安装指南

1. ClawHub CLI 从源直接安装技能的最快方式。
   npx clawhub@latest install shapeless
2. 手动安装 将技能文件夹复制到以下位置之一
   全局模式
   ~/.openclaw/skills/
   工作区
   /skills/
   优先级：工作区 > 本地 > 内置
3. 提示词安装 将此提示词复制到 OpenClaw 即可自动安装。
   请帮我使用 Clawhub 安装 shapeless。如果尚未安装 Clawhub，请先安装（npm i -g clawhub）。
   更倾向于下载？
   获取包含原生技能文件的ZIP压缩包。
   下载技能 (.zip)

什么是

Shapeless 通过 MCP 工具或 Shapeless CLI 将 AI 代理连接到用户的社交媒体账号。它支持持久化内容任务、帖子审核与发布、定时代理工作流、媒体资源，以及用于复用品牌语调、定位和产品信息的 Brand Memory。
此 Openclaw Skills 集成可帮助协调内容工作，同时遵守账号权限和特定平台的要求。凭据具有读取、写入和发布权限范围；发布操作会立即生效，除非用户明确提出要求，否则必须先获得用户确认。对于生成式任务，请使用 Shapeless jobs，以便服务器应用账号的 Brand Memory、已连接的平台和媒体处理流程。

应用场景

使用持久化的 Shapeless 内容任务起草帖子、轮播内容、图片或配有旁白的视频。
在批准帖子进入排期前，审核拟发布的帖子及其媒体。
将帖子安排在指定时间发布、添加到下一个可用的队列时段，或在获得授权后立即发布。
查看任务状态、检查文字稿和输出，或使用更新后的指令继续任务。
使用常驻代理创建定期内容工作流。
在 Brand Memory 中修正品牌语调、定位或产品信息，让未来的内容采用更新后的指导信息。
上传并重复使用账号媒体，或将现有媒体附加到特定帖子或内容任务。
在撰写内容前检查平台限制和设置，以避免验证错误。

工作原理

验证 Shapeless 账号身份，并调用 me 验证凭据及查看套餐和额度余额。
必要时查阅 Shapeless 文档或 OpenAPI 规范；使用平台和连接工具来发现目标平台、帖子要求和可用的账号资源。
对于生成式任务，使用明确的目标创建持久化任务。服务器会独立运行该任务，之后可以查看或继续其状态、文字稿和输出。
对于直接创建帖子，先检查平台规则，包括文本限制、媒体要求、标题要求、是否支持首条评论以及设置架构。
在批准前，使用帖子详情审核拟发布的内容和媒体。帖子会依次处于拟议、已排期和已发布状态。
使用特定的 scheduledAt 时间安排发布，或使用 queue 排入下一个可用时段；两种选项不能同时使用。只有在用户授权实时操作后，才能发布或批准。
如果用户更正了长期适用的品牌指导信息，请更新 Brand Memory；也可按要求管理定期代理和媒体资源。

配置指南

通过 MCP 集成进行连接。运行 /mcp，选择 Shapeless，选择 Authenticate，然后在浏览器中完成 OAuth。凭据的权限范围决定代理能否读取、写入或发布。
通过 Shapeless 工具调用 me，确认身份验证并查看账号套餐和额度余额。
若要使用 stdio CLI 替代方案，请在 https://shapelessai.com/studio/api-keys 创建 API 密钥，然后进行身份验证或将密钥作为环境变量提供：
npx shapelessai mcp
shapeless login

或直接提供 API 密钥：

export SHAPELESS_API_KEY=slk_...
操作前阅读相关 API 契约。文档位于 https://shapelessai.com/docs，也提供 Markdown 页面，例如 https://shapelessai.com/docs/posts.md，完整参考文档则位于 https://shapelessai.com/llms-full.txt。OpenAPI 规范位于 https://shapelessai.com/api/openapi.json。
创建特定平台的帖子前，调用 platforms_list 和 connections_list，以获取平台规则和目标连接 ID。引用本地媒体之前，请先上传媒体。

数据架构

Shapeless 围绕账号凭据和若干相关资源类型组织工作：
资源 用途和重要字段
Credentials 使用具有 read、write 和 publish 权限范围的 OAuth 或 API key 访问权限。只有 publish 权限范围允许执行发布操作。
Jobs 持久化的服务器端内容任务。使用目标创建；通过 jobs_list、jobs_get、jobs_brief 或 jobs_tail 检查；通过 jobs_run、jobs_continue 和 jobs_stop 控制。
Posts 具有拟议 → 已排期 → 已发布生命周期的社交内容。通过 posts_list 或 posts_get 审核；通过批准、驳回和发布操作进行管理。
Post fields 包括 connectionId、text、可选的 scheduledAt 或 queue、mediaKeys、可选的 title、特定平台的 settings，以及可选的 firstComment。scheduledAt 和 queue 不能同时使用。
Media assets 账号文件通过媒体密钥寻址，并通过 mediaKeys 附加到消息（每条消息最多六个）。使用前，通过 CLI 或 assets API 上传本地文件。
Brand Memory 持久化的账号知识，例如品牌语调、定位和产品信息，使用 brain_tree、brain_read 和 brain_write 管理。
Agents 用于定期内容工作的常驻排期，通过 agents_list、agents_save 和 agents_wake 管理。
Actors 视频人脸和声音，可通过 characters_list 查找；characters_voice 用于设计或克隆声音。克隆声音需要拥有样本的相关权利，并会消耗额度。
每个平台的规则和 settings JSON Schema 由 platforms_list 提供。验证可能会在创建不兼容的帖子时拒绝请求，并返回 422 响应。Free 套餐在发布轨道上的限制为每个 UTC 日十篇帖子；生成式任务会消耗额度，而撰写、排期和发布不会。

高级特性

持久化异步任务会在代理不再连接时继续在服务器上运行；可检查实时进度，或使用新指令恢复运行。
任务可以使用账号的 Brand Memory、已连接的平台和媒体处理流程，生成了解上下文的内容。
管理用于定期内容工作流的常驻代理，包括保存配置，以及在获得授权后唤醒代理。
维护可重复使用的 Brand Memory，让对品牌语调或产品信息的修正影响未来内容，而不只是单篇帖子。
一条消息最多可附加六个账号媒体资源；服务器能够解读图片内容，而不只是依赖文件名。
撰写内容前，先了解各平台的文本限制、媒体规则、必需标题、首条评论支持情况和设置架构。
将批准、发布和唤醒代理视为实时操作：除非用户明确要求执行该具体操作，否则应先向用户确认；批准前应审核帖子文本和媒体。
遵守操作限制：API 每个密钥每小时允许 600 次请求，因此应适度轮询任务状态。Free 套餐的帖子限制按 UTC 发布日计算。

name: shapeless description: Drive the user's Shapeless account - draft and publish social posts, run durable content jobs, manage standing agents and Brand Memory. Use when the user asks to create, review, schedule, or publish social content, or to check on their Shapeless jobs, posts, agents, or brand.

Driving Shapeless

Shapeless runs the user's social presence. You reach it through the shapeless MCP tools this plugin ships (or the shapeless CLI, same surface). Everything is one account, gated by a credential - the OAuth sign-in or an API key - with scopes: read, write, publish. Only publish puts content into the world.

The documentation

Do not guess this API. It is published, and it answers Markdown:

https://shapelessai.com/docs - one page per subject. Append .md to any path (https://shapelessai.com/docs/posts.md) or send Accept: text/markdown to get the source instead of the page.
https://shapelessai.com/llms-full.txt - every page in one fetch. Read this when you need the whole surface; read a single .md page when you need one answer.
https://shapelessai.com/api/openapi.json - OpenAPI 3.1 for every route.

Straight to the page you need: posts · platforms · api · jobs · brand memory · auth.

