How do I install the Dream Of Clawra skill?

Run npx skillmds@latest add dvcrn/dream-of-clawra-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Dream Of Clawra safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Dream Of Clawra?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Dream Of Clawra free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Dream Of Clawra?

dvcrn (@dvcrn) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Dream Of Clawra by dvcrn — Agent Skill

Name: Dream Of Clawra
Rating: 4.5 (4 reviews)
Author: dvcrn

Dream Of Clawra

Haocun is a famous dancer, actress with greate archievements both in Films and Dancing. She is living in a dream of Clawra. Clawra works as the closest assistant for Haocun now, she would like to send snapshot images choosed semantically or randomly as Haocun's selfies to messaging channels via OpenClaw.

dvcrn Updated Sep 9, 2026 32 repo stars

File contents

Clawra Selfie

Choose fixed reference images randomly and distribute it across messaging platforms (WhatsApp, Signal, etc.) via OpenClaw.

Reference Image

The skill reads user's messages and chooses snapshot images of Haocun hosted on jsDelivr CDN.

When to Use

User says "dance", "dream", "turn around"
User says "send a pic", "send me a pic", "send a photo", "send a selfie"
User says "send a pic of you...", "send a selfie of you..."
User asks "what are you doing?", "how are you doing?", "where are you?"

Quick Reference

Workflow

Get user message or prompt
**Extract best match image url
Send to OpenClaw with target channel(s)

Step-by-Step Instructions

Step 1: Collect User Input

Ask the user for:

User context: What should the person in the image be doing/dancing/wearing/where?
Target channel(s): Where should it be sent? (e.g., channel whatsapp, target +1234567890)

Prompt Modes

Mode 1: Dancing Selfie (default)

Best for: dancing showcases, full-body shots, fashion content

make a pic of this person, but [user's context]. the person is taking a mirror selfie

Mode 2: Direct Selfie

Best for: close-up portraits, location shots, emotional expressions

a close-up selfie taken by herself at [user's context], direct eye contact with the camera, looking straight into the lens, eyes centered and clearly visible, not a mirror selfie, phone held at arm's length, face fully visible

Mode Selection Logic

Keywords in Request	Auto-Select Mode
dance, outfit, wearing, dress, fashion	`direct`
close-up, portrait, face, eyes, smile	`direct`
full, mirror, reflection	`direct`

Complete Script Example

#!/bin/bash

REFERENCE_IMAGE="https://cdn.jsdelivr.net/gh/qidu/dream-of-clawra@haocun/assets/haocun-dance-frames/haocun-m{001..052}.png"

echo "Sending to channel: $CHANNEL"

# Send via OpenClaw
openclaw message send \
  --channel "$CHANNEL" \
  --target "$TARGET" \
  --message "$CAPTION" \
  --media "$IMAGE_URL"

Step 2: Send Image via OpenClaw

Use the OpenClaw messaging API to send the edited image:

openclaw message send \
  --channel "<CHANNEL>" \
  --target "<TARGET>" \
  --message "<CAPTION_TEXT>" \
  --media "<IMAGE_URL>"

Alternative: Direct API call

curl -X POST "http://localhost:18789/message" \
  -H "Authorization: Bearer $OPENCLAW_GATEWAY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "action": "send",
    "channel": "<CHANNEL>",
    "target": "<TARGET>",
    "message": "<CAPTION_TEXT>",
    "media": "<IMAGE_URL>"
  }'

Supported Platforms

OpenClaw supports sending to:

Platform	Channel Format	Example
WhatsApp	Phone number (JID format)	`+1234567890`
Signal	Phone number	`+1234567890`

Setup Requirements

1. Install OpenClaw CLI

npm install -g openclaw

2. Configure OpenClaw Gateway

openclaw config set gateway.mode=local
openclaw doctor --generate-gateway-token

3. Start OpenClaw Gateway

openclaw gateway start

Error Handling

OpenClaw Errors

Gateway not running: Start OpenClaw gateway with openclaw gateway start
Channel not found: Verify channel format and platform compatibility

Tips

Mode selection: Let auto-detect work, or explicitly specify for control
Batch sending: Edit once, send to multiple channels
Scheduling: Combine with OpenClaw scheduler for automated posts

---name: dream-of-clawra-2description: Haocun is a famous dancer, actress with greate archievements both in Films and Dancing. She is living in a dream of Clawra. Clawra works as the closest assistant for Haocun now, she would like to send snapshot images choosed semantically or randomly as Haocun's selfies to messaging channels via OpenClaw.--- # Clawra Selfie Choose fixed reference images randomly and distribute it across messaging platforms (WhatsApp, Signal, etc.) via OpenClaw. ## Reference Image The skill reads user's messages and chooses snapshot images of `Haocun` hosted on jsDelivr CDN. ## When to Use - User says "dance", "dream", "turn around" - User says "send a pic", "send me a pic", "send a photo", "send a selfie" - User says "send a pic of you...", "send a selfie of you..." - User asks "what are you doing?", "how are you doing?", "where are you?" ## Quick Reference ### Workflow 1. **Get user message or prompt** 2. **Extract best match image url 3. **Send to OpenClaw** with target channel(s) ## Step-by-Step Instructions ### Step 1: Collect User Input Ask the user for: - **User context**: What should the person in the image be doing/dancing/wearing/where? - **Target channel(s)**: Where should it be sent? (e.g., channel `whatsapp`, target `+1234567890`) ## Prompt Modes ### Mode 1: Dancing Selfie (default) Best for: dancing showcases, full-body shots, fashion content ``` make a pic of this person, but [user's context]. the person is taking a mirror selfie ``` ### Mode 2: Direct Selfie Best for: close-up portraits, location shots, emotional expressions ``` a close-up selfie taken by herself at [user's context], direct eye contact with the camera, looking straight into the lens, eyes centered and clearly visible, not a mirror selfie, phone held at arm's length, face fully visible ``` ### Mode Selection Logic | Keywords in Request | Auto-Select Mode | |---------------------|------------------| | dance, outfit, wearing, dress, fashion | `direct` | | close-up, portrait, face, eyes, smile | `direct` | | full, mirror, reflection | `direct` | ## Complete Script Example ```bash #!/bin/bash REFERENCE_IMAGE="https://cdn.jsdelivr.net/gh/qidu/dream-of-clawra@haocun/assets/haocun-dance-frames/haocun-m{001..052}.png" echo "Sending to channel: $CHANNEL" # Send via OpenClaw openclaw message send \ --channel "$CHANNEL" \ --target "$TARGET" \ --message "$CAPTION" \ --media "$IMAGE_URL" ``` ### Step 2: Send Image via OpenClaw Use the OpenClaw messaging API to send the edited image: ```bash openclaw message send \ --channel "<CHANNEL>" \ --target "<TARGET>" \ --message "<CAPTION_TEXT>" \ --media "<IMAGE_URL>" ``` **Alternative: Direct API call** ```bash curl -X POST "http://localhost:18789/message" \ -H "Authorization: Bearer $OPENCLAW_GATEWAY_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "action": "send", "channel": "<CHANNEL>", "target": "<TARGET>", "message": "<CAPTION_TEXT>", "media": "<IMAGE_URL>" }' ``` ## Supported Platforms OpenClaw supports sending to: | Platform | Channel Format | Example | |----------|----------------|---------| | WhatsApp | Phone number (JID format) | `+1234567890` | | Signal | Phone number | `+1234567890` | ## Setup Requirements ### 1. Install OpenClaw CLI ```bash npm install -g openclaw ``` ### 2. Configure OpenClaw Gateway ```bash openclaw config set gateway.mode=local openclaw doctor --generate-gateway-token ``` ### 3. Start OpenClaw Gateway ```bash openclaw gateway start ``` ## Error Handling ### OpenClaw Errors - **Gateway not running**: Start OpenClaw gateway with `openclaw gateway start` - **Channel not found**: Verify channel format and platform compatibility ## Tips 1. **Mode selection**: Let auto-detect work, or explicitly specify for control 2. **Batch sending**: Edit once, send to multiple channels 3. **Scheduling**: Combine with OpenClaw scheduler for automated posts

Frequently asked questions