← 返回 Skills 市场
87
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install telegram-geeknews
功能描述
매일 GeekNews(news.hada.io)에서 오늘의 HOT 이슈 5개를 큐레이션하고, 오픈소스 출시·GitHub star 급상승 프로젝트를 우선 선정하여 텔레그램으로 전송하는 데일리 브리프 에이전트 스킬. 사용자가 "긱뉴스 요약", "오늘 개발 뉴스", "OSS 뉴스", "텔...
安全使用建议
Things to consider before installing or running this skill:
- Required credentials are not declared in the registry metadata. The runtime needs TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID (mandatory) and the run script requires ANTHROPIC_API_KEY (it will exit if missing). It also recommends GITHUB_TOKEN to avoid rate limits. Don't run the cron script unless you intend the pipeline to call Anthropic.
- Implementation mismatch: SKILL.md describes scraping/RSS fallback, but the provided automation delegates to Anthropic's API (claude) with a web_search tool. If you prefer local scraping (so content never leaves your host), you'll need to implement that yourself or modify run_geeknews_brief.sh. Running as-is will transmit prompts and rely on Anthropic; evaluate whether that data flow (site URLs and prompt content) is acceptable.
- Network endpoints used: api.anthropic.com (if ANTHROPIC_API_KEY set) and api.telegram.org. The Telegram bot token must be protected; any compromise of that token would allow message sends as your bot. Keep tokens in a secure place and avoid committing them to repo.
- Review message contents: the script sends the full generated markdown via send_telegram.py. Ensure no sensitive information is included in the generated brief or prompt context (the prompt instructs the model to "check the main page" — the model/tool may retrieve and process site content).
- Actionable steps: ask the publisher to update registry metadata to list required env vars; if you don't trust remote LLM calls, modify the pipeline to perform local RSS parsing/scraping and GitHub queries yourself; store tokens in a secure secret store; test send_telegram.py manually with a test bot/chat before enabling cron.
Overall, the skill is not evidently malicious but has clear inconsistencies and a surprising dependency on an external LLM for the automated pipeline — treat it cautiously and correct the manifest and/or implementation before enabling automated runs.
功能分析
Type: OpenClaw Skill
Name: telegram-geeknews
Version: 1.0.0
The skill is a legitimate utility designed to curate tech news from GeekNews and send daily summaries to a Telegram channel. It uses the Anthropic API for content summarization and the Telegram Bot API for delivery, requiring standard environment variables (TELEGRAM_BOT_TOKEN, ANTHROPIC_API_KEY) for operation. The code in scripts/run_geeknews_brief.sh and scripts/send_telegram.py is transparent, well-documented, and strictly follows the logic described in SKILL.md without any evidence of data exfiltration, obfuscation, or malicious intent.
能力评估
Purpose & Capability
The declared purpose (curate GeekNews and send Telegram briefs) matches the provided code (send_telegram.py, run_geeknews_brief.sh) and references. However the registry metadata claims no required environment variables, while the SKILL.md and scripts clearly require TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID and the cron script requires ANTHROPIC_API_KEY (and optionally GITHUB_TOKEN). The missing env var declarations in metadata are a mismatch and reduce transparency.
Instruction Scope
SKILL.md describes collecting data via RSS and web scraping (with clear fallback rules). The actual run_geeknews_brief.sh script, however, does not implement scraping or RSS parsing — it delegates to the Anthropic API (claude) when ANTHROPIC_API_KEY is present and otherwise exits with an instruction to implement scraping manually. That is an instruction/implementation mismatch: the user-facing doc promises local collection options but the shipped automation relies on an external LLM/web_search tool. The agent will also send the high-level prompt to Anthropic which requests checking the main page; this causes remote network access to news.hada.io via the model/tool and may transmit contextual data to the external LLM provider.
Install Mechanism
No install script or remote download is present; the skill is instruction-first with two small scripts and a reference doc. This is low-risk from an install mechanism perspective because nothing arbitrary is fetched or extracted at install time.
Credentials
The skill requires TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID to function and the cron script requires ANTHROPIC_API_KEY to run the pipeline — but the declared registry metadata lists no required env vars. The script also recommends GITHUB_TOKEN to avoid GitHub API rate limits. Requiring an LLM API key (Anthropic) is a reasonable design choice if the pipeline deliberately uses that service, but it must be declared up front. The omission is disproportionate to the manifest and could mislead users into installing without realizing required credentials will be used remotely.
Persistence & Privilege
always is false and the skill does not request or attempt to modify other skills or system-wide agent settings. It writes a temporary markdown file (/tmp/geeknews_brief_YYYYMMDD.md) and checks environment variables; this is normal for a cron-driven script and does not request elevated persistence.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install telegram-geeknews - 安装完成后,直接呼叫该 Skill 的名称或使用
/telegram-geeknews触发 - 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
v1.0.0
- 최초 공개 버전.
- GeekNews의 HOT 이슈 5개를 오픈소스/GitHub 중심으로 선정하여 텔레그램으로 자동 전송하는 데일리 브리프 기능 제공.
- RSS 피드 우선, 실패 시 웹 스크래핑으로 데이터 수집.
- 오픈소스, GitHub 트렌드, 개발 생산성 등 우선순위 기반 이슈 큐레이션 로직 구현.
- 텔레그램 메시지 자동 포맷 및 전송 지원.
- cron을 통한 매일 오전 8시 자동 실행 안내 포함.
元数据
常见问题
geeknews-bot 是什么?
매일 GeekNews(news.hada.io)에서 오늘의 HOT 이슈 5개를 큐레이션하고, 오픈소스 출시·GitHub star 급상승 프로젝트를 우선 선정하여 텔레그램으로 전송하는 데일리 브리프 에이전트 스킬. 사용자가 "긱뉴스 요약", "오늘 개발 뉴스", "OSS 뉴스", "텔... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 87 次。
如何安装 geeknews-bot?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install telegram-geeknews」即可一键安装,无需额外配置。
geeknews-bot 是免费的吗?
是的,geeknews-bot 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
geeknews-bot 支持哪些平台?
geeknews-bot 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 geeknews-bot?
由 DongJuS(@dongjus)开发并维护,当前版本 v1.0.0。
推荐 Skills