型路由决策树（默认视频 = Seedance 2.5，广告 = Marketing Studio）。
技能内嵌 scripts/generate_video.py，uv run 执行；frontmatter 白名单收窄执行面。key 只从环境变量读（禁止 CLI 参数防 history 泄露）、产物视为不可信输入、固定文件名时间戳约定。
无 SDK/CLI 依赖，agent 照抄 curl/Python 模板即可运行；14 个 MCP 工具逐一说明。真正有价值的是 universal-video-prompt-skill：写一次模型无关 spec，再编译到任意模型——三桶模型（Global/Locks/Time）× 可验证性改写 × 能力降级规则，完整中英双语。
全部克隆至 /Users/lifcc/Desktop/code/AI/tools/video-ai-landscape/。所有技能文档已渲染为在线版本，点开即可阅读。
| 本地目录 | 来源仓库 | SKILL.md | 大小 | 执行模型 | 亮点 |
|---|---|---|---|---|---|
higgsfield-skills/ | higgsfield-ai/skills MIT · 1.1k★ · v0.12.0 | 8 | 2.1M | 自家 CLI（higgsfield） | evals 场景 · 营销垂直 skill · agent 自装剧本 |
runwayml-skills/ | runwayml/skills 2026-02 起 | 11 | 336K | Python 脚本（uv run） | allowed-tools 白名单 · 安全工程 · 双族技能 |
runway-mcp-plugin/ | runwayml/runway-mcp-plugin | 2 | 196K | 官方托管 MCP | mcp.json 一键接入 · 技能薄封装 |
atlascloud-skills/ | AtlasCloudAI/atlas-cloud-skills 32★ · 66 commits | 3 | 1.1M | 裸 REST（无 SDK/CLI 依赖） | 方法论 skill · 中英双语 · providers 适配层 |
fal-community-skills/ | fal-ai-community/skills MIT · 243★ | 17 | 1.1M | genmedia CLI | SHA256 索引 · 16 垂直域 · 智能路由 |
elevenlabs-plugin/ | elevenlabs/plugin | 42 | 1.8M | 远程 MCP + OAuth | 语音域最全 · architect 子族 30+ 技能 |
anthropics-skills/ | anthropics/skills 格式参照基准 | 20 | 16M | — | 官方 spec + template · 无任何视频 skill |
技能怎么装、装到哪、如何保证不被篡改——四家给出了四种答案。
| 机制 | Higgsfield | Runway | AtlasCloud | fal |
|---|---|---|---|---|
| 安装方式 | npx skills add + marketplace + agent 自装剧本 |
skills.sh / marketplace 插件 | install.sh（git clone + 拷贝）/ npx skills add |
genmedia init / genmedia skills install |
| 安装目标 | 按平台分路径：~/.claude/skills · ~/.cursor/plugins · ~/.codex/plugins |
仓库 + 插件双形态 | ~/.claude/skills/ |
.claude/skills/ 或 .agents/skills/ |
| 完整性保障 | 无 | 无 | 无 | index.json SHA256 |
| 质量保障 | evals/ 场景集 | Common Failures 表 | troubleshooting.md | 16 垂直领域分层 |
| 版本标识 | frontmatter version | CHANGELOG.md | 无 | index version |
| 更新方式 | 重新安装 | git pull / 插件更新 | 重新运行 install.sh | genmedia skills update |
同一个量纲（美元 / 秒视频）下，最贵与最便宜相差 15 倍。悬停条形可查看精确值。
从"语音厂商先行"到"三件套标配"，只用了 16 个月。
接入前必须知道的七件事。
atlas-cloud.ai ≠ AtlasCloud（正确域名 atlascloud.ai）；mcp.luma.com 是日历公司 Luma 不是 Luma AI；docs.runway.team 的 MCP 是另一家 VFX 管理公司；npm 的 fal 包是无关项目。如果要做面向 Claude Code / Codex 的 CLI + skills 产品，这十项是从 103 个 SKILL.md 里筛出的可直接复用模式。
| # | 模式 | 来源 | 要点 |
|---|---|---|---|
| 1 | per-model llms.txt | fal.ai | 每个模型一份机器可读 schema+定价，与平台元数据同源生成，杜绝文档漂移 |
| 2 | 成本感知工具 | AtlasCloud / fal | MCP/CLI 内置 balance / costs / 预估命令，agent 提交前可自检预算 |
| 3 | 动态 schema 校验 | AtlasCloud | 提交前校验参数合法性，避免无效调用浪费 credit |
| 4 | 细粒度工具白名单 | Runway | frontmatter allowed-tools: Bash(uv run *) 把 skill 执行面收窄到具体脚本 |
| 5 | Key 卫生规范 | Runway | 密钥只走环境变量，禁止 CLI 参数（防 shell history 与进程列表泄露） |
| 6 | SHA256 技能索引 | fal | index.json 记录每个文件哈希，skill 分发的供应链完整性 |
| 7 | skill 质量回归 | Higgsfield | evals/ 场景集让 skill 行为可测试、可回归 |
| 8 | 一键安装进技能目录 | fal genmedia | init 直接写 .claude/skills/ 或 .agents/skills/，CLI 即分发渠道 |
| 9 | spec→compile prompt 范式 | AtlasCloud | 模型无关 spec + 每模型编译 profile，跨模型迁移零重写；配套可验证性改写规则 |
| 10 | 反面教材：双轨计费 | Higgsfield（警示） | CLI/MCP 与 API 预算割裂——自己的产品务必统一计费口径 |
7 个仓库里全部 103 个 SKILL.md，按厂商分组，点名称直达在线渲染页。
| 技能 | 描述 |
|---|---|
higgsfield-brandkithiggsfield-brandkit/SKILL.md | | Create and extend complete visual brand systems through the Higgsfield CLI and bundled determinist… |
higgsfield-generatehiggsfield-generate/SKILL.md | | Generate images/videos/3D assets/audio via Higgsfield AI. Defaults: GPT Image 2.5 for image/design… |
higgsfield-marketplace-cardshiggsfield-marketplace-cards/SKILL.md | | Generate marketplace product image cards through Higgsfield: compliant main image, secondary produ… |
higgsfield-product-photoshoothiggsfield-product-photoshoot/SKILL.md | | Generate brand-quality product images through Higgsfield product-photoshoot prompt enhancement on … |
higgsfield-soul-idhiggsfield-soul-id/SKILL.md | | Train a Soul Character — a personalized model on a person's face that Higgsfield uses for identity… |
higgsfield-video-explainerhiggsfield-video-explainer/SKILL.md | | Build a complete non-photoreal narrated explainer or story video from ordered 10-second blocks: on… |
higgsfield-websiteshiggsfield-websites/SKILL.md | | Build, edit, and deploy full-stack websites, apps and games via the Higgsfield CLI (`higgsfield we… |
higgsfield-youtube-thumbnailhiggsfield-youtube-thumbnail/SKILL.md | | Create high-click-through YouTube thumbnails and vertical video covers through the Higgsfield CLI.… |
| 技能 | 描述 |
|---|---|
runway-devskills/runway-dev/SKILL.md | Foundation for building, modifying, debugging, or verifying Runway Dev Platform integrations in an a… |
runway-dev-charactersskills/runway-dev-characters/SKILL.md | Build, modify, debug, or verify Runway Characters integrations: inspect preset or custom avatars wit… |
runway-dev-model-routersskills/runway-dev-model-routers/SKILL.md | Build, modify, debug, or verify Runway Model Routers: inspect live config and eligible models via MC… |
runway-dev-modelsskills/runway-dev-models/SKILL.md | Build, modify, debug, or verify Runway model generation in an application: discover accessible model… |
runway-dev-recipesskills/runway-dev-recipes/SKILL.md | Choose, build, modify, debug, or verify Runway recipe integrations: match a recipe to the user's use… |
runway-dev-workflowsskills/runway-dev-workflows/SKILL.md | Build, modify, debug, or verify integrations that expose Runway app workflows as API endpoints. Use … |
rw-check-org-detailsskills/rw-check-org-details/SKILL.md | Query the Runway API for organization details: rate limits, credit balance, usage tier, and daily ge… |
rw-generate-audioskills/rw-generate-audio/SKILL.md | Generate audio using the Runway API via runnable scripts. Supports TTS, sound effects, voice isolati… |
rw-generate-imageskills/rw-generate-image/SKILL.md | Generate images directly using the Runway API via runnable scripts. Supports text-to-image with opti… |
rw-generate-videoskills/rw-generate-video/SKILL.md | Generate videos directly using the Runway API via runnable scripts. Supports text-to-video, image-to… |
use-runway-apiskills/use-runway-api/SKILL.md | Directly use the Runway API from the agent to generate media, manage resources, and inspect account … |
| 技能 | 描述 |
|---|---|
runway-mediaskills/runway-media/SKILL.md | Generate and edit images, video, music, speech, and sound effects with Runway MCP. Use when the user… |
runway-workflowsskills/runway-workflows/SKILL.md | Build, inspect, validate, and run Runway editor workflow graphs via MCP. Use when the user asks to c… |
| 技能 | 描述 |
|---|---|
atlas-cloudatlas-cloud/SKILL.md | Atlas Cloud API integration skill — quickly call 300+ AI image generation, video generation, audio (… |
seedance-2-5-skillskills/seedance-2-5-skill/SKILL.md | >- Plan and generate controllable Seedance video using Seedream 5.0 Pro storyboards and Seedance 2.0… |
universal-video-prompt-skillskills/universal-video-prompt-skill/SKILL.md | >- Write one model-agnostic video prompt spec, then compile it to whichever video model you can actu… |
| 技能 | 描述 |
|---|---|
character-designskills/character-design/SKILL.md | > Build consistent character designs and character media with genmedia. Use this for original charac… |
cinematographyskills/cinematography/SKILL.md | > Design cinematic image and video prompts for genmedia. Use this for shot language, camera movement… |
commercialskills/commercial/SKILL.md | > Plan and run commercial image or video production with genmedia. Use this for product photography,… |
fal-gamedevskills/fal-gamedev/SKILL.md | > Generate 2D pixel art game assets, characters, sprite sheets, background removal, and game backgro… |
fal-models-catalogskills/fal-models-catalog/SKILL.md | > Choose the right fal.ai endpoint for a given task. Modality-organized catalog of production endpoi… |
fal-promptingskills/fal-prompting/SKILL.md | > Model-family-specific prompt craft for fal.ai endpoints. Trigger when the user mentions a specific… |
fal-recipesskills/fal-recipes/SKILL.md | > Use-case-driven multi-step pipelines on fal.ai. Trigger when the user asks for a specific kind of … |
fal-redesignskills/fal-redesign/SKILL.md | Upgrade a coded website to award-tier, editorially-crafted design using fal.ai. Takes a local HTML f… |
fal-regenerate-3dskills/fal-regenerate-3d/SKILL.md | Build a fully-interactive 3D character-selector experience powered entirely by fal.ai. Generates sty… |
fal-workflowskills/fal-workflow/SKILL.md | Author and execute multi-step media pipelines on fal.ai. Two modes: (A) declarative workflow JSON fi… |
fan-camskills/fan-cam/SKILL.md | > Create personalized live sports broadcast fan-cam videos with genmedia. Use this for realistic spe… |
genmediaskills/genmedia/SKILL.md | > Use the genmedia CLI to search, inspect, run, and manage 1200+ fal.ai model endpoints. Trigger whe… |
genmedia-workflowskills/genmedia-workflow/SKILL.md | > Design and execute multi-step media workflows with genmedia. Use this for pipelines that combine p… |
marketingskills/marketing/SKILL.md | > Plan and run campaign-level marketing asset production with genmedia. Use this for launch kits, ca… |
model-routingskills/model-routing/SKILL.md | > Choose default fal.ai endpoint IDs for genmedia production skills. Use this with commercial, marke… |
storytellingskills/storytelling/SKILL.md | > Build multi-shot narrative image, video, and audio workflows with genmedia. Use this for storyboar… |
ugcskills/ugc/SKILL.md | > Plan and run UGC-style creator ads and social proof videos with genmedia. Use this for direct-to-c… |
| 技能 | 描述 |
|---|---|
agent-simplificationarchitect/skills/agent-simplification/SKILL.md | Simplify a complex ElevenLabs voice agent (typically a large workflow agent) into a leaner architect… |
architect-agent-memoryarchitect/skills/architect-agent-memory/SKILL.md | Use when the user wants the agent to remember, learn, save, or memorize a fact, or reports a one-off… |
architect-branches-versions-mergearchitect/skills/architect-branches-versions-merge/SKILL.md | Use when working with agent branches, versions, drafts, traffic splits, or merges. Fires on "make a … |
architect-create-client-toolarchitect/skills/architect-create-client-tool/SKILL.md | Use when the user wants the agent to trigger something in their own browser, app, or SDK during a ca… |
architect-create-llm-testarchitect/skills/architect-create-llm-test/SKILL.md | Use when the user wants a single-turn test that checks WHAT the agent says for a given turn. Fires o… |
architect-create-simulation-testarchitect/skills/architect-create-simulation-test/SKILL.md | Use when the user wants a full multi-turn conversation test where a simulated user talks to the agen… |
architect-create-tool-testarchitect/skills/architect-create-tool-test/SKILL.md | Use when the user wants a test asserting the agent CALLS a specific tool (with specific parameters, … |
architect-create-webhook-toolarchitect/skills/architect-create-webhook-tool/SKILL.md | Use when the user wants to give an agent a NEW webhook / server / HTTP tool so it can call an extern… |
architect-edit-existing-toolarchitect/skills/architect-edit-existing-tool/SKILL.md | Use when the user wants to change an existing tool on their agent (rename it, fix its description, c… |
architect-edit-string-fieldsarchitect/skills/architect-edit-string-fields/SKILL.md | Use when changing wording inside a long text field on an agent (system prompt, first message / greet… |
architect-edit-workflowsarchitect/skills/architect-edit-workflows/SKILL.md | Use when the user wants to build or change an agent's workflow or a specific node ("add a node", "co… |
