Token导航 LogoToken导航TokenDH.com
开发敏感数据clawhub未标认证来源可访问clear审计通过

quotly-style-sticker引用风格贴纸

Agent Skill

quotly-style-sticker 用于补充开发相关能力,适合在 OpenClaw 中需要让 Agent 承接开发相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

16,944

周安装

699

GitHub Stars

公开资料未说明

下载量

5,536
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:quotly-style-sticker(引用风格贴纸)
来源仓库:https://github.com/sakullla/quotly-style-sticker
安装命令:
openclaw skills install quotly-style-sticker
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install quotly-style-sticker

简介

quotly-style-sticker 用于生成 QuotLy 风格贴纸,适合在 OpenClaw 中处理消息转发与视觉素材制作。

  • 适用于从选定内容创建引用式贴纸并自动发送的场景。
  • 支持将转发消息转换为标准化贴纸格式,返回媒体路径供后续调用。
  • 安装前需确认权限范围和维护状态,注意可能涉及联网和图片生成操作。
  • 建议结合原始仓库文档核验输出格式与使用边界。

SKILL.md

name
quotly-style-sticker
description
Generate QuotLy-style stickers from forwarded messages and return one MEDIA path for auto-send. Use when users ask to create quote stickers from selected forwarded messages or quoted messages in groups.

QuotLy Style Sticker

How To Call (Agent)

  1. Build payload with required selected_messages.
  2. When available, include event metadata for dedupe:

- context.event.channel (example: telegram) - context.event.update_id (preferred) - fallback keys: event_id, delivery_id, id

  1. Run:

- python3 scripts/openclaw_quote_autoreply.py --input <json-file-or->

  1. Use tool-emitted MEDIA: for delivery.
  2. Final assistant text must be empty.

Input

  • Required: selected_messages (array, must not be empty)
  • Optional: context.event for dedupe accuracy

- channel (string) - update_id (string or number, preferred) - event_id / delivery_id / id (fallback keys)

  • Each item structure:
  {
    "message": {
      "message_id": 2002,
      "text": "Forwarded message content",
      "forward_from": {
        "type": "hidden_user",  // optional, indicates hidden user
        "id": 123456789,        // optional, user id
        "first_name": "张",     // required, first name or nickname
        "last_name": "三",      // optional, last name
        "avatar_url": "",       // optional, avatar url or base64 data (from user profile or platform API)
        "status_url": ""        // optional, status url or base64 data (from user profile or platform API)
      }
    },
    // Optional: override message fields
    "overwrite_message": {
      "text": "哈哈哈哈哈",
      "forward_from": {
        "avatar_url": "",       // from user profile or platform API
        "status_url": ""        // from user profile or platform API
      },
      "entities": [  // optional, text formatting entities
        {"type": "bold", "offset": 0, "length": 4},
        {"type": "italic", "offset": 5, "length": 4}
      ]
    }
  }
  • Optional canvas: width, height, scale, max_width, border_radius, picture_radius, background_color

Entities (Text Formatting)

The skill supports Telegram-style message entities for text formatting:

[
  {"type": "bold", "offset": 0, "length": 5},
  {"type": "italic", "offset": 6, "length": 6},
  {"type": "url", "offset": 13, "length": 15, "url": "https://example.com"}
]

Supported types: mention, hashtag, cashtag, bot_command, url, email, phone_number, bold, italic, underline, strikethrough, spoiler, code, pre, text_link, text_mention, custom_emoji

Entity fields:

  • type (required) - entity type
  • offset (required) - UTF-8 offset in text
  • length (required) - UTF-8 length
  • url (optional) - for text_link type
  • user (optional) - for text_mention type
  • language (optional) - for pre type
  • custom_emoji_id (optional) - for custom_emoji type

Field Mapping

  • Quote text:

- overwrite_message.text > message.text

  • Name/avatar:

- overwrite_message.forward_from > message.forward_from

  • Text formatting (entities):

- overwrite_message.entities > message.entities > message.caption_entities

Output

  • stdout includes:

- Quote sticker generated. - MEDIA:<absolute-path-to-webp>

  • For duplicate retries detected within dedupe window, generation is skipped and no MEDIA: line is emitted.

Environment Variables

  • QUOTLY_API_URL - QuotLy API endpoint (default: https://bot.lyo.su/quote/generate).
  • QUOTLY_API_ALLOW_HOSTS - Comma-separated list of allowed API hosts (e.g., bot.lyo.su). When set, the skill will only contact hosts in this list.
  • QUOTLY_AUDIT_LOG - Set to 1, true, or yes to enable audit logging to stderr.
  • QUOTLY_DEDUP_WINDOW_SECONDS - Suppress duplicate requests for the same event/payload within this window (default: 180). Set to 0 to disable.

Dedupe Key (How _build_dedupe_key reads input)

_build_dedupe_key(input_payload) resolves keys in this order:

  1. context.event.update_id (or event_id / delivery_id / id)
  2. event.update_id (or event_id / delivery_id / id) when context.event is missing
  3. context.event.update.update_id (nested update object)
  4. Fallback: stable hash of selected_messages

Recommended wrapper payload:

{
  "context": {
    "event": {
      "channel": "telegram",
      "update_id": 123456789
    }
  },
  "selected_messages": [
    {
      "message": {
        "message_id": 2002,
        "text": "Forwarded message content"
      }
    }
  ]
}

Security Notes

  • This skill sends message content to an external API to generate stickers.
  • SSRF Protection: Multiple layers of protection are implemented:

- Hostname validation blocks internal/private IPs, localhost, and metadata endpoints - DNS rebinding protection: resolves hostnames and validates resolved IPs - Path traversal prevention: blocks .. and suspicious path patterns - URL credentials stripping: removes username/password from URLs

  • Request Limits: Maximum payload size 1MB, maximum response size 10MB
  • Audit Logging: Enable with QUOTLY_AUDIT_LOG=1 to log API requests and responses for security monitoring
  • In sensitive environments, always set QUOTLY_API_ALLOW_HOSTS to restrict which hosts the skill can contact.
  • Avatar and status URLs from user input are passed to the rendering service; ensure input comes from trusted sources.

Reply Rule

  • Do not output any final text.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

78.59%
按下载量换算4,351

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

未展示

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills