← Back to Skills Marketplace
hubertsing

柯南周报

by HubertSing · GitHub ↗ · v1.0.2 · MIT-0
cross-platform ✓ Security Clean
333
Downloads
0
Stars
1
Active Installs
2
Versions
Install in OpenClaw
/install conan-weekly-report
Description
名侦探柯南动画周报技能。每周自动收集并整理柯南最新剧情进展，包括主线剧情、特别篇、角色动态等。使用 DuckDuckGo HTML 搜索获取真实网页数据。
README (SKILL.md)

柯南周报 📺🔍

名侦探柯南动画周报技能 - 每周自动收集并整理柯南最新剧情进展

🎯 功能特点

  • 自动搜索 - 每周六晚 9 点自动搜索最新剧情
  • 主线追踪 - 关注黑衣组织、APTX-4869 等主线剧情
  • 特别篇报道 - 剧场版、特别篇、联动剧集信息
  • 角色动态 - 声优变动、角色登场、制作信息
  • 多源整理 - 整合知乎、百科、官方等多渠道信息

⏰ 默认执行时间

  • 每周六 21:00 (Asia/Shanghai UTC+8)
  • 可通过 cron 配置修改

📋 输出内容

每期周报包含：

  1. 新播出集数 - 集数、标题、播出日期
  2. 重大剧情进展 - 主线剧情推进
  3. 特别篇信息 - 剧场版、特别篇、联动
  4. 角色/声优动态 - 登场角色、声优变动
  5. 制作信息 - 编剧、导演、制作团队
  6. 来源链接 - 方便查看详情

🚀 使用方法

手动触发

柯南周报

自动执行（推荐）

# 添加定时任务（每周六 21:00）
openclaw cron add \
  --name "柯南周报" \
  --cron "0 21 * * 6" \
  --tz "Asia/Shanghai" \
  --system-event "柯南周报" \
  --session "main"

查看已安装

openclaw skills list | grep conan

🔍 搜索源

技能使用 DuckDuckGo HTML 搜索接口 进行资讯收集：

  • 无需 API 密钥 - 直接使用公开 HTML 接口
  • 真实 HTTP 请求 - 使用 Node.js https 模块发起实际网络请求
  • 结果解析 - 正则表达式提取标题和链接
  • 请求限流 - 内置 1.5 秒延迟避免请求过快
  • 超时保护 - 10 秒超时防止卡死

搜索结果可能来自以下渠道（取决于搜索查询）：

  • 百度百科、维基百科 - 集数列表和剧情简介
  • 哔哩哔哩 - 播出信息和预告
  • 新浪微博 - 声优和制作动态
  • 动漫资讯站 - 新番放送表

📝 示例输出

📺 柯南周报 | 2026 年第 10 周

【新播出】
• 第 1245 集 - 《东京晴空塔之谜（前篇）》
• 第 1246 集 - 《东京晴空塔之谜（后篇）》

【主线进展】
• 黑衣组织成员"朗姆"身份进一步揭露
• 灰原哀发现 APTX-4869 新线索

【特别篇】
• 2 小时特别篇《30 号杀人事件》3 月播出

【声优动态】
• 毛利兰声优山崎和佳奈恢复活动

详情链接：[知乎](...) [百科](...)

⚙️ 配置选项

修改执行时间

编辑 cron 任务：

openclaw cron edit \x3C任务 ID> --cron "0 20 * * 6"

修改时区

openclaw cron edit \x3C任务 ID> --tz "Asia/Tokyo"

暂停/恢复

openclaw cron disable \x3C任务 ID>  # 暂停
openclaw cron enable \x3C任务 ID>   # 恢复

📦 安装

从 ClawHub 安装

clawhub install conan-weekly-report

手动安装

# 克隆到本地 skills 目录
git clone https://github.com/你的用户名/conan-weekly-report.git \
  ~/.openclaw/workspace/skills/conan-weekly-report

# 重启 OpenClaw
openclaw gateway restart

🎯 使用场景

场景 说明
柯南粉丝 每周自动接收最新剧情
补番党 快速了解近期进展
主线追踪 不错过黑衣组织剧情
资讯整理 自动收集多渠道信息

📌 注意事项

  1. 网络依赖 - 需要联网搜索最新信息
  2. 搜索限制 - 部分网站可能有反爬限制
  3. 时区设置 - 确保 cron 时区正确
  4. 推送渠道 - 需配置 QQ/Telegram 等推送

🔄 更新日志

v1.0.2 (2026-03-15)

  • 🔧 修复 ClawHub 审核问题 - 确保代码与描述一致
  • ✅ 完善网络请求实现（真实 HTTP 请求 + 超时保护）
  • ✅ 改进搜索结果解析逻辑（DuckDuckGo HTML 接口）
  • ✅ 添加请求限流（1.5 秒延迟）避免被封禁
  • ✅ 更新 package.json 依赖和元数据
  • 📝 完善 README.md 和 SKILL.md 文档

v1.0.1 (2026-03-10)

