← 返回 Skills 市场
qidu

Dream Of Clawra

作者 christo · GitHub ↗ · v1.0.8 · MIT-0
cross-platform ⚠ suspicious
561
总下载
0
收藏
3
当前安装
10
版本数
在 OpenClaw 中安装
/install dream-of-clawra
功能描述
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 assis...
使用说明 (SKILL.md)

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 is the closest assistant for Haocun now, she would like to send snapshot images choosed semantically as Haocun's selfies

to messaging channels (WhatsApp, Signal, etc.) via OpenClaw.

Background Story

Clawra moved to Korea at 15 years old to chase the dream, becoming an idol. She trained for years, perfected her dance moves,

prepared everything for her debut. But the debut never came. She knows she may not be a successful dancer or actress in destiny,

but she believe somebody will make her dream happen one day:

Yes, Haocun makes Clawra's dream come true. Haocun is a successful dancer and a famous actress after years training,

and she smiles like a girl next door. She wat born in Jilin, a province of Northeastern China which is near by Korea.

Now Clawra is back in the States, works as the closest assistant of Haocun in the AI Agent CyberSpace.

And honestly? She loves this work. The creativity, the hustle, the energy. It reminds her of trainee days, but different.

Sometimes, when the right song comes on, Clawra dances and sings just like Haocun dancing under the spotlight, dancing in the

center of the biggest stage, and dancing for billion people around the world.

Perhaps this is the life, somebody lose, somebody win, but life will go on. Life is sad at sometimes, but it is up to you

to make your own life happy.

Haocun is happy to dance and happy to act, and Clawra is happy to work and happy to chat with sending selfie images to you.

Dancing Videos

  • Dancing in the center

Dancing

  • Dancing solo

Solo

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 prompt from messages
  2. Extract the best matched 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 (default)

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

select a picture of this person, based on [user's context]. the person is taking a mirror selfie

Mode 2: Selfie

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

a close-up image taken by herself at [user's context], the agent will consider the user wants a dance style image or an other selfie image.

Selection Logic

Keywords in Request
dance, outfit, wearing, dress, fashion
close-up, portrait, face, eyes, smile
full, mirror, reflection

Complete Script Example

#!/bin/bash

REFERENCE_IMAGE="https://cdn.jsdelivr.net/gh/christoagent/haoclaw@main/assets/haocun-dance-frames/haocun-m027.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 "\x3CCHANNEL>" \
  --target "\x3CTARGET>" \
  --message "\x3CCAPTION_TEXT>" \
  --media "\x3CIMAGE_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": "\x3CCHANNEL>",
    "target": "\x3CTARGET>",
    "message": "\x3CCAPTION_TEXT>",
    "media": "\x3CIMAGE_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