architect-explain-test-runsarchitect/skills/architect-explain-test-runs/SKILL.md | Use when the user asks why a test or test run passed or failed, why one run in a repeat set differs,… |
architect-explore-agentarchitect/skills/architect-explore-agent/SKILL.md | Use when starting a task that needs an agent's current setup, or when another skill tells you to exp… |
architect-generate-agentarchitect/skills/architect-generate-agent/SKILL.md | Use when the user asks to generate, build, or create a new agent from a description ("create an agen… |
architect-get-agent-ci-greenarchitect/skills/architect-get-agent-ci-green/SKILL.md | Use when an agent's test suite is red and needs to be driven to green. Fires on "get CI green", "the… |
architect-llm-selectionarchitect/skills/architect-llm-selection/SKILL.md | Use when choosing or recommending an LLM for an ElevenLabs agent, or answering "which model should t… |
architect-manage-proceduresarchitect/skills/architect-manage-procedures/SKILL.md | Use when you want to add, edit, rename, inspect, or list an agent's procedures, or when a procedure … |
architect-migrate-from-competitorarchitect/skills/architect-migrate-from-competitor/SKILL.md | Use when the user wants to move a voice agent onto ElevenLabs Conversational AI from another platfor… |
architect-migrate-to-proceduresarchitect/skills/architect-migrate-to-procedures/SKILL.md | Use when the user wants to migrate a system-prompt-driven agent to a procedure-driven setup, pull st… |
architect-mock-all-toolsarchitect/skills/architect-mock-all-tools/SKILL.md | Use when a simulation test needs every tool call mocked so runs are deterministic and never hit live… |
architect-post-call-dataarchitect/skills/architect-post-call-data/SKILL.md | Use when the user wants to extract structured fields from finished calls (data collection) or define… |
architect-review-live-callsarchitect/skills/architect-review-live-calls/SKILL.md | Review an agent's recent finished conversations to find what is actually going wrong in production, … |
architect-schedule-launcharchitect/skills/architect-schedule-launch/SKILL.md | Use when preparing an agent change now but applying it later at a specific moment (product launch, m… |
architect-secure-for-productionarchitect/skills/architect-secure-for-production/SKILL.md | Use when a customer asks how to make their agent safe, secure, or production-ready, or how to roll i… |
architect-structured-proceduresarchitect/skills/architect-structured-procedures/SKILL.md | Use when you want to create, rewrite, inspect, or fix a structured / deterministic / flow-style proc… |
architect-troubleshoot-tool-errorsarchitect/skills/architect-troubleshoot-tool-errors/SKILL.md | Use when an agent tool (webhook/server, client, system, or MCP) errors, fails validation, won't save… |
architect-turn-taking-latencyarchitect/skills/architect-turn-taking-latency/SKILL.md | Use when the user asks about turn taking, speculative turns, agent response latency, preparing respo… |
architect-update-config-safelyarchitect/skills/architect-update-config-safely/SKILL.md | Use when changing an agent setting (LLM, voice, TTS model, language, first message, ASR, guardrails,… |
code-toolsarchitect/skills/code-tools/SKILL.md | Generate JavaScript/TypeScript modules for ElevenLabs code tools — sandbox tools that export a defau… |
fix-agent-qa-ticketarchitect/skills/fix-agent-qa-ticket/SKILL.md | > Fix an Architect QA triage ticket (agtqa_*) end-to-end via the raw agents API: fetch the ticket + … |
agentsskills/general/agents/SKILL.md | Build voice AI agents with ElevenLabs. Use when creating voice assistants, customer service bots, in… |
dubbingskills/general/dubbing/SKILL.md | Dub audio and video into other languages using the ElevenLabs Dubbing API (dubbing_v2), preserving t… |
musicskills/general/music/SKILL.md | Generate music using ElevenLabs Music API. Use when creating instrumental tracks, songs with lyrics,… |
