Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
WhatsApp skill with a 3-rule security gate. Your agent speaks only when spoken to — in the right chat, by the right person.
WhatsApp skill with a 3-rule security gate. Your agent speaks only when spoken to — in the right chat, by the right person.
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
Everything you can do in WhatsApp, your AI agent can do too. This skill documents all WhatsApp capabilities available through OpenClaw's native channel integration. No external Docker services, no CLI wrappers — just direct WhatsApp Web protocol via Baileys.
OpenClaw with WhatsApp channel configured WhatsApp account linked via QR code (openclaw whatsapp login)
CategoryFeaturesMessagingText, media, polls, stickers, voice notes, GIFsInteractionsReactions, replies/quotes, edit, unsendGroupsCreate, rename, icon, description, participants, admin, invite links Total: 22 distinct actions
message action=send channel=whatsapp to="+34612345678" message="Hello!"
message action=send channel=whatsapp to="+34612345678" message="Check this out" filePath=/path/to/image.jpg Supported: JPG, PNG, GIF, MP4, PDF, DOC, etc.
message action=poll channel=whatsapp to="+34612345678" pollQuestion="What time?" pollOption=["3pm", "4pm", "5pm"]
message action=sticker channel=whatsapp to="+34612345678" filePath=/path/to/sticker.webp Must be WebP format, ideally 512x512.
message action=send channel=whatsapp to="+34612345678" filePath=/path/to/audio.ogg asVoice=true Critical: Use OGG/Opus format for WhatsApp voice notes. MP3 may not play correctly.
message action=send channel=whatsapp to="+34612345678" filePath=/path/to/animation.mp4 gifPlayback=true Convert GIF to MP4 first (WhatsApp requires this): ffmpeg -i input.gif -movflags faststart -pix_fmt yuv420p -vf "scale=trunc(iw/2)*2:trunc(ih/2)*2" output.mp4 -y
message action=react channel=whatsapp chatJid="34612345678@s.whatsapp.net" messageId="ABC123" emoji="🚀"
message action=react channel=whatsapp chatJid="34612345678@s.whatsapp.net" messageId="ABC123" remove=true
message action=reply channel=whatsapp to="34612345678@s.whatsapp.net" replyTo="QUOTED_MSG_ID" message="Replying to this!"
message action=edit channel=whatsapp chatJid="34612345678@s.whatsapp.net" messageId="ABC123" message="Updated text"
message action=unsend channel=whatsapp chatJid="34612345678@s.whatsapp.net" messageId="ABC123"
message action=group-create channel=whatsapp name="Project Team" participants=["+34612345678", "+34687654321"]
message action=renameGroup channel=whatsapp groupId="123456789@g.us" name="New Name"
message action=setGroupIcon channel=whatsapp groupId="123456789@g.us" filePath=/path/to/icon.jpg
message action=setGroupDescription channel=whatsapp groupJid="123456789@g.us" description="Team chat for Q1 project"
message action=addParticipant channel=whatsapp groupId="123456789@g.us" participant="+34612345678"
message action=removeParticipant channel=whatsapp groupId="123456789@g.us" participant="+34612345678"
message action=promoteParticipant channel=whatsapp groupJid="123456789@g.us" participants=["+34612345678"]
message action=demoteParticipant channel=whatsapp groupJid="123456789@g.us" participants=["+34612345678"]
message action=leaveGroup channel=whatsapp groupId="123456789@g.us"
message action=getInviteCode channel=whatsapp groupJid="123456789@g.us" Returns: https://chat.whatsapp.com/XXXXX
message action=revokeInviteCode channel=whatsapp groupJid="123456789@g.us"
message action=getGroupInfo channel=whatsapp groupJid="123456789@g.us" Returns: name, description, participants, admins, creation date.
WhatsApp uses JIDs (Jabber IDs) internally: TypeFormatExampleIndividual<number>@s.whatsapp.net34612345678@s.whatsapp.netGroup<id>@g.us123456789012345678@g.us When using to= with phone numbers, OpenClaw auto-converts to JID format.
Always use OGG/Opus format: ffmpeg -i input.wav -c:a libopus -b:a 64k output.ogg
Convert images to WebP stickers: ffmpeg -i input.png -vf "scale=512:512:force_original_aspect_ratio=decrease,pad=512:512:(ow-iw)/2:(oh-ih)/2:color=0x00000000" output.webp
Send an instant text message when an inbound message is received — fires at gateway level before model inference: { "channels": { "whatsapp": { "ackMessage": { "text": "⚡", "direct": true, "group": "never" } } } } FieldTypeDefaultDescriptiontextstring""Message to send (empty = disabled)directbooleantrueSend in direct chatsgroup"always" / "mentions" / "never""never"Group behavior This is different from ackReaction (which sends an emoji reaction). ackMessage sends a standalone message bubble — visible in WhatsApp Web even when reaction flips aren't.
WhatsApp has anti-spam measures. Avoid: Bulk messaging to many contacts Rapid-fire messages Messages to contacts who haven't messaged you first
To react/edit/unsend, you need the message ID. Incoming messages include this in the event payload. For your own sent messages, the send response includes the ID.
Featurewhatsapp-ultimatewacliwhatsapp-automationgif-whatsappNative integration✅❌ (CLI)❌ (Docker)N/ASend text✅✅❌❌Send media✅✅❌❌Polls✅❌❌❌Stickers✅❌❌❌Voice notes✅❌❌❌GIFs✅❌❌✅Reactions✅❌❌❌Reply/Quote✅❌❌❌Edit✅❌❌❌Unsend✅❌❌❌Group create✅❌❌❌Group management✅ (full)❌❌❌Receive messages✅✅✅❌Two-way chat✅❌❌❌External depsNoneGo binaryDocker + WAHAffmpeg
Download images, videos, documents, and audio from past WhatsApp messages stored in the history database. Uses Baileys' downloadContentFromMessage with the media keys stored in raw_json — no active socket needed.
cd ~/src/tinkerclaw && npx tsx src/whatsapp-history/download-media.ts --list-media [--since YYYY-MM-DD] [--chat <jid|name>] [--limit N]
cd ~/src/tinkerclaw && npx tsx src/whatsapp-history/download-media.ts --id <messageId> [--out <directory>] Default output: ~/.openclaw/workspace/data/wa-media/<messageId>.<ext>
Media URLs on WhatsApp servers expire after ~2 weeks. Download promptly. Works for: images, videos, documents, audio, stickers, voice notes. Extension auto-detected from the message's mimetype. The raw_json column in the messages table must contain the original Baileys proto (live-captured messages only, not imported .txt exports).
Added: Media download from history — download-media.ts script extracts media keys from stored raw_json and downloads/decrypts directly from WhatsApp CDN without needing an active socket connection.
Added: ackMessage — gateway-level instant message acknowledgment. Sends a configurable text message (e.g. ⚡) the moment an inbound message arrives, before any model inference. Fires at the same speed as ackReaction (emoji flip). Useful as a visual cue to distinguish your messages from bot replies in WhatsApp Web where reaction flips aren't visible.
Fixed: Chat search now resolves LID/JID aliases — searching by chat name finds messages across both @lid and @s.whatsapp.net JID formats Added: resolveChatJids() cross-references chats, contacts, and messages tables to discover all JID aliases for a given chat filter Improved: Search falls back to original LIKE behaviour if no JIDs resolve, so no regressions
Your Agent ↓ OpenClaw message tool ↓ WhatsApp Channel Plugin ↓ Baileys (WhatsApp Web Protocol) ↓ WhatsApp Servers No external services. No Docker. No CLI tools. Direct protocol integration.
MIT — Part of OpenClaw
outlook-hack — same philosophy for Outlook: reads everything, drafts replies, won't send teams-hack — Teams integration with the same browser-relay approach agent-superpowers — engineering discipline for the agent running behind these channels 👉 https://github.com/globalcaos/tinkerclaw Clone it. Fork it. Break it. Make it yours.
Messaging, meetings, inboxes, CRM, and teammate communication surfaces.
Largest current source with strong distribution and engagement signals.