Tdoc DOCX
LeoYeAI/openclaw-master-skills
Word 文档全能处理技能 | Complete Word Document Processing Skill. An agent skill from LeoYeAI/openclaw-master-skills.
把一段中文(或任意 Whisper 支持语言)的会议/面试录音用本地 Whisper large-v3 转成文本,再清洗成带说话人标签、修过 ASR 错字、分好章节的 markdown 文档(可选再转成 docx)。跨平台(macOS Apple Silicon 用 mlx-whisper,Windows/Linux/Intel Mac 用…
$ npx skills add xiaopengde/murmur --skill murmur -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install xiaopengde/murmur murmur --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "murmur" agent skill from https://github.com/xiaopengde/murmur/tree/main into .claude/skills/murmur/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "murmur", 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.
$ npx skills add xiaopengde/murmur --skill murmur -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install xiaopengde/murmur murmur --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "murmur" agent skill from https://github.com/xiaopengde/murmur/tree/main into .agents/skills/murmur/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "murmur", 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 xiaopengde/murmur --skill murmur -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install xiaopengde/murmur murmur --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "murmur" agent skill from https://github.com/xiaopengde/murmur/tree/main into .cursor/skills/murmur/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "murmur", 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.
$ npx skills add xiaopengde/murmur --skill murmur -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install xiaopengde/murmur murmur --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "murmur" agent skill from https://github.com/xiaopengde/murmur/tree/main into .gemini/skills/murmur/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "murmur", 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 xiaopengde/murmur murmurInstalls 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 xiaopengde/murmur --skill murmur -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "murmur" agent skill from https://github.com/xiaopengde/murmur/tree/main into .github/skills/murmur/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "murmur", 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 xiaopengde/murmur --skill murmur -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install xiaopengde/murmur murmur --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "murmur" agent skill from https://github.com/xiaopengde/murmur/tree/main into .opencode/skills/murmur/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "murmur", 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.
murmur把一段中文(或任意 Whisper 支持语言)的会议/面试录音用本地 Whisper large-v3 转成文本,再清洗成带说话人标签、修过 ASR 错字、分好章节的 markdown 文档(可选再转成 docx)。跨平台(macOS Apple Silicon 用 mlx-whisper,Windows/Linux/Intel Mac 用…
Murmur is an agent skill from xiaopengde/murmur. 把一段中文(或任意 Whisper 支持语言)的会议/面试录音用本地 Whisper large-v3 转成文本,再清洗成带说话人标签、修过 ASR 错字、分好章节的 markdown 文档(可选再转成 docx)。跨平台(macOS Apple Silicon 用 mlx-whisper,Windows/Linux/Intel Mac 用 whisper-ctranslate2)。零云端、零订阅、隐私不出本机。适用:替代飞书妙计/通义听悟/Otter.ai 这类付费转录服务、需要在 VS Code 或 Word 里直接拿到可读稿、在 AI agent(Claude Code/Copilot/Codex/Cursor)里端到端跑通。不适用:实时转录、强噪声多人重叠会议、需要严格说话人分离的场景。
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 30 other files, including scripts (for example `README.md`, `docs/install-mac.md` and `docs/install-windows.md`).
It sits in AI & LLM Engineering, covering Speech recognition and synthesis and Word documents. It works with Microsoft Word, Linux, Visual Studio Code and macOS. The repository describes itself as: 🎙 Local zero-cost audio→markdown/docx pipeline. Whisper + AI cleanup. Replaces Otter.ai/飞书妙计. Agent-ready (Claude Code/Codex/Copilot/Cursor). macOS/Windows/Linux. The licence is MIT.
7 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit eef63ab. 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.
Ships 7 files in scripts/ (Python, Shell and PowerShell, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
pythonbashuvxffmpegbrewwingetFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
pypi.tuna.tsinghua.edu.cnhf-mirror.comAlso links to:
agentskills.ioFrom 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.
Murmur loads about 2.9k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 766 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 noted patterns worth knowing about, such as sudo or a known installer.
- 如果用户在 macOS 且首次安装,可能需要 sudo 提示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); the scripts in this folder are not scanned.
The full file from xiaopengde/murmur at commit eef63ab, republished under its MIT licence (© xiaopengde). 766 words, ~2,940 tokens.
.claude/skills/murmur/SKILL.md (or your agent's skills folder). This skill also uses 26 other files; get the full folder from GitHub.仓库:https://github.com/xiaopengde/murmur 适用 agent:GitHub Copilot Agent / Claude Code / OpenAI Codex / Cursor / 任意遵循 agentskills.io 的 agent
满足以下任一触发该 skill:
.m4a / .mp3 / .wav / .mp4 / .webm / .flac / .ogg 文件假设用户是新机器,刚装完 Claude Code / Codex / Copilot,没装其他任何东西。所以先检查环境:
# macOS / Linux
bash scripts/doctor.sh
# Windows (PowerShell)
powershell -ExecutionPolicy Bypass -File scripts/doctor.ps1doctor 脚本会分两块输出:
ffmpeg / uvx / pandoc / python3 / 平台和芯片 / 模型缓存(ModelScope / HuggingFace)如果核心依赖有 ❌,跑对应的 install 脚本:
# macOS
bash scripts/install-mac.sh
# Windows (需要管理员 PowerShell)
powershell -ExecutionPolicy Bypass -File scripts/install-windows.ps1安装完再跑一次 doctor。如果要在自动化里强校验,使用 strict 模式:
bash scripts/doctor.sh --strict
powershell -ExecutionPolicy Bypass -File scripts/doctor.ps1 -Strict--strict / -Strict 只有在核心依赖齐全且 onboarding 已完成时才返回 0;依赖缺失或 onboarding 未完成都会返回非 0。doctor 如果提示 onboarding 未完成,不要说“可以开始转录”,下一步必须跑 python scripts/transcribe.py --onboarding。
端到端验证(首次安装强烈推荐,或排查问题时;会使用临时配置,不污染用户默认值):
bash scripts/doctor.sh --smoke # macOS / Linux
powershell -ExecutionPolicy Bypass -File scripts/doctor.ps1 -Smoke # Windows会自动生成 2 秒测试音频跑完整 pipeline。大陆 Apple Silicon 会优先用 ModelScope large-v3-turbo 4bit(首次约 464MB),其他环境用 tiny 模型(首次约 75MB);通过后说明 ffmpeg → uvx → mlx/whisper → 文件输出全链路工作。失败时会保留临时目录方便排查。
无论用户是否已经给了音频文件,都必须先跑:
python scripts/transcribe.py --onboarding读取 JSON:
needs_onboarding=false:可以进入步骤 C。needs_onboarding=true:agent 必须使用 AskQuestion / 候选框让用户选择,不能自己决定,不能直接执行 JSON 里的 example。JSON 会明确包含:must_ask_user: truedo_not_choose_for_user: truedo_not_run_example_without_user_choice: true必须向用户询问两个候选项:
md 或 docxlarge-v3-turbo / large-v3 / medium / small用户选完后,运行:
python scripts/transcribe.py --init-defaults --format <md|docx> --set-default-model <model>只有这个命令成功后,才允许继续转录。--format / --model 是单次覆盖参数,不能绕过首次 onboarding;未完成 onboarding 时,转录主流程会直接退出并要求先完成 onboarding。
如果用户后来想改默认:
python scripts/transcribe.py --set-default md # 或 docx
python scripts/transcribe.py --set-default-model mediumpython scripts/transcribe.py <音频文件> [--lang zh] [--output-dir .] [--model medium] [--cn]脚本内部会:
ffmpeg 把任意输入转成 16kHz 单声道 WAV(关键——直接喂 m4a 会触发 Whisper 幻觉循环)uvx --from mlx-whisper mlx_whisper(GPU 加速,最快)uvx whisper-ctranslate2(CTranslate2 后端,CPU 也很快)转录原稿.txt + 字幕.srt 到目标目录⛔️ 进度转述硬约束(agent 必读,最常翻车的一步)
反模式(你大概率会犯,越自信的模型越容易犯):把这条转录命令当成「一个会返回结果的调用」,用一次性、长时间的前台阻塞等待(例如
Waiting 12m for shell/ 一个 timeout=30min 的同步调用)等它跑完,期间不回头看终端。你可能觉得「下载和推理中间没我什么事,等结束再汇报最高效」——这是错的。脚本每 30 秒就在终端打一行心跳(📥 模型下载/准备中... 已用时 x:xx/⏳ 转录推理中... 已用时 x:xx),但只要你一次性阻塞到结束,这些心跳全被你埋掉,用户面对的就是 十几分钟纯静默的终端,完全不知道是在下载、在推理、还是已经卡死。说一句「我会盯着进度」不等于你真的在盯。必须这样做(不可省略、不可优化掉):
- 禁止用单次「阻塞等到命令结束」的方式跑转录。要么把它放后台跑,要么用短 timeout(如每次最多等 30–45 秒)然后反复回来读终端。
- 每约 30 秒必须主动 poll 一次终端输出。
- 每次 poll 后,只要看到新的心跳或阶段变化(
📥 下载/准备→⏳ 转录推理→✅ 完成),立刻用一句前台消息转述给用户(例如「模型还在下载,约 40%」「已进入转录推理,已用时 2:00」「转录完成,正在整理输出」)。- 从命令开始到结束,中间不允许出现一次超过 ~45 秒的静默。如果你发现自己正打算「等它跑完再说」,停下——那就是上面的反模式。
首次没有缓存时,下载/准备完成后才算进入推理阶段;这两个阶段都要分别转述,不要把「还在下载」说成「在推理」。
🇨🇳 大陆网络:transcribe.py 会按时区/语言自动判断是否在大陆。命中后默认使用 --model-source auto:
~/.cache/murmur/models/,然后把本地目录交给现有 mlx-whisper / whisper-ctranslate2 推理。HF_ENDPOINT=https://hf-mirror.com(HuggingFace 镜像)和 UV_INDEX_URL=https://pypi.tuna.tsinghua.edu.cn/simple(uv 拉依赖走清华)。⚠️ 走 ModelScope 时注意 VPN:ModelScope 是国内 CDN,大陆直连最快。如果用户开了全局 VPN / 代理,流量会绕到海外再回国内,反而拖慢下载。看到走 ModelScope 时,agent 应提醒用户:「正在从国内源 ModelScope 下载,如开着全局 VPN 建议临时关掉直连更快」。(这点和走 HuggingFace 时相反——HF 路线开 VPN 才快。)
可手动指定模型源:
python scripts/transcribe.py 录音.m4a --model-source modelscope # 强制优先 ModelScope
python scripts/transcribe.py 录音.m4a --model-source hf # 强制原 HuggingFace/引擎默认源当前已验证映射:
mlx-whisper:large-v3-turbo → mlx-community/whisper-large-v3-turbo-4bit(ModelScope,约 464MB;下载后自动适配 model.safetensors → weights.safetensors)whisper-ctranslate2:large-v3-turbo → mobiuslabsgmbh/faster-whisper-large-v3-turbo(ModelScope,约 1.62GB,CTranslate2 格式;需要按目标平台 smoke test)用户已经手动设过的同名环境变量不会被覆盖。显式 --cn / --no-cn 强制单次开关。
持久化偏好(避免每次都加 --cn):
python scripts/transcribe.py --set-default-cn on # 以后每次自动启用
python scripts/transcribe.py --set-default-cn off # 以后每次走官方源
python scripts/transcribe.py --set-default-cn auto # 恢复按时区/语言自动判断(默认)也可以直接 bash scripts/install-mac.sh --cn(或 -CN for Windows),安装脚本会在结束时把偏好写进配置。
换更小的模型(CPU 慢机器常用):
python scripts/transcribe.py 录音.m4a --model medium # 单次
python scripts/transcribe.py --set-default-model medium # 永久(写入 config)
