ClawHub

Blind Boxes

v0.1.0

提供关于网红盲盒的推荐清单、打卡路线与指南。用户搜索网红盲盒或规划相关出行时调用。

⭐ 0· 143·0 current·0 all-time
by@mike47512

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for mike47512/blind-boxes.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Blind Boxes" (mike47512/blind-boxes) from ClawHub.
Skill page: https://clawhub.ai/mike47512/blind-boxes
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install blind-boxes

ClawHub CLI

Package manager switcher

npx clawhub@latest install blind-boxes
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name and description (recommend lists, routes, guides for trendy blind-box stores) match the SKILL.md content. There are no unexpected environment variables, binaries, or config paths requested.
✓
Instruction Scope
SKILL.md contains only filters, return fields, examples, update cadence and user-facing notes. It does not instruct reading files, accessing environment variables, or sending data to external endpoints beyond normal agent behavior.
✓
Install Mechanism
No install spec and no code files — this is instruction-only. Nothing is written to disk or fetched at install time.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths; the requested scope is minimal and appropriate for a recommendation guide.
✓
Persistence & Privilege
always is false (not force-included). disable-model-invocation is false (agent can invoke autonomously), which is the platform default and reasonable for a user-invocable recommendation skill.
Assessment
This skill appears coherent and low-risk: it only contains prose for producing recommendations and asks for no secrets. Before installing, consider: (1) the source is unknown and there's no homepage—if provenance matters to you, prefer skills from identifiable authors; (2) the agent may request or use your location or trip details when you ask for personalized recommendations—avoid sharing sensitive personal data or payment info through the skill; (3) autonomous invocation is allowed by default, so monitor outputs and disable the skill if it behaves unexpectedly. If you need bookings or payments, handle those directly with the vendor rather than via the skill.

Like a lobster shell, security has layers — review code before you run it.

latestvk971xswwz8qh7gcy9jkfts5xcx8367ma
143downloads
0stars
1versions
Updated 1mo ago
v0.1.0
MIT-0
@mike47512
latest
Download

网红盲盒

筛选项

  • 风格偏好（国潮/复古/二次元/汉服等）
  • 价格区间/正品保障/是否限量发售
  • 服务（改造/试妆/预约）/拍摄友好度

返回字段

  • 店铺/项目名称/亮点/价格/评分/人流
  • 地址/营业时间/预约方式/拍摄与试穿规则
  • 活动/快闪/联名信息/社交平台热度

示例请求

  • “广州 网红盲盒 国潮清单（学生友好）”
  • “成都 网红盲盒 小众手作TOP30（可定制）”

更新频率

  • 每周迭代，结合新热度与口碑反馈

注意事项

  • 高峰期排队较久，建议提前预约或错峰
  • 部分项目有拍摄限制或最低消费，按现场规则执行

Comments

Loading comments...