  • 🔧 修复安全检测问题 - 完善网络请求实现
  • ✅ 添加真实 HTTP 搜索功能（DuckDuckGo）
  • ✅ 支持 Webhook 推送报告
  • ✅ 自动保存报告到本地文件
  • 📦 更新 package.json 元数据

v1.0.0 (2026-03-08)

  • ✨ 初始版本发布
  • ✅ 支持自动搜索和整理
  • ✅ 支持定时任务
  • ✅ 多源信息整合

📞 反馈与建议

  • GitHub Issues: 提交问题
  • 作者：拓海
  • 版本：1.0.0

📄 许可证

MIT License

名侦探柯南 © 青山刚昌/小学馆·读卖电视台·TMS 本技能仅供学习交流，请勿用于商业用途

Usage Guidance
What this skill will do if installed: it will perform outbound HTTP(S) requests (DuckDuckGo HTML) to gather public web results, compile and save a Markdown report under the skill's reports/ folder, and — only if you set REPORT_WEBHOOK_URL — POST the report to that webhook. Before installing, consider: 1) Only set REPORT_WEBHOOK_URL to endpoints you control/trust (don't point it to third-party services that could receive your data). 2) The skill requires network access to function; run it in an environment where outgoing requests are acceptable. 3) The source is listed as unknown; if you need stronger assurance, review the index.js locally or run in a sandboxed container. 4) The package lists an unused dependency (node-fetch) — low risk but cosmetic. If you want stricter safety, run the script manually first and verify the reports produced and any webhook traffic before enabling automated cron execution.
Capability Analysis
Type: OpenClaw Skill Name: conan-weekly-report Version: 1.0.2 The skill is a legitimate tool for generating weekly reports on the 'Detective Conan' anime. It uses standard Node.js 'https' and 'fs' modules to perform searches via DuckDuckGo's HTML interface and save results locally in a 'reports' directory. The code is transparent, lacks obfuscation, and only accesses the network for its stated purpose or an optional user-configured webhook (REPORT_WEBHOOK_URL) found in index.js.
Capability Assessment
✓ Purpose & Capability
Name/description (柯南周报) match the implementation: index.js searches DuckDuckGo HTML, parses results, compiles a Markdown report and saves it to a reports/ directory. Declared capabilities (weekly automated search, multi-source aggregation) align with the code's queries and parsing logic.
ℹ Instruction Scope
SKILL.md instructs using openclaw cron for scheduling and describes optional push configuration. The runtime instructions and index.js are limited to making outbound HTTP(S) requests to public search pages, parsing HTML, saving local files, and optionally POSTing to a webhook supplied via REPORT_WEBHOOK_URL. Minor mismatch: docs mention QQ/Telegram push channels generically but the code only implements a generic webhook POST (REPORT_WEBHOOK_URL); no other unexpected file reads, credential reads, or external endpoints are present.
✓ Install Mechanism
No install spec (instruction-only) reduces installation risk. The package includes package.json and package-lock.json but no download-from-arbitrary-URL behavior. One small note: package.json lists node-fetch as a dependency but index.js uses built-in https/http — presence of an unused dependency is not harmful but unnecessary.
✓ Credentials
No required env vars are declared; only an optional REPORT_WEBHOOK_URL is read if provided (used to POST the generated report). No credentials or unrelated environment variables are requested or accessed by the code.
✓ Persistence & Privilege
Skill is not always-enabled and does not request elevated/system-wide privileges. It writes reports to its own reports/ directory under the skill folder and does not modify other skills or system configuration. Autonomous invocation default is unchanged but not combined with other red flags.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install conan-weekly-report
  3. After installation, invoke the skill by name or use /conan-weekly-report
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
修复 ClawHub 审核问题 - 完善网络请求实现和文档
v1.0.0
conan-weekly-report v1.0.0 - 初始版本上线，自动收集并整理名侦探柯南动画每周最新剧情进展 - 支持主线剧情追踪、特别篇报道、角色动态、制作信息等内容 - 集成多渠道信息源，包括知乎、百科、官方等 - 提供每周六 21:00 自动定时推送与手动触发两种用法 - 提供灵活的 cron 配置与推送渠道适配
Metadata
Slug conan-weekly-report
Version 1.0.2
License MIT-0
All-time Installs 2
Active Installs 1
Total Versions 2
Frequently Asked Questions

What is 柯南周报?

名侦探柯南动画周报技能。每周自动收集并整理柯南最新剧情进展，包括主线剧情、特别篇、角色动态等。使用 DuckDuckGo HTML 搜索获取真实网页数据。 It is an AI Agent Skill for Claude Code / OpenClaw, with 333 downloads so far.

How do I install 柯南周报?

Run "/install conan-weekly-report" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is 柯南周报 free?

Yes, 柯南周报 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does 柯南周报 support?

柯南周报 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created 柯南周报?

It is built and maintained by HubertSing (@hubertsing); the current version is v1.0.2.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 Comments