python scripts/transcribe.py --set-default-model "" # 清空恢复内置默认 large-v3-turbo支持 tiny / base / small / medium / large-v2 / large-v3 / large-v3-turbo 短名,会按引擎自动映射:
mlx-whisper 使用显式 HuggingFace repo 映射(例如 large-v3-turbo → mlx-community/whisper-large-v3-turbo,不是 ...-turbo-mlx)whisper-ctranslate2 透传短名(如 large-v3-turbo / medium)也支持透传完整 HF repo 名给高级用户。转录失败时,脚本会打印 resolved model,并尽量区分网络问题与 repo 不存在 / 私有 / 映射错误。
预期耗时:
~/.cache/murmur/models/(ModelScope 路线)或 ~/.cache/huggingface/hub/(原 HuggingFace 路线;Win 是 %USERPROFILE%\.cache\huggingface\hub\),日志显示 📥 模型下载/准备中;缓存就绪后才显示 ⏳ 转录推理中,之后秒级冷启动⚠️ 关键约定:脚本里已经默认关掉了 condition-on-previous-text,因为这是 No.1 大坑(不关会输出"X 点 X 点 X 点……"或"谢谢观看"成段重复)。不要修改这个默认值。
读 转录原稿.txt,按以下步骤执行(不要跳过任何一步):
1. 组装 prompt(两种方式选一)
python scripts/clean.py 转录原稿.txt [--scene interview|meeting|podcast]
# 输出组装好的 prompt,复制到 LLM 对话框即可docs/prompts/clean-transcript.md,把 ## === PROMPT 开始 === 到 ## === PROMPT 结束 === 之间的内容原封不动复制出来(不要总结、不要省略、不要用下面的简化版代替)。然后在末尾的占位符处贴入 转录原稿.txt 的全部内容。2. 补场景描述(如已知,加在 prompt 最前面)
这是一段中文面试录音,面试官代称"面试官",应试者代称"我"。这是一段工作会议录音,已知参与者:[姓名/代号]。3. 发给 LLM 执行(GPT-4o / Claude / Gemini / 国内大模型均可)
4. 对照「输出前自检清单」核查
拿到 LLM 输出后,过一遍 docs/prompts/clean-transcript.md 末尾的「输出前自检清单」(7 项)。有不合格项让 LLM 补改后再保存。
5. 保存为 逐字稿-清洗版.md,放在和音频同目录。
6. 主动把成果递到用户眼前(不要只报路径)
清洗稿是用户唯一真正关心的交付物,落盘后必须:
逐字稿-清洗版.md(Cursor / VS Code:用打开文件的工具直接打开它,让用户一抬眼就看到稿子;Claude Code / Codex CLI 等无法直接开文件时,在回复里贴出开头一段做即时预览)。python scripts/md2docx.py 逐字稿-清洗版.md会在同目录输出 逐字稿-清洗版.docx,用 pandoc 实现,跨平台一致。
如果用户配置了默认 docx,不要问"要不要转 docx",直接转就完事——这是设默认的意义。转好后同样主动打开/告知 docx 的完整路径,别让用户自己去找。
仅当用户明确说"复盘 / 纪要 / 总结 / retro"时做。读 docs/prompts/retrospective.md,按里面的模板生成 复盘纪要.md。
默认只交付步骤 D 的清洗稿,不要主动给复盘——大多数人只要可读逐字稿。
一次会议/面试 = 一个子目录:
<场景名-YYYY-MM-DD>/
├── 录音.m4a ← 用户的原始音频
├── 字幕.srt ← transcribe.py 输出,保留
├── 转录原稿.txt ← transcribe.py 输出,保留(清洗依据)
├── 逐字稿-清洗版.md ← LLM 清洗产物,主要交付物
├── 逐字稿-清洗版.docx ← 默认 docx 时附加产物
└── 复盘纪要.md ← 可选如果用户音频文件本来就在某个目录里,就在那个目录就地输出;不要无中生有创建子目录除非用户要求。
通用红线:所有平台都必须遵守步骤 C 的「进度转述硬约束」——不要用一次性长阻塞等转录跑完。下面是各平台具体怎么做到「后台跑 / 短轮询 + 每 30s 转述」。
mode='sync' + 一个 30min 长 timeout 一次性等完——那样心跳全被埋掉。改用后台运行(isBackground=true)或 mode='sync' 配短 timeout(30–45s)然后反复再读同一终端的输出send_to_terminal 任何命令到正在转录的持久 zsh——会 Ctrl+C 掉进程Bash 调用阻塞到结束。把转录放后台(命令尾 & 或后台模式),再用 BashOutput 每约 30s 轮询一次输出并转述心跳| 症状 | 原因 | 解法 |
