Web Reader TTS - 网页内容朗读技能
v1.0.0提取网页正文，自动检测语言，使用微软Edge TTS合成语音并通过Whisper识别，支持中英日及混合语言朗读。
⭐ 0· 0·0 current·0 all-time
byZach@phentse
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (web -> TTS -> Whisper) match the provided code and SKILL.md. Required packages (playwright, edge-tts, openai-whisper, langdetect) are appropriate for the stated functionality.
Instruction Scope
Runtime instructions and code limit actions to: navigate to the provided URL with Playwright, extract document.body.innerText, clean text, synthesize with edge-tts, and transcribe with Whisper. This is within scope. Note: Playwright runs a real browser (Chromium) which executes page JS/network activity while loading pages — the skill does not attempt to read local files or environment variables, but it will load remote content and the TTS call goes to Microsoft endpoints.
Install Mechanism
This is instruction-only (no install spec). The SKILL.md instructs pip installs and running `python -m playwright install chromium`. That is expected but heavy: Playwright will download Chromium and Whisper may download large model weights. No arbitrary URL downloads or unusual installers are present in the package itself.
Credentials
No environment variables, credentials, or config paths are requested. The skill relies on network access for edge-tts and for downloading Whisper models, which is consistent with its function.
Persistence & Privilege
The skill does not request always:true or persistent/system-level changes. It does not modify other skills or agent-wide configuration. Autonomous invocation is default but not combined with other privilege escalations.
Assessment
This skill is internally coherent, but consider these practical points before installing: it will open arbitrary web pages in a headless Chromium instance (page JavaScript may run and make network requests while loading), and edge-tts sends text/audio generation requests to Microsoft endpoints (external network). Whisper will download model weights (medium ≈ 769 MB by default) and use local CPU/GPU, so expect substantial disk/CPU use. No credentials are requested, and no hidden endpoints were found in the files. If you will process sensitive content, avoid sending it to external services or review the code and run in a sandbox. Also ensure you have bandwidth/disk space for Playwright/Chromium and Whisper models.Like a lobster shell, security has layers — review code before you run it.
latestvk972rzb3qhgmdn5ggwkg5a321s84rftc
License
MIT-0
Free to use, modify, and redistribute. No attribution required.