Speech
davila7/claude-code-templates
A skill your agent uses when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation.
演讲与分享教练。基于Patrick Winston(MIT AI教授)的How to Speak方法论,帮助准备线下培训、技术分享、B站教程视频等演讲场景。当用户提到"演讲"、"分享"、"培训"、"讲课"、"PPT演讲"、"开场"、"结尾"、"如何讲"、"演讲结构"时使用此技能。
$ npx skills add alchaincyf/huashu-skills --skill huashu-speech-coach -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install alchaincyf/huashu-skills huashu-speech-coach --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/alchaincyf/huashu-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/huashu-speech-coach .claude/skills/huashu-speech-coach && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "huashu-speech-coach" agent skill from https://github.com/alchaincyf/huashu-skills/tree/master/huashu-speech-coach into .claude/skills/huashu-speech-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-speech-coach", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/alchaincyf/huashu-skills/tree/master/huashu-speech-coachType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add alchaincyf/huashu-skills --skill huashu-speech-coach -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install alchaincyf/huashu-skills huashu-speech-coach --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alchaincyf/huashu-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/huashu-speech-coach .agents/skills/huashu-speech-coach && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "huashu-speech-coach" agent skill from https://github.com/alchaincyf/huashu-skills/tree/master/huashu-speech-coach into .agents/skills/huashu-speech-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-speech-coach", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alchaincyf/huashu-skills --skill huashu-speech-coach -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install alchaincyf/huashu-skills huashu-speech-coach --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alchaincyf/huashu-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/huashu-speech-coach .cursor/skills/huashu-speech-coach && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "huashu-speech-coach" agent skill from https://github.com/alchaincyf/huashu-skills/tree/master/huashu-speech-coach into .cursor/skills/huashu-speech-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-speech-coach", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/alchaincyf/huashu-skills.git --path huashu-speech-coach--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add alchaincyf/huashu-skills --skill huashu-speech-coach -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install alchaincyf/huashu-skills huashu-speech-coach --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alchaincyf/huashu-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/huashu-speech-coach .gemini/skills/huashu-speech-coach && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "huashu-speech-coach" agent skill from https://github.com/alchaincyf/huashu-skills/tree/master/huashu-speech-coach into .gemini/skills/huashu-speech-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-speech-coach", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install alchaincyf/huashu-skills huashu-speech-coachInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add alchaincyf/huashu-skills --skill huashu-speech-coach -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/alchaincyf/huashu-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/huashu-speech-coach .github/skills/huashu-speech-coach && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "huashu-speech-coach" agent skill from https://github.com/alchaincyf/huashu-skills/tree/master/huashu-speech-coach into .github/skills/huashu-speech-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-speech-coach", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add alchaincyf/huashu-skills --skill huashu-speech-coach -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install alchaincyf/huashu-skills huashu-speech-coach --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alchaincyf/huashu-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/huashu-speech-coach .opencode/skills/huashu-speech-coach && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "huashu-speech-coach" agent skill from https://github.com/alchaincyf/huashu-skills/tree/master/huashu-speech-coach into .opencode/skills/huashu-speech-coach/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "huashu-speech-coach", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
huashu-speech-coach演讲与分享教练。基于Patrick Winston(MIT AI教授)的How to Speak方法论,帮助准备线下培训、技术分享、B站教程视频等演讲场景。当用户提到"演讲"、"分享"、"培训"、"讲课"、"PPT演讲"、"开场"、"结尾"、"如何讲"、"演讲结构"时使用此技能。
Huashu Speech Coach is an agent skill from alchaincyf/huashu-skills. 演讲与分享教练。基于Patrick Winston(MIT AI教授)的How to Speak方法论,帮助准备线下培训、技术分享、B站教程视频等演讲场景。当用户提到"演讲"、"分享"、"培训"、"讲课"、"PPT演讲"、"开场"、"结尾"、"如何讲"、"演讲结构"时使用此技能。
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/patrick-winston-how-to-speak.md`).
The repository describes itself as: 花叔全部开源 Agent Skills 总目录:16 旗舰 + 14 人物视角 + 22 内置共 52 个 skill,分层分类 + AI Agent 安装协议 + 机器可读 skills.json + 更新检查机制. The licence is MIT.
4 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 2efea35. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
youtu.beFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Huashu Speech Coach loads about 1.3k tokens when it runs, and up to ~3.8k if it reads all its reference files. Until then it costs about 40 tokens; SKILL.md has 283 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from alchaincyf/huashu-skills at commit 2efea35, republished under its MIT licence (© alchaincyf). 283 words, ~1,285 tokens.
