Token导航 LogoToken导航

Agent Skill · 开发

post-see-scheduler(后见调度程序)

post-see-scheduler 用于整理文档、README、Markdown 和说明材料,适合在 OpenClaw 中需要把零散信息整理成结构清晰的文档时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

post-see-scheduler 是开发类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在开发类的 21,746 个 Skill 里排第 7,495。

总安装 3,745周安装 153GitHub Stars 公开资料未说明下载 1,212核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.0

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:post-see-scheduler(后见调度程序)
来源仓库:https://github.com/makani20/post-see-scheduler
安装命令:
openclaw skills install post-see-scheduler
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install post-see-scheduler

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

用于将 OpenClaw 接入 Post See API,实现自主社交媒体管理。适合在 Instagram、LinkedIn 等平台安排、发布或管理内容排期。通过 clawhub 安装后,可批量导入素材并设置发布时间计划。需授权对应社交账户权限,注意各平台的内容政策与频率限制。

建议定期检查 API 调用日志,确保任务按计划稳定执行。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install post-see-scheduler;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

post-see-scheduler 怎么安装?

在终端执行 openclaw skills install post-see-scheduler。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

post-see-scheduler 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

post-see-scheduler 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

post-see-scheduler 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

post-see-scheduler 用的人多吗?

公开数据是累计安装 3,745 次,近一周安装 153 次,下载 1,212 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

post-see-scheduler 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
post-see-scheduler

后见调度程序 · 本页

3,745—接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
post-see-post-scheduling-skill
description
Turn your OpenClaw into an autonomous social media manager using the Post See API. Use when scheduling, posting, or managing content across Instagram, LinkedIn, X, Facebook, Threads, Bluesky, Pinterest, YouTube, Mastodon, Discord, and other networks Post See supports.
version
1.1.0
metadata
openclaw
requires
env
bins
primaryEnv
POST_SEE_API_KEY
homepage
https://api.post-see.com/

Social Media Assistant (via Post See / post-see.com)

Autonomously manage social scheduling and publishing through the Post See REST API.

Canonical spec: download or reference https://api.post-see.com/openapi.yaml (same host as the docs).

Bundled helpers (optional): this package includes prompts/generate-post.txt, prompts/schedule-post.txt, skill.json, and Node CLIs under actions/*.js (Node 18+). The runtime instructions below are sufficient without executing those files.

Setup

  1. Create a Post See account at post-see.com.
  2. Connect your social accounts and link them into a workspace.
  3. Enable API access and create an API key (pk_live_… as shown in the API docs “Try it”).
  4. Store your API key in workspace .env:
   POST_SEE_API_KEY=pk_live_xxxxx
  1. Optional: save the OpenAPI document locally for offline reference:
   curl -sS https://api.post-see.com/openapi.yaml -o post-see-openapi.yaml
  1. ffmpeg — used when you work from local video files (extract a frame to read on-screen text before writing captions). Post See accepts public HTTPS URLs in media_urls; host files on your storage/CDN first.

Auth

All requests use a Bearer token:

Authorization: Bearer <POST_SEE_API_KEY>
Content-Type: application/json

Base URL: https://api.post-see.com/api/v1

Responses

  • Success: { "data": …, "meta": { "api_version": "1.0", … } }
  • Error: { "error": { "code", "message", "details?" }, "meta": … } — branch on error.code (e.g. unauthorized, workspace_forbidden, post_locked, validation_error).

Workspace scope

Pass workspace_id as a query parameter (or X-Workspace-Id where supported). Resolve membership before trusting any id. Roles: readonly can read; creating/updating/deleting posts requires collaborator, admin, or owner.

Optional: timezone query or X-Timezone (IANA) for schedule display or naive local times.

Platform slugs (platform field)

Documented today (lowercase; treat as opaque — new values may appear): bluesky, discord, facebook, instagram, linkedin, mastodon, pinterest, threads, x, youtube. X uses x, not twitter. Always match the platform string returned from GET /social-accounts for the chosen connection.

