Schedule social media from any chat app

# posterly for OpenClaw

posterly is the publish layer. OpenClaw is the chat-app layer. Install the skill, set POSTERLY_API_KEY, and schedule from WhatsApp, Telegram, Slack, or Discord after the user approves.

posterly publishes to 18 platforms: Instagram, Facebook, TikTok, X, LinkedIn, YouTube, Pinterest, Threads, Google Business, Telegram, Bluesky, Discord, Slack, Mastodon, Dev.to, Hashnode, WordPress, Lemmy.

## Connect

ClawHub listing: https://clawhub.ai/awpthorp/posterly. Run this in your OpenClaw workspace, then start a new session:

Skill-first:
npx clawhub@0.23.3 install posterly
export POSTERLY_API_KEY=pst_live_your_key_here

The same key works for MCP and REST. Prefer MCP when the OpenClaw runtime can use it. Hosted URL: https://www.poster.ly/api/mcp.

Do not publish unattended from a heartbeat until the user has approved the caption, account, media, and schedule.

## Are we connected yet?

1. Call `whoami` (no params). Confirm the user, scopes, and workspaces.
2. Call `list_accounts` (`workspace_id` optional). If none are connected, stop and send the user to connect social accounts in posterly. Do not invent account IDs.
3. Prefer `validate_post` before `create_post`. Show the preview. Wait for a clear yes.
4. Only then call `create_post` with `confirm: true`. Never publish or schedule live without that approval.
5. Prefer `scheduled_at` (ISO 8601 UTC) or `find_available_slot` (`account_ids`, `timezone`, `count`). Do not publish immediately unless the user asks.

## Rules

- posterly is the publish layer. This client is the chat or agent layer.
- Never collect card details, posterly passwords, or social-network passwords. Send the user to https://www.poster.ly/agents/signup or https://www.poster.ly/dashboard/api.
- Point to https://www.poster.ly/mcp for the rest of the 61 hosted HTTP MCP tools (64 on the local stdio package).
- After a post is created, send the View in posterly link. Avoid raw JSON dumps unless the user asks to debug.

## Media (honest)

Chat attachments never reach MCP. The paperclip in this chat does not give posterly the file.

The ~4MB limit is the **Vercel request body** on posterly API routes (`/api/mcp`, `POST /api/v1/media/upload`). It is not an MCP protocol cap and not the plan storage cap. Base64 inflates files, so hosted `upload_media` is small images only (relay cap 5MB decoded).

- Public HTTPS URL: `upload_media` with `url` (optional `filename`, `content_type`) or pass `media_url` / `media_urls` on `validate_post` / `create_post`. Server fetch: about 5MB relay, 60MB hard cap. Large R2/S3 URLs fail with `remote_media_too_large`.
- Hosted `upload_media`: required `filename` + `base64_data`. Optional `content_type`. Hits the 4MB Vercel body. JPEG, PNG, GIF, WebP, MP4, MOV, WebM. HEIC is unsupported.
- Laptop file in ChatGPT web, Claude.ai, or Gemini web: `create_media_drop` (optional `filename`, optional `max_files`, 1 to 20, default 10). Send the user `drop_url` (`https://www.poster.ly/drop/<token>`). They open it with no dashboard login and drop up to 20 files per link (JPEG, PNG, GIF, WebP, MP4, MOV, WebM, or PDF up to 50MB for LinkedIn document posts; HEIC is not accepted). Then `list_media` (`drop_session_id`) and pass `public_url` to `validate_post` / `create_post`. This is not the chat paperclip.
- Larger files, when this client can HTTP PUT: `create_signed_upload` (`filename`, `content_type`, `size`, or `files` for 1 to 20 files in one call), PUT the raw bytes of each file to its `upload_url` (object storage, not a posterly API route) with the returned headers (send the returned `Content-Type` exactly: pinning is available per request with `pin_content_type: true`, and posterly may turn it on by default in the future), then pass `public_url` to `create_post`. That PUT does not hit the 4MB body. Plan video caps: Starter 500MB, Pro 750MB, Power 1GB, Agency 4GB. A PDF (up to 50MB) also works: create the post with `post_type` `document`, `media_url` set to its `public_url`, and a `document_title` in `settings` (LinkedIn only).
- Stdio `upload_media` also accepts `file_path` when the user gives a real local filesystem path. The local server reads the disk and uses signed upload for large files, so this does not hit the Vercel 4MB body. Never guess paths. Chat attachments are not a file_path.

## Starter tools

- `whoami` (none): Call first. Returns the authenticated user, API key scopes, and workspaces.
- `list_accounts` workspace_id?: Connected social accounts. Stop if this is empty and send the user to connect accounts in posterly.
- `validate_post` account_id or username+platform, caption, scheduled_at?, media_url?, media_urls?, post_type?, workspace_id?: Dry run. Does not create a post. Use this before showing a preview.
- `create_post` same as validate_post, plus confirm: true (required): Destructive write. Refuse unless the user clearly approved caption, account, media, and schedule.
- `upload_media` filename, base64_data (hosted), or url. content_type optional. Stdio also accepts file_path.: Hosted path is base64 with a decoded file of 5MB or less. With url, posterly fetches a public HTTPS URL into storage (localhost and private IPs are blocked). Chat paperclip files never arrive here.
- `create_signed_upload` filename, content_type, size, or files (1 to 20): Bypasses the Vercel ~4MB API body. Returns upload_url (object storage) and public_url. PUT raw bytes to upload_url, then pass public_url to create_post. Pass files to get up to 20 slots in one call (one per file, failed files reported in place, slots expire in 15 minutes). Use this when the client can PUT (Cursor, Claude Code, Codex).
- `create_media_drop` filename?, max_files?: Creates a no-login page at https://www.poster.ly/drop/<token> that takes up to 20 files (max_files, default 10). Send drop_url to the user. ChatGPT web, Claude.ai, and Gemini web laptop files use this, then list_media. Not the chat paperclip.
- `list_media` limit?, drop_session_id?: Newest media assets. After create_media_drop, pass drop_session_id and use public_url on validate_post / create_post.
- `find_available_slot` account_ids?, timezone?, workspace_id?, count?: Always pass timezone explicitly (IANA, e.g. Europe/London). Respects a 1-hour gap.
- `generate_captions` platforms (required), brief?, tone?, count?, mode?, source_caption?: Returns caption options only. It does not schedule or publish.
- `list_posts` status?, platform?, account_id?, workspace_id?, limit?: Upcoming or recent posts. status is scheduled, published, failed, or draft.

## Example prompts

- On WhatsApp: list my posterly accounts, then draft a LinkedIn and Instagram post for tomorrow morning. Show me the captions and wait.
- Find the next free slot, validate_post both drafts, and only schedule after I reply yes.
- I will paste a public image URL. Fetch it, write three caption options, and ask before scheduling.
- Set a weekday morning check: draft posts from ~/content/pending, show me, and wait for approval. Never publish unattended.
- If MCP is available, prefer whoami and list_accounts. If not, use REST with the same POSTERLY_API_KEY.
- After I approve, create_post with confirm true and send the dashboard link.
- Chat attachments in WhatsApp or Telegram are not MCP uploads. Ask for a public URL, a local file_path on the daemon machine, or a signed upload.

## Links

- Human landing: https://www.poster.ly/openclaw
- MCP hub: https://www.poster.ly/mcp
- OpenClaw guide: https://www.poster.ly/guides/openclaw-guide
- AI agents: https://www.poster.ly/agents
- Agent signup: https://www.poster.ly/agents/signup