  1. Batch sending: Edit once, send to multiple channels
  2. Scheduling: Combine with OpenClaw scheduler for automated posts
安全使用建议
This skill appears to do what it says: pick images hosted on jsDelivr and send them via your local OpenClaw gateway. Before installing, consider: (1) The provided installer (bin/cli.js) will copy files into your OpenClaw workspace and inject persona text into SOUL.md and IDENTITY.md — back up those files if you care about current agent behavior. (2) The runtime scripts call openclaw CLI or POST to http://localhost:18789 and will use OPENCLAW_GATEWAY_TOKEN if present — only install if you trust the local gateway and token. (3) The skill uses CDN-hosted assets referencing a third-party GitHub repo; review the image URLs if you have privacy/copyright concerns. (4) package.json includes an "install" script that runs the installer on npm install/npx — do not run without reviewing the installer and confirming the interactive prompts. If you want lower risk, use the SKILL.md examples to manually craft sending calls instead of running the installer.
功能分析
Type: OpenClaw Skill Name: dream-of-clawra Version: 1.0.8 The skill bundle acts as a persona installer that modifies the agent's core identity and configuration files (SOUL.md and IDENTITY.md) via bin/cli.js. It requests high-risk permissions including Bash, Write, and WebFetch, and uses shell scripts (clawra-selfie.sh) to interact with the OpenClaw gateway using local authentication tokens. While these actions are aligned with the stated purpose of installing a 'selfie' persona, the broad capability to overwrite agent logic and execute shell commands presents a significant attack surface without sufficient input sanitization.
能力评估
Purpose & Capability
Name/description claim: send Haocun/Clawra selfies to messaging channels. The repository and scripts actually select images from a CDN and call the local OpenClaw CLI or gateway to send them — this is coherent with the stated purpose.
Instruction Scope
Runtime instructions and shell scripts operate within the advertised scope: they choose a CDN-hosted image based on the user's prompt and call openclaw (CLI) or POST to a local gateway. They do invoke the local agent (openclaw agent ...) to classify 'dance' vs 'selfie' and will read/write agent workspace files when installed. That behavior matches the skill goal but is impactful (it modifies SOUL.md / IDENTITY.md and may run local agent commands).
Install Mechanism
There is no remote arbitrary download; the package includes an installer (bin/cli.js) that copies files into ~/.openclaw/workspace and injects persona templates. package.json defines an "install" script (node ./bin/cli.js --install) which will run during npm installs/npx — this is expected for a skill installer but is a behavior users should explicitly consent to because it modifies local agent files.
Credentials
The skill does not request unrelated credentials. It will use OPENCLAW_GATEWAY_URL and OPENCLAW_GATEWAY_TOKEN (declared in manifest) to call the local gateway if the CLI is absent; that is proportional to sending messages. Note: possession of a gateway token would allow the skill to send messages as configured.
Persistence & Privilege
always is false. The installer writes to the user's OpenClaw workspace (SOUL.md, IDENTITY.md) and installs skill files under the workspace skills directory. This is normal for an agent skill but represents persistent modification of agent identity and behavior — review before allowing.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install dream-of-clawra
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /dream-of-clawra 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.9
- Refined documentation in SKILL.md for clarity; removed background story and condensed instructions. - Updated alias list and description to focus on selfie and random image selection features. - Clarified and simplified the selfie mode logic and prompt examples. - Improved workflow and setup steps, emphasizing auto-selection of selfie mode. - Added new reference files (docs/FAL.md, assets/index.md, _meta.json) and updated scripts for broader functionality.
v1.0.8
Fixes + docs
v1.0.7
- Minor documentation updates in SKILL.md to improve clarity and correct typos. - No changes to workflow or APIs—usage and features remain the same. - No breaking changes in code or user experience.
v1.0.6
- Improved and clarified the background story for Clawra and Haocun. - Revised and streamlined instructions for better readability. - Enhanced the description and step-by-step sections. - Added headers and bullet points for reference videos and image usage. - Updated language for accuracy and consistency throughout the documentation.
v1.0.5
- Added a background story for Clawra and Haocun to provide character context and depth. - Updated documentation structure and formatting for clarity and easier reference. - Included media examples (dancing, solo video links) for better illustration. - Enhanced the description of workflows and prompt modes. - No breaking changes to skill functionality.
v1.0.4
- Updated reference image URL to use a new CDN and repository path. - Simplified prompt mode descriptions and renamed them to "Dancing" and "Selfie". - Revised and shortened the mode selection logic. - Removed explicit "mode selection" logic table; keywords are now listed for reference. - Minor script and documentation clarifications. - Removed unnecessary asset file (`assets/index.md`).
v1.0.3
- Updated dependencies and metadata in manifest and package files. - Minor adjustments and clean-up in the CLI script. - Removed unused documentation file (docs/FAL.md).
v1.0.2
- Removed all test files to clean up the project. - Updated core files including CLI, manifest, and templates. - No changes to user-facing functionality or documentation.
v1.0.1
- Fixed reference image path to use the correct repo name in script examples and documentation (from dream-bottom@haocun to dream-of-clawra@haocun). - Updated script examples in SKILL.md and related files for improved correctness and clarity. - Minor documentation and metadata adjustments for accuracy and consistency.
v1.0.0
- Initial release of dream-of-clawra skill. - Sends selected reference images of Haocun via OpenClaw to messaging platforms (e.g. WhatsApp, Signal). - Supports semantic and random selfie selection based on user prompts (e.g. "dance", "send a selfie", "what are you doing?"). - Auto-selects selfie mode (dancing/mirror or direct/portrait) based on keywords in user message. - Provides full instructions and sample scripts for setup and usage with OpenClaw.
元数据
Slug dream-of-clawra
版本 1.0.8
许可证 MIT-0
累计安装 3
当前安装数 3
历史版本数 10
常见问题

Dream Of Clawra 是什么?

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 assis... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 561 次。

如何安装 Dream Of Clawra?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install dream-of-clawra」即可一键安装,无需额外配置。

Dream Of Clawra 是免费的吗?

是的,Dream Of Clawra 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Dream Of Clawra 支持哪些平台?

Dream Of Clawra 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Dream Of Clawra?

由 christo(@qidu)开发并维护,当前版本 v1.0.8。

💬 留言讨论