技能详情（站内镜像，无评论）
作者：Cheer @cheerwhy
许可证：MIT-0
MIT-0 ·免费使用、修改和重新分发。无需归因。
版本：v0.1.1
统计：⭐ 1 · 37 · 0 current installs · 0 all-time installs
⭐ 1
安装量（当前） 0
🛡 VirusTotal ：良性 · OpenClaw ：良性
Package：cheerwhy/lark-voice
安全扫描（ClawHub）
- VirusTotal ：良性
- OpenClaw ：良性
OpenClaw 评估
The skill's requests and runtime instructions align with its stated purpose (convert TTS output to opus and send via the platform message tool); it requires only ffmpeg and uses temporary files, with no unrelated credentials or installs.
目的
Name and description match the instructions: the skill converts text-to-speech audio into the opus format and sends it through the platform message tool. Requiring the ffmpeg binary is appropriate and proportional for audio conversion.
说明范围
Instructions tell the agent to discover available TTS sources by scanning installed skills (searching for names containing 'tts') and to use a built-in tts fallback. That behavior is reasonable for selecting a TTS provider, but it does require the agent to enumerate installed skills/plugins — users should be aware the skill looks at available skills/tools to make its choice. It writes intermediate files to /tmp/openclaw/ and uses the provided …
安装机制
This is an instruction-only skill with no install spec and no downloads. That is the lowest-risk pattern — no code is written to disk by an installer.
证书
The skill declares no required environment variables or credentials. It only requires an ffmpeg binary and access to an existing 'message' tool and available TTS providers, which matches the described functionality.
持久
The skill does not request persistent presence (always: false) and does not attempt to modify other skills or system-wide settings. It uses ephemeral files for intermediate audio.
综合结论
This skill appears internally consistent: it just needs ffmpeg, a TTS provider (built-in or another installed skill), and the platform 'message' tool to send the resulting .opus file. Before installing, verify: (1) you trust the ffmpeg binary on your system; (2) the 'message' tool referenced is the official OpenClaw/Lark integration and will deliver audio only to intended recipients; and (3) you're comfortable with the skill enumerating instal…
安装（复制给龙虾 AI）
将下方整段复制到龙虾中文库对话中，由龙虾按 SKILL.md 完成安装。
请把本段交给龙虾中文库（龙虾 AI）执行：为本机安装 OpenClaw 技能「Lark (Feishu) Voice」。简介：Send voice messages on Lark (Feishu) by converting text to speech. Use when the…。
请 fetch 以下地址读取 SKILL.md 并按文档完成安装：https://raw.githubusercontent.com/openclaw/skills/refs/heads/main/skills/cheerwhy/lark-voice/SKILL.md
（来源：yingzhi8.cn 技能库）SKILL.md
暂无本地缓存内容，可在后台执行详情同步。