Menu
Generate speech audio from text using Gemini 3.1 Flash TTS (with emotion control) or Edge TTS fallback. Use when the user says "/tts", "语音合成", "文字转语音", "念出来", "读出来", "生成语音", "帮我念", "说出来", or when asked to convert text to speech audio.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
NVIDIA NVL72 (GB200/GB300) GPU 集群验收测试。Profile 驱动的端到端质检：硬件自检、DCGM 诊断、NCCL 带宽、cuBLAS GEMM、单域/跨域多节点 NCCL、日志分析、报告生成、故障节点处理。含验收 baseline 阈值与判定标准。当用户说"验收测试"、"GPU QA"、"质检"、"跑一下 hw-check"、"NCCL benchmark"、"节点健康检查"、"GPU 集群测试"、"NVL72 测试"、"GB300 QA"、"GB200 QA"等关键词时触发。
Build polished, on-brand slide decks (python-pptx → Google Slides) and richly formatted Google Docs, with a reusable design system, matplotlib charts, AI-generated imagery (Nano Banana), a render-verify loop, and link-stable Drive uploads (PATCH same fileId so the share link never changes). Use when the user wants to create or iterate a presentation / briefing deck / exec one-pager / formatted Google Doc — especially customer or executive briefings that go into Google Drive. Also covers extracting user-pasted images from the session transcript and converting decks/docs to PNG for visual self-check.
Generate music using Google Lyria 3 (DeepMind). Use for "生成音乐", "作曲", "写一首曲子", "generate music", "create a song", "compose", "piano piece", "钢琴曲", "make a beat", "生成钢琴曲", "来一首歌".
Read WeChat Official Account (微信公众号) articles. Trigger when user shares any mp.weixin.qq.com URL, or says "微信文章", "公众号文章", "读一下这个微信链接", "WeChat article". Bypasses WeChat's anti-scraping CAPTCHA by emulating the WeChat in-app browser. MUST be used instead of WebFetch/Jina for any mp.weixin.qq.com link — those tools WILL fail with "环境异常" CAPTCHA.
Compute Hong Kong salaries tax partial exemption for share awards (GSU / RSU / stock options) under DIPN No. 38 paragraphs 43-46 and section 8(1A)(a) of the Inland Revenue Ordinance. Full lifecycle: (1) auto-extract vest data from Morgan Stanley / IRD / IR56B via Chrome MCP, (2) compute DIPN 38 time apportionment, (3) cross-check IR56B vs IRD assessment to detect unclaimed exemptions, (4) generate APPENDIX-EQUITY PDF for eTAX submission, (5) generate HTML audit report for personal review, (6) guide eTAX BIR60 filing or 70A retrospective claim. Triggers: HK salaries tax, BIR60, IR56B, share award apportionment, DIPN 38, 'partial exemption', cross-border GSU/RSU vest, '报税分析', '股票减税', 'GSU 豁免', '从内地转来香港', '70A', 'time apportionment', '股票报税'.
Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.
| name | tts-generator |
| description | Generate speech audio from text using Gemini 3.1 Flash TTS (with emotion control) or Edge TTS fallback. Use when the user says "/tts", "语音合成", "文字转语音", "念出来", "读出来", "生成语音", "帮我念", "说出来", or when asked to convert text to speech audio. |
Generate expressive speech audio using Google Gemini 3.1 Flash TTS with emotion/audio tag support. Falls back to Edge TTS if Gemini is unavailable.
# Generate OGG audio (Gemini, default)
OGG=$(~/.claude/skills/tts-generator/scripts/tts-generate.py "[casually] 你好世界")
# Choose voice
OGG=$(~/.claude/skills/tts-generator/scripts/tts-generate.py "[excitedly] 太棒了！" --voice sulafat)
# Fallback to Edge TTS
OGG=$(~/.claude/skills/tts-generator/scripts/tts-generate.py "你好" --engine edge --voice xiaoxiao)
# Send as Discord voice message
~/.claude/scripts/send-to-discord.sh --voice "$OGG"
# Clean up
rm -f "$OGG"
| 代号 | 风格 | 代号 | 风格 |
|---|---|---|---|
aoede (default) | 轻松 | achird | 友好 |
sulafat | 温暖 | kore | 坚定 |
puck | 欢快 | charon | 知性 |
fenrir | 兴奋 | leda | 青春 |
zephyr | 明亮 | achernar | 柔和 |
gacrux | 成熟 | sadachbia | 活泼 |
algieba | 顺滑 | vindemiatrix | 温柔 |
orus | 坚定 |
Gemini TTS 支持 inline audio tags 控制情感和风格。有两种工作模式，行为不同：
只有一个开头标签时，脚本把它翻译成 director 指令喂给 Gemini："[casually] 你好" → "Say the following in Chinese, casually:\n你好"。这种模式下任意词都能用（因为 Gemini 把它当自然语言指令理解），所以下面这些"自创"标签都能工作：
"[casually] 今天的进度还不错" # 随意
"[excitedly] 实验通过了！" # 兴奋
"[thoughtfully] 这个方案有两个权衡点" # 思考
"[seriously] 注意这个安全隐患" # 严肃
"[cheerfully] 早上好！" # 愉快
"[calmly] 总结一下今天的工作" # 平静
文本里有 ≥2 个标签时，脚本不动它，原样 pass 给 Gemini。Gemini 只认它训练时见过的官方词，自创词会被静默丢弃。一段话里想多次切换情绪（推荐用法，更生动）必须用下面的官方词：
思考类：[thinking] [contemplative] [analysis] [focus] [reflection] [planning] [speculation] [pensive] [curiosity]
积极类：[excitement] [enthusiasm] [joy] [happy] [pleased] [optimism] [playful] [amusement] [friendly] [triumph] [satisfaction]
中性类：[neutral] [contentment] [serenity] [relaxation] [certainty]
严肃类：[seriousness] [urgency] [warning] [concern] [caution] [emphasis]
惊讶类：[surprise] [amazement] [realization] [confusion] [uncertainty] [doubt] [disbelief]
消极类：[disappointment] [frustration] [regret] [exhaustion] [weariness]
幽默类：[humor] [sarcasm] [amused] [self-deprecation]
自信类：[confidence] [determination] [assertive] [pride]
特效类：[whispers] [laughs] [sighs] [slow] [fast]
说明类：[informative] [explaining] [summary] [instruction] [suggestion]
多标签例子（好）：
[curiosity] 我先看下日志。[realization] 哦原来是端口冲突。
[amused] 这种小坑最烦了。[suggestion] 你 kill 8080 那个就行。
多标签例子（差）：
[casually] 我看了日志发现端口冲突 你 kill 8080 就行
# 整段一个标签，且 [casually] 不是官方词，多标签场景下还会被丢
xiaoxiao — 女声（默认）xiaoyi — 女声，温柔yunxi — 男声，活力yunjian — 男声，成熟yunyang — 男声，新闻播报yunxia — 男声，少年GOOGLE_API_KEY env var or GCP Application Default Credentials