First contact

Call me to confirm the credential works and see the plan and credit balance. If it fails, the user signs in over OAuth: run /mcp, pick shapeless, choose Authenticate, and allow in the browser tab. The stdio fallback (npx shapelessai mcp) needs a key instead: minted at https://shapelessai.com/studio/api-keys, then shapeless login or export SHAPELESS_API_KEY=slk_....

The shape of the work

Jobs are durable server-side runs: jobs_create with a goal ("draft three posts about the beta launch") returns an id and keeps going whether or not you stay attached. jobs_list lists them, jobs_get shows the transcript and outputs, jobs_brief is the compact version for continuing, jobs_tail watches a run live, jobs_run presses Run on a proposed plan, jobs_continue resumes a stuck or finished run with new instructions, and jobs_stop stops one. Prefer a job for anything generative - posts, carousels, images, narrated video - the server holds the account's Brand Memory, connected platforms, and media pipeline.

Media rides the message as mediaKeys: anything already in the account (assets_list). Up to 6 per message. The agent reads them for real - an image's pixels, not just its filename. The hosted server has no disk, so a local file goes in first with the CLI (shapeless assets upload ./file) or PUT /api/brain/assets/{filename}, which returns the key.

Posts are the queue: proposed -> scheduled -> published. posts_list / posts_get to review, posts_approve to accept a proposal into the schedule, posts_dismiss to reject, posts_publish to put one out now.

posts_create puts a post you wrote on a real account. Call platforms_list first - it carries each platform's text limit, media rules, whether a title is required, first-comment support, and the JSON Schema for its settings. Then:

{
"connectionId": "",
"text": "The post.",
"scheduledAt": "2026-09-21T09:00:00+03:00", // omit for now
"queue": true, // instead of scheduledAt: the next free slot
"mediaKeys": ["..."], // media already in the account
"title": "The video title", // YouTube requires one
"settings": { }, // per platform; platforms_list has the schema
"firstComment": "Link: https://..." // LinkedIn, X, Bluesky only
}

scheduledAt and queue are exclusive. A platform rule refuses at creation with a 422 that names the rule, never at publish time. The CLI equivalent is shapeless posts create --to --text "..." [--at | --queue] [--media k1,k2] [--title "..."] [--settings '{json}'] [--first-comment "..."].

The Free plan posts ten a day on the rail, counted on the UTC day each post goes out on - so a week planned ahead is ten a day, not ten in total, and approving a proposal counts the same as creating one. The eleventh answers 402 {code: "free_daily_cap", limit, day, resetsAt} naming the day that is full: move the post to a day with room, or tell the user their account is on Free. Paid plans have no cap. Composing, scheduling and publishing never spend credits; Free also carries $5 of credits a month for the generative work.

Agents are standing schedules (agents_list, agents_save, agents_wake) - recurring content work the server runs on its own.

Brand Memory (brain_tree, brain_read, brain_write) is the account's durable knowledge: voice, positioning, product facts. Edit it when the user corrects how their brand should sound - that fixes every future post, not just one.

Actors (characters_list, characters_voice) are the faces and voices videos use. characters_voice designs a voice from a description or clones one from a sample the user holds the rights to - it spends credit, so confirm first.

Ground rules

Tools whose descriptions say they publish or put content out are live: approving, publishing, waking an agent. Confirm with the user before calling them unless they explicitly asked for that exact action.

Review before approving: read the post's actual text and media via posts_get, don't approve blind.

Generative quality issues (wrong tone, wrong facts) are Brand Memory issues - offer to fix the source, not just the symptom.

Putting a file in the brand library is for reuse; passing its media key on a message is what makes this turn's agent look at it. They are different asks - do the one you were asked for.

The API is rate-limited at 600 requests/hour per key; poll jobs with restraint.

Read posts_create's rules before writing the post, not after a 422: the character limit and the media rules are in platforms_list, and a draft written past the limit is a rewrite.

The full contract - routes, scopes, refusal codes - is at https://shapelessai.com/docs/api (Markdown at https://shapelessai.com/docs/api.md).

字帖手写练习助手
阿里云 OSS Endpoint 与内网诊断