Immediate publish on create (POST /posts, per OpenAPI): linkedin, facebook, instagram, x, pinterest, bluesky, threads. Others (e.g. youtube, mastodon, discord) support drafts and scheduled posts via scheduled_at / worker — do not assume synchronous publish in the create response.

Core workflow

1. List workspaces (get workspace_id)

GET /workspaces

Use data.workspaces[] → id, name, myRole.

2. Get linked social accounts

GET /social-accounts?workspace_id=<workspace_id>

Returns data.connections[] with id (use as connection_id), platform, platform_username, is_connected, needs_reauth, and for Pinterest optionally default_pin_destination_link. OAuth tokens are never returned. If needs_reauth is true, the user must reconnect in the product before publish will succeed.

3. List and inspect posts

GET /posts?workspace_id=<id>&status=<draft|scheduled|published|fail>&platform=<slug>&page=1&limit=20
GET /posts/{id}

4. Create post

POST /posts

Required: workspace_id.

Typical JSON body:

{
  "workspace_id": 7,
  "connection_id": 42,
  "platform": "instagram",
  "text": "Caption and #hashtags",
  "caption": "Optional alias for text",
  "scheduled_at": "2026-04-01T14:00:00Z",
  "media_urls": ["https://cdn.example.com/asset.jpg"]
}
  • Omit scheduled_at / date_time for drafts.
  • media_urls: public HTTPS URLs only (upload to your storage first).
  • Pinterest: board_id or boardId; optional default outbound URL may exist on the connection.
  • YouTube: post_title, youtube_options (object, default {}) for product-specific hints (privacy, category, shorts vs long-form, etc.).
  • All platforms: platform_options (object, default {}) for forward-compatible flags (visibility, audience, etc.).

Deprecated: social_account_ids — prefer connection_id.

201 may include data.publish_results when immediate publish was attempted.

5. Update or delete posts

PUT /posts/{id}
DELETE /posts/{id}

Use PUT, not PATCH. 409 post_locked if the post is published or cannot be changed.

6. Check publish results

GET /post-results?workspace_id=<id>&post_id=<optional>&page=1&limit=20
GET /post-results/{id}

Inspect data.results[]: status (pending | success | fail), external_post_url, nested error (e.g. publish_failed).

7. Current user (optional)

GET /me
PATCH /me

Team / workspace admin (optional)

Routes under /workspaces/... (members, invitations, transfer) are destructive or role-sensitive. Use only when the user explicitly asks; see OpenAPI for owner vs admin requirements.

Recommended workflow for video content

  1. Store videos in a local folder.
  2. Extract a frame with ffmpeg to read any text overlays:
   ffmpeg -i video.mp4 -ss 00:00:04 -frames:v 1 frame.jpg -y
  1. Write caption from content + hashtags; upload media to HTTPS storage and copy URLs.
  2. POST /posts with media_urls, connection_id, platform, and schedule (or draft).
  3. Move posted assets to a posted/ subfolder to avoid duplicates.
  4. After the scheduled time, GET /post-results?post_id=... to confirm status and external_post_url.

Tips

  • Resolve workspace_id and connection_id before every create/update; guessing ids causes 403 or empty lists.
  • Stagger posts across the day for better reach when scheduling manually.
  • Keep hashtags focused (roughly 4–5 where appropriate for the network).
  • Re-fetch openapi.yaml when integrating — new fields and platforms appear there first.
  • Use a test workspace and non-production accounts before automating brands you care about.

Safety

Use a least-privilege API key; revoke from the dashboard if leaked. This skill implies the agent may read .env, workspace files, and public media URLs you provide — avoid sensitive paths and shared/synced folders you do not trust. If you do not want autonomous posting, require human confirmation before POST /posts or restrict agent autonomy in your OpenClaw config.

平台分布

OpenClaw

78.95%
按下载量换算957

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

可疑

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills