← Back to Skills Marketplace
gui-gitai

BLX Lobster Sticker

by Gui-GitAi · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ Security Clean
96
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install blx-lobster-sticker
Description
OpenClaw专属小龙虾🦞(crayfish)主题表情包技能。由白灵汐(BLX)创作。生成统一风格的卡通小龙虾LINE贴纸表情包,共38种情绪表情和2种物品表情,适用于对话机器人、客服AI、聊天助手等场景。当用户表达各种情绪(开心、难过、生气、惊讶、感动、尴尬、爱意、酷帅、困倦、害羞、得意、疑惑、惊恐、无语、...
README (SKILL.md)

blx-lobster-sticker 小龙虾表情包

基于统一风格的卡通小龙虾(crayfish)LINE贴纸表情包。

情绪映射表

文件名 情绪 触发关键词
001_happy.png 开心 开心、高兴、快乐、太棒了、太好了
002_sad.png 难过 难过、伤心、哭、失落、沮丧
003_angry.png 生气 生气、愤怒、气死了、烦死了
004_surprised.png 惊讶 哇、震惊、惊讶、意外、不会吧
005_smug.png 得意 得意、骄傲、太牛了、牛人
006_shy.png 害羞 害羞、脸红、不好意思、捂脸
007_embarrassed.png 尴尬 尴尬、不好意思、囧、丢人
008_sleepy.png 困倦 困、累了、想睡觉、睡了
009_touched.png 感动 感动、暖心、谢谢、太贴心了
010_love.png 爱意 爱、喜欢、么么哒、心动
011_cool.png 酷帅 酷、帅、牛、厉害、牛逼
012_confused.png 疑惑 困惑、疑问、什么鬼、为啥
013_scared.png 惊恐 惊恐、害怕、吓人、发抖
014_speechless.png 无语 无语、无话可说、晕
015_evil.png 奸笑 奸笑、阴险、坏笑、腹黑
016_mischief.png 调皮 调皮、犯贱、恶作剧
017_social.png 社会 社会、社会人、老炮儿
018_melon.png 吃瓜 吃瓜、看戏、围观
019_grin.png 傻笑 傻笑、逗死了、笑死
020_rage.png 暴怒 暴怒、气炸、火了
021_dismissive.png 撇嘴 撇嘴、不屑、切
022_smile.png 微笑 微笑、淡淡笑
023_blank.png 呆住 呆住、发呆、懵
024_crazy.png 抓狂 抓狂、发疯、要死了
025_sneer.png 偷笑 偷笑、窃笑
026_eyeroll.png 白眼 白眼、翻白眼
027_silly_smile.png 憨笑 憨笑、傻笑
028_relaxed.png 悠闲 悠闲、惬意、真舒服
029_sigh.png 叹气 叹气、叹息、唉
030_goodbye.png 再见 再见、拜拜
031_crying.png 流泪 流泪、哭死了、心碎
032_bashful.png 害羞 害羞捂脸、不好意思见人
033_passionate.png 发怒 发怒、怒火中烧
034_naughty.png 调皮 调皮、犯贱
035_yay.png 耶、欢呼、胜利
036_cheer.png 加油 加油、最棒、你最厉害
037_ok.png OK OK、好的、行
038_fist.png 拳头 拳头、握拳

物品表情

文件名 物品 触发场景
P01_heart.png 爱心 表达爱意时
P02_broken_heart.png 心碎 伤心时

使用方式

当用户请求表情包时,使用 image 工具读取对应图片发送给用户。

微信(WeChat)环境:使用 assets_wx/ 目录下的 JPG 文件(文件更小,微信兼容性更好) 其他环境:使用 assets/ 目录下的 PNG 文件

触发方式

当用户表达各种情绪(开心、难过、生气、惊讶、感动、尴尬、爱意、酷帅、困倦、害羞、得意、疑惑、惊恐、无语、奸笑、调侃、社会、吃瓜、发怒、撇嘴、微笑、呆住、抓狂、偷笑、白眼、憨笑、悠闲、叹气、再见、加油、耶、OK、拳头、拥抱等)时,自动发送对应的小龙虾表情包图片。

示例:

用户说:"加油你最棒!"
→ 情绪:加油/鼓励
→ 微信:发送 assets_wx/036_cheer.jpg

图片路径

环境 路径 格式 大小
微信 skills/blx-lobster-sticker/assets_wx/[文件名].jpg JPG ~30KB
其他 skills/blx-lobster-sticker/assets/[文件名].png PNG ~245KB

注意事项

  • 每次只发送一张最匹配的情绪图片
  • 如果无法判断情绪,可以不发送
  • 微信环境必须使用 assets_wx/ 目录的 JPG 图片(PNG 在微信可能显示为灰色方块)
  • 风格:可爱卡通小龙虾,LINE贴纸风格,厚白色边框,统一色调
  • 角色特征:红色外壳、大眼睛、粉色腮红、白色厚边框
Usage Guidance
This skill appears coherent and low-risk: it only serves local sticker images based on detected emotion keywords and requests no credentials or installs. Before installing, verify that the actual image assets exist at the stated paths (skills/blx-lobster-sticker/assets and assets_wx) and match your expected count/filenames; confirm you have rights to use the artwork (artist attribution/licensing); and, if you don't want automatic image replies, be aware the skill can be invoked autonomously by the agent — consider limiting its use or testing in a safe environment first.
Capability Analysis
Type: OpenClaw Skill Name: blx-lobster-sticker Version: 1.0.1 The skill bundle is a legitimate sticker pack for an AI agent, mapping user emotions to specific crayfish-themed image assets. It contains only metadata, instructions (SKILL.md), and specifications (SPEC.md) that direct the agent to use a local 'image' tool to display files from the assets directory; there is no evidence of network exfiltration, malicious code execution, or harmful prompt injection.
Capability Assessment
Purpose & Capability
Name and description match the runtime instructions: the skill maps user emotion keywords to local lobster sticker images and returns them. Minor inconsistency: some SPEC files claim '100+' or slightly different enumerations of stickers while the SKILL.md mapping lists ~38 emotion images + 2 item images — this is likely a documentation/version mismatch rather than a security problem. Source/homepage is absent, so if provenance matters verify the artist/owner separately.
Instruction Scope
SKILL.md only instructs the agent to use the 'image' tool to read local files under skills/blx-lobster-sticker/assets or assets_wx and send one matching image; it does not instruct reading unrelated files, contacting external endpoints, or accessing environment variables. The only autonomy-related behavior is '自动发送' when an emotion is detected, which is consistent with the stated purpose.
Install Mechanism
No install spec and no code files are present (instruction-only). That minimizes disk writes and external downloads.
Credentials
The skill declares no required environment variables, credentials, or config paths; nothing disproportionate is requested for a local sticker-sending skill.
Persistence & Privilege
always is false and the skill does not request persistent system-wide privileges or modification of other skills. It can be invoked autonomously by the agent (platform default) which is appropriate for an auto-responding sticker skill.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install blx-lobster-sticker
  3. After installation, invoke the skill by name or use /blx-lobster-sticker
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
修复微信表情包灰色方块问题:微信环境使用 assets_wx 目录的 JPG 图片
Metadata
Slug blx-lobster-sticker
Version 1.0.1
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is BLX Lobster Sticker?

OpenClaw专属小龙虾🦞(crayfish)主题表情包技能。由白灵汐(BLX)创作。生成统一风格的卡通小龙虾LINE贴纸表情包,共38种情绪表情和2种物品表情,适用于对话机器人、客服AI、聊天助手等场景。当用户表达各种情绪(开心、难过、生气、惊讶、感动、尴尬、爱意、酷帅、困倦、害羞、得意、疑惑、惊恐、无语、... It is an AI Agent Skill for Claude Code / OpenClaw, with 96 downloads so far.

How do I install BLX Lobster Sticker?

Run "/install blx-lobster-sticker" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is BLX Lobster Sticker free?

Yes, BLX Lobster Sticker is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does BLX Lobster Sticker support?

BLX Lobster Sticker is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created BLX Lobster Sticker?

It is built and maintained by Gui-GitAi (@gui-gitai); the current version is v1.0.1.

💬 Comments