|---|---|---|
| 转录文本反复 "X 点 X 点 X 点…" 或某句话整段重复 | condition-on-previous-text 未关 | 用本仓库的 transcribe.py 不会有这个问题;如果手动改过命令,加回 --condition-on-previous-text False |
| 全程 "谢谢观看" 成段重复 | 音频开头有静音 + 没做 ffmpeg 预处理 | 用本仓库的 transcribe.py 自动处理;手动跑时记得先 ffmpeg -ar 16000 -ac 1 |
| 速度极慢 | 用成了 openai-whisper PyPI 版(纯 CPU + Python) | 确认走的是 mlx-whisper(Mac AS)或 whisper-ctranslate2(其他) |
| 模型下载卡住 | HuggingFace 网络问题 | 优先加 --model-source modelscope 或 --cn 走 ModelScope 已验证模型;常用国内的话直接 --set-default-cn on |
| uvx 首次拉 mlx-whisper / whisper-ctranslate2 卡住 | PyPI 访问慢 | 同样加 --cn,会同时注入 UV_INDEX_URL=https://pypi.tuna.tsinghua.edu.cn/simple |
| CPU 机器转录慢、显存不够 | 模型太大 | 换小模型:--model medium 单次,或 --set-default-model medium 永久 |
brew install / winget install 卡在下载 | 国内访问 Homebrew bottle / GitHub Releases 慢 | 重跑安装脚本时加 CN flag:<br>Mac: bash scripts/install-mac.sh --cn(启用 USTC 镜像)<br>Win: powershell -ExecutionPolicy Bypass -File scripts\install-windows.ps1 -CN(启用 Scoop/PyPI 兜底)<br>脚本默认会按时区/语言自动判断,加 flag 是强制启用 |
| Mac 上 install-mac.sh 报 "command not found: brew" | Homebrew 没装 | 让用户先装 Homebrew(脚本会给提示) |
| Windows 上 install-windows.ps1 报权限错误 | PowerShell 没用管理员模式 | 右键 PowerShell → 以管理员身份运行 |
| Windows 上 winget 找不到 | 旧版 Windows 10 没装 winget | 让用户从 Microsoft Store 装 "App Installer" |
| 英文术语全错 | 多语言混读触发了语言切换 | transcribe.py 默认 --language zh,对中文为主的录音最稳;纯英文用 --lang en |
| 说话人混在一起 | Whisper 不带 diarization | 清洗阶段靠上下文推断;多人混乱场景用 **说话人 1/2/3** 占位 |
| 转录到一半进程被杀 | 同一持久终端被 send_to_terminal 干扰 / 电脑休眠 | 见 §3 "GitHub Copilot Agent" 注意事项 |
完整故障排查见 docs/troubleshooting.md。
假设用户给你一个 面试.m4a,目标默认 docx:
# 1) 环境检查(macOS)
bash scripts/doctor.sh
# 2) 缺啥装啥
bash scripts/install-mac.sh
# 3) 转录(首次会问 md/docx,让用户回答)
python scripts/transcribe.py 面试.m4a
# 4) agent 你来读 转录原稿.txt,按 docs/prompts/clean-transcript.md
# 清洗输出 逐字稿-清洗版.md(这一步是 LLM 自己做,不调脚本)
# 5) 默认 docx → 转
python scripts/md2docx.py 逐字稿-清洗版.md
# 6) 用户说要复盘?再来一步
# 读 docs/prompts/retrospective.md,输出 复盘纪要.md整个过程只有一次用户交互(首次 onboarding 的格式 + 模型选择),之后都是无人值守。
写给后续维护者 / fork 这个 skill 的 agent:
docs/prompts/,agent 直接读,方便用户改© xiaopengde, 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 26 other files (scripts) in the repository root of xiaopengde/murmur.
Open the folder on GitHubat commit eef63ab
Murmur 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 |
|---|---|---|---|---|---|---|
| Murmur this skillxiaopengde/murmur | 109 | — | ~2.9k | Automated safety check: Notes | MIT | |
| Tdoc DOCXLeoYeAI/openclaw-master-skills | 2.2k | — | ~3.6k | Automated safety check: Notes | MIT | |
| Video EditingLeoYeAI/openclaw-master-skills | 2.2k | — | ~2.7k | Automated safety check: Notes | MIT | |
| Local Asrysyecust/lecture-to-notes | 269 | — | ~1.6k | Automated safety check: Pass | Custom licence | |
| Local RAGnigo81/nigo-skills | 133 | — | ~1.4k | Automated safety check: Pass | MIT | |
| Vlog Auto Editznyupup/ai-video-editing-skill | 144 | — | ~6.8k | Automated safety check: Pass | MIT |
LeoYeAI/openclaw-master-skills
Word 文档全能处理技能 | Complete Word Document Processing Skill. An agent skill from LeoYeAI/openclaw-master-skills.
LeoYeAI/openclaw-master-skills
Automated video editing skill for talk/vlog/standup videos. An agent skill from LeoYeAI/openclaw-master-skills.
ysyecust/lecture-to-notes
把本地长视频/音频转写成文字稿 + 可选字幕,纯本地(不上传云端),用 sherpa-onnx X-ASR Zipformer transducer 模型(int8 量化、中英双语、自动标点)。已在 macOS Apple Silicon(int8 + AMX,~100× 实时)、Linux ARM64(CPU,~32× 实时)与 Windows(PowerShell…
nigo81/nigo-skills
本地向量知识库,支持按项目管理文档(docx/doc/pdf/md),语义检索。默认用硅基流动免费 API,零模型安装即可使用。支持多项目隔离、中文制度文档专用切片、Embedding+Rerank 两阶段检索。触发词:知识库、向量检索、RAG、制度检索、文档入库、语义搜索、local…
znyupup/ai-video-editing-skill
AI Agent自动剪辑旅行Vlog的完整工作流。从原始素材到成品视频,系统级只需ffmpeg,其余在Python venv内完成。by nyx研究所 (GitHub @znyupup · B站/小红书 @nyx研究所)
zhuzhaoyun/Molio
PRIMARY skill for converting .pdf, .docx, .pptx, .xlsx, .doc, .ppt, .xls, images, and audio/video files (.mp3, .wav, .m4a, .mp4, .mov, etc.) to Markdown.
Categories
把一段中文(或任意 Whisper 支持语言)的会议/面试录音用本地 Whisper large-v3 转成文本,再清洗成带说话人标签、修过 ASR 错字、分好章节的 markdown 文档(可选再转成 docx)。跨平台(macOS Apple Silicon 用 mlx-whisper,Windows/Linux/Intel Mac 用…. Murmur is an agent skill from xiaopengde/murmur.
Murmur fits situations like: tasks that involve Speech recognition and synthesis; tasks that involve Word documents.
Run `npx skills add xiaopengde/murmur --skill murmur -a claude-code`. Or copy the skill folder (the xiaopengde/murmur repository) into .claude/skills/murmur in your project. Claude Code loads it when a task matches its description.
Run `npx skills add xiaopengde/murmur --skill murmur -a codex`. Or copy the skill folder (the xiaopengde/murmur repository) into .agents/skills/murmur 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 xiaopengde/murmur --skill murmur -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/murmur, .gemini/skills/murmur, .github/skills/murmur and .opencode/skills/murmur in your project.
Going by SKILL.md and its folder, Murmur needs Python, a shell and PowerShell for the scripts in its folder and the command-line tools its instructions call (python, bash, uvx, ffmpeg, brew and winget). Our summary lists: Python 3; A Bash shell; PowerShell.
SKILL.md names 3 domains. In commands or code: pypi.tuna.tsinghua.edu.cn and hf-mirror.com; the agent is likely to contact these when it follows the instructions. As links in the text: agentskills.io. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found notes only (runs commands with sudo), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Murmur is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Murmur: Tdoc DOCX (LeoYeAI/openclaw-master-skills, 2.2k stars), Video Editing (LeoYeAI/openclaw-master-skills, 2.2k stars), Local Asr (ysyecust/lecture-to-notes, 269 stars) and Local RAG (nigo81/nigo-skills, 133 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
xiaopengde (a GitHub user) maintains it in xiaopengde/murmur, which has 109 GitHub stars. The repository was last updated on May 31, 2026.
Source: xiaopengde/murmur on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.