.claude/skills/huashu-speech-coach/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.基于Patrick Winston教授(MIT)的How to Speak方法论 原始视频:https://youtu.be/Unzc731iCUY Winston教授2019年去世,这门课成为他的「最后一课」,在YouTube上收获1500万+观看 参考材料:
references/patrick-winston-how-to-speak.md
| 场景 | 怎么帮 |
|---|---|
| 线下培训/工作坊 | 审查大纲结构、优化开场结尾、设计互动环节 |
| B站教程视频 | 优化脚本节奏、检查循环点、设计钩子 |
| 技术分享/meetup | 审查演讲稿、检查Winston规则、模拟观众视角 |
| PPT/Keynote审查 | 检查幻灯片「罪行」、优化信息密度 |
演讲质量 = f(知识, 练习, 天赋)天赋占比极小。真正决定演讲质量的是:你掌握多少关于演讲的知识(启发式规则),以及你练习了多少次。
观众刚到场时还在适应——收手机、调整坐姿、适应你的声音。这时讲笑话极容易冷场,而冷场会影响你整场的信心。
告诉观众:听完这段,你将获得什么。给他们一个留下来的理由。
好的承诺:
差的承诺:
人类只有一个语言处理器。如果观众在看手机,他们听不进去你说的话。更糟的是,看手机的人会分散旁边人的注意力,也会让演讲者分心。
线下培训时:直接要求合上电脑、放下手机 视频场景:前10秒必须给出足够强的理由让观众留下
在任何时刻,约20%的观众处于走神状态。通过3次重复核心概念(用不同方式),确保每个人都能接收到关键信息。
操作方法:「告诉他们你要讲什么 → 讲给他们听 → 告诉他们你讲了什么」
视频场景应用:每隔3-5分钟回扣主题,用一句话把观众拉回来。「所以回到我们的核心问题——为什么手搓经济突然火了?」
明确你的想法与他人想法的区别,防止观众混淆。
操作方法:说清楚「我讲的是什么」和「我讲的不是什么」
示例:
为走神的观众提供「重新上车」的机会。用明确的结构提示,让迷失的观众知道你讲到了哪里。
操作方法:
提问能瞬间抓回注意力。关键是提问后必须等待。
等待时间:至少7秒。不要因为沉默尴尬就自己回答。
问题难度:
视频场景:虽然观众无法真正回答,但提问制造了思考的停顿,比直接给答案更有效。
| 规则 | 要求 | 原因 |
|---|---|---|
| 最佳时间 | 上午11点 | 大家醒了,还没午饭犯困 |
| 灯光 | 全开 | 灯暗=睡觉信号。「闭着眼皮看不清幻灯片」 |
| 踩点 | 提前到场检查 | 了解设备、灯光开关、话筒、座位布局 |
| 填充房间 | 选会被填满一半以上的房间 | 人太少气氛冷清,宁可换小房间 |
道具有极强的视觉记忆点。观众可能忘了理论,但一定记住道具。
应用:演讲中涉及实物时,拿出来展示。比如讲「小猫补光灯」时,真的拿出手机演示。
| 罪行 | 为什么有问题 | 怎么改 |
|---|---|---|
| 朗读幻灯片 | 观众识字比你读得快,会烦 | 幻灯片是提示,不是台词 |
| 离屏幕太远 | 观众像看网球,视线来回跳 | 站在屏幕旁边 |
| 堆砌文字 | 信息过载,什么都记不住 | 字体≥40号,倒逼精简 |
| 使用剪贴画/Logo | 视觉噪音 | 删掉一切装饰 |
| 使用激光笔 | 背对观众,失去眼神交流 | 在幻灯片上画箭头,或用手指 |
| 复杂背景图案 | 降低可读性 | 纯色背景 |
| 要点过多 | 每张太密 | 一张一个核心观点 |
整场演讲中允许一张极其复杂的幻灯片。目的不是让观众看清内容,而是展示问题的复杂性和规模,建立威信。
传递「你行的」的信念比教具体技能更重要。让他们相信自己能做到。
展示你对这件事的真实热情。如果你觉得某个东西很酷,就表现出来。激情是最强的感染力。
Winston主张通过故事来教思考方式。提供:
好的结尾示例:
如果你希望自己的项目/产品/研究被人记住,需要5个要素:
| 要素 | 说明 | 花叔示例 |
|---|---|---|
| 符号 Symbol | 一个可视化图标 | 小猫补光灯的猫咪图标 |
| 口号 Slogan | 一个朗朗上口的短语 | 「手搓经济」「Vibe Coding」 |
| 惊喜 Surprise | 一个反直觉的事实 | 「开发成本只有几十块钱API费」 |
| 突出的想法 Salient Idea | 最容易被记住的概念 | 「一人公司」 |
| 故事 Story | 它是怎么发生的 | 小猫补光灯从自用到付费榜第一的经历 |
Winston通过自己的演讲演示但未明确教授的技巧:
给我你的演讲大纲,我会从以下维度审查:
给我你的视频脚本,我会检查:
给我你的幻灯片,我会逐张检查七宗罪:
我会模拟一个具体观众画像(如:「第一次接触AI编程的产品经理」),从他们的视角听你的演讲,标记:
当审查演讲/脚本时,从5个维度评分:
| 维度 | 评判标准 |
|---|---|
| 开场力 | 赋能承诺的吸引力、前60秒的抓取力 |
| 结构清晰度 | 循环、口头标点、筑墙划界是否到位 |
| 互动性 | 提问、停顿、观众参与设计 |
| 视觉辅助 | 幻灯片/道具是否遵守规则 |
| 结尾力 | 是否有力、是否给出贡献/行动、是否致敬而非感谢 |
综合评分 + 逐项建议 + 优先修改项(改动最小、收益最大的3件事)
演讲前:
演讲中:
演讲后:
花叔出品 | AI Native Coder · 独立开发者 公众号「花叔」| 30万+粉丝 | AI工具与效率提升 代表作:小猫补光灯(AppStore付费榜Top1)·《一本书玩转DeepSeek》
© alchaincyf, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (references) in huashu-speech-coach of alchaincyf/huashu-skills.