setup-api-keyskills/general/setup-api-key/SKILL.md | Guides users through setting up an ElevenLabs API key for ElevenLabs MCP tools. Use when the user ne… |
sound-effectsskills/general/sound-effects/SKILL.md | Generate sound effects from text descriptions using ElevenLabs. Use when creating sound effects, gen… |
speech-engineskills/general/speech-engine/SKILL.md | Add real-time voice conversations to a custom agent runtime with ElevenLabs Speech Engine. Use when … |
speech-to-textskills/general/speech-to-text/SKILL.md | Transcribe audio to text using ElevenLabs Scribe v2. Use when converting audio/video to text, genera… |
text-to-speechskills/general/text-to-speech/SKILL.md | Convert text to speech using ElevenLabs voice AI. Use when generating audio from text, creating voic… |
voice-changerskills/general/voice-changer/SKILL.md | Transform the voice in an audio recording into a different target voice while preserving emotion, ti… |
voice-isolatorskills/general/voice-isolator/SKILL.md | Remove background noise and isolate vocals/speech from audio using ElevenLabs Voice Isolator (audio … |
agents-platformskills/mcp/agents-platform/SKILL.md | Manage ElevenLabs voice agents through the connected ElevenLabs MCP server. Use when the user asks t… |
creative-studioskills/mcp/creative-studio/SKILL.md | Generate and edit media through the connected ElevenLabs MCP server — speech, images, video, music, … |
| 技能 | 描述 |
|---|---|
academy-guideskills/academy-guide/SKILL.md | > Stop and check this skill before finishing any reply to a question about how to use Claude or a Cl… |
algorithmic-artskills/algorithmic-art/SKILL.md | Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. U… |
brand-guidelinesskills/brand-guidelines/SKILL.md | Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit fr… |
canvas-designskills/canvas-design/SKILL.md | Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this … |
claude-apiskills/claude-api/SKILL.md | |- Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, M… |
discernment-nudgeskills/discernment-nudge/SKILL.md | > After you give a substantive answer or draft that the user may act on — advice or recommendations,… |
doc-coauthoringskills/doc-coauthoring/SKILL.md | Guide users through a structured workflow for co-authoring documentation. Use when user wants to wri… |
docxskills/docx/SKILL.md | Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx fi… |
frontend-designskills/frontend-design/SKILL.md | Guidance for distinctive, intentional visual design when building new UI or reshaping an existing on… |
internal-commsskills/internal-comms/SKILL.md | A set of resources to help me write all kinds of internal communications, using the formats that my … |
mcp-builderskills/mcp-builder/SKILL.md | Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact wi… |
pdfskills/pdf/SKILL.md | Use this skill whenever the user wants to do anything with PDF files. This includes reading or extra… |
pptxskills/pptx/SKILL.md | Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. Th… |
skill-creatorskills/skill-creator/SKILL.md | Create new skills, modify and improve existing skills, and measure skill performance. Use when users… |
slack-gif-creatorskills/slack-gif-creator/SKILL.md | Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, valida… |
theme-factoryskills/theme-factory/SKILL.md | Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML la… |
web-artifacts-builderskills/web-artifacts-builder/SKILL.md | Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern fronten… |
webapp-testingskills/webapp-testing/SKILL.md | Toolkit for interacting with and testing local web applications using Playwright. Supports verifying… |
xlsxskills/xlsx/SKILL.md | Use this skill any time a spreadsheet file is the primary input or output. This means any task where… |
template-skilltemplate/SKILL.md | Replace with description of the skill and when Claude should use it. |