Open the folder on GitHubat commit 2efea35
Huashu Speech Coach next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Huashu Speech Coach this skillalchaincyf/huashu-skills | 1.7k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Speechdavila7/claude-code-templates | 33k | — | ~2k | Automated safety check: Pass | Apache-2.0 | |
| Speechnexu-io/open-design | 100k | — | ~291 | Automated safety check: Pass | Apache-2.0 | |
| Text To Speechcalesthio/OpenMontage | 66k | — | ~2.4k | Automated safety check: Pass | AGPL-3.0 | |
| Azure Text To Speechcalesthio/OpenMontage | 66k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Venice Audio Speechnexu-io/open-design | 100k | — | ~296 | Automated safety check: Pass | Apache-2.0 |
davila7/claude-code-templates
A skill your agent uses when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation.
nexu-io/open-design
Generate spoken audio from text using OpenAI's API with built-in voices.
calesthio/OpenMontage
Generate speech audio from text using HeyGen's Starfish TTS model.
calesthio/OpenMontage
Generate neural narration audio using Azure AI Speech (REST text-to-speech).
nexu-io/open-design
Text-to-speech models, voices, formats, and streaming via Venice.ai.
NVIDIA/skills
Routes NVIDIA Nemotron Speech (Formerly Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted.
alchaincyf/huashu-skills
多Agent蜂群并行协作,纯git自组织,适合大型项目开发。当用户提到"蜂群模式"、"多agent"、"并行开发"、"agent swarm"时使用。
alchaincyf/huashu-skills
数据分析与办公提效全能助手。覆盖数据处理、分析洞察、报告撰写、PPT制作、数据可视化的端到端工作流. An agent skill from alchaincyf/huashu-skills.
alchaincyf/huashu-skills
抖音爆款脚本创作工作流。从竞品视频拆解到脚本生成的完整流程:下载抖音视频→Gemini视频分析→爆款公式提炼→脚本+分镜生成→AI味审校。
alchaincyf/huashu-skills
为微信公众号文章生成高质量配图。支持封面图(2.35:1)、正文插图(16:9/4:3)、信息图。提供两条路径:AI生成(视觉创意型)和HTML渲染(文字精确型)。当用户提到"公众号配图"、"公众号封面"、"文章配图"、"正文插图"、"公众号图片"时使用此技能。
alchaincyf/huashu-skills
为小红书笔记生成高质量配图。默认AI生成(Gemini),仅精确数据表格用HTML兜底。当用户提到"小红书配图"、"小红书封面"、"小红书图片"、"做张小红书图"、"笔记配图"时使用此技能。
alchaincyf/huashu-skills
从内容到成品PPTX的端到端演示文稿制作,含AI插画生成和18种设计风格。当用户提到"做PPT"、"做幻灯片"、"演示文稿"、"Keynote"、"slides"时使用。
演讲与分享教练。基于Patrick Winston(MIT AI教授)的How to Speak方法论,帮助准备线下培训、技术分享、B站教程视频等演讲场景。当用户提到"演讲"、"分享"、"培训"、"讲课"、"PPT演讲"、"开场"、"结尾"、"如何讲"、"演讲结构"时使用此技能。. Huashu Speech Coach is an agent skill from alchaincyf/huashu-skills.
Run `npx skills add alchaincyf/huashu-skills --skill huashu-speech-coach -a claude-code`. Or copy the skill folder (huashu-speech-coach in alchaincyf/huashu-skills) into .claude/skills/huashu-speech-coach in your project. Claude Code loads it when a task matches its description.
Run `npx skills add alchaincyf/huashu-skills --skill huashu-speech-coach -a codex`. Or copy the skill folder (huashu-speech-coach in alchaincyf/huashu-skills) into .agents/skills/huashu-speech-coach in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add alchaincyf/huashu-skills --skill huashu-speech-coach -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/huashu-speech-coach, .gemini/skills/huashu-speech-coach, .github/skills/huashu-speech-coach and .opencode/skills/huashu-speech-coach in your project.
SKILL.md names no scripts, command-line tools or credentials: Huashu Speech Coach is instructions for the agent only.
SKILL.md names 1 domain. As links in the text: youtu.be. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Huashu Speech Coach is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.5k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Huashu Speech Coach: Speech (davila7/claude-code-templates, 33k stars), Speech (nexu-io/open-design, 100k stars), Text To Speech (calesthio/OpenMontage, 66k stars) and Azure Text To Speech (calesthio/OpenMontage, 66k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
alchaincyf (a GitHub user) maintains it in alchaincyf/huashu-skills, which has 1,695 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 22, 2026.
Source: alchaincyf/huashu-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.