Agent skill

Tingwu Asr

by cat-xierluo in cat-xierluo/legal-skills

使用阿里云通义听悟进行云端音频/视频转录。本技能应在用户需要云端语音转文字、长音频转录、本地 ASR 不可用或需要更高精度时使用。不适用于无网络环境或需要完全离线的场景。

MITAuto-check: notesAI & LLM Engineering

Install Tingwu Asr

skills CLI
$ npx skills add cat-xierluo/legal-skills --skill tingwu-asr -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install cat-xierluo/legal-skills tingwu-asr --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/cat-xierluo/legal-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tingwu-asr .claude/skills/tingwu-asr && rm -rf skills-src

Use ~/.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/

Facts

Skill name
tingwu-asr
GitHub stars
720
Token cost
~1.7k tokens
SKILL.md length
381 words
Files
26 (incl. scripts, references)
Skills in repo
62
Repo updated
First seen
Licence
MIT

At a glance

使用阿里云通义听悟进行云端音频/视频转录。本技能应在用户需要云端语音转文字、长音频转录、本地 ASR 不可用或需要更高精度时使用。不适用于无网络环境或需要完全离线的场景。

  • Works in 7 steps: 检查登录状态 → 执行转录 → 输出说明 → …
  • Tasks that involve Speech recognition and synthesis
  • SKILL.md covers 功能, 依赖, 首次使用:登录(首选:内置 Playwright 脚本) and 每日签到(领取免费额度), plus 4 more sections
  • Runs Python scripts from its folder; calls python3, pip3 and bash; reaches tingwu.aliyun.com and xiaoyuzhoufm.com

What it does

Tingwu Asr is an agent skill from cat-xierluo/legal-skills. 使用阿里云通义听悟进行云端音频/视频转录。本技能应在用户需要云端语音转文字、长音频转录、本地 ASR 不可用或需要更高精度时使用。不适用于无网络环境或需要完全离线的场景。

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 29 other files, including scripts and reference files (for example `CHANGELOG.md`, `config/cookie.example.json` and `references/api-capture.md`).

It sits in AI & LLM Engineering, covering Speech recognition and synthesis. It works with Playwright. The licence is MIT.

When your agent uses it

  • Tasks that involve Speech recognition and synthesis

Example prompts

  • “/tingwu-asr”

Requirements

  • Python 3

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. 检查登录状态
  2. 执行转录
  3. 输出说明
  4. 生成 AI 总结(复用 local-asr)
  5. 异步提交
  6. 后台监控(按 Agent 运行时选择)
  7. 手动查询

What it can do on your machine

Read from SKILL.md and the folder at commit db2c58c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    Ships 7 files in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • pip3
    • bash
    • playwright

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • tingwu.aliyun.com
    • xiaoyuzhoufm.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tingwu Asr loads about 1.7k tokens when it runs, and up to ~2.8k if it reads all its reference files. Until then it costs about 24 tokens; SKILL.md has 381 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~24
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.8k

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.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:42
    - 凭证从 `config/.env` 读取(从 `config/.env.example` 复制填写)
  • NoteMentions a .env fileSKILL.md:58
    账号密码可预配置在 `config/.env` 文件中(从 `config/.env.example` 复制)。
  • NoteMentions a .env fileSKILL.md:153
    .env                ← 账号密码凭证(gitignore,不提交)

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.

SKILL.md

The full file from cat-xierluo/legal-skills at commit db2c58c, republished under its MIT licence (© cat-xierluo). 381 words, ~1,732 tokens.

Download SKILL.mdSave it as .claude/skills/tingwu-asr/SKILL.md (or your agent's skills folder). This skill also uses 25 other files; get the full folder from GitHub.
name
tingwu-asr
description
使用阿里云通义听悟进行云端音频/视频转录。本技能应在用户需要云端语音转文字、长音频转录、本地 ASR 不可用或需要更高精度时使用。不适用于无网络环境或需要完全离线的场景。
homepage
https://github.com/cat-xierluo/legal-skills
author
杨卫薪律师(微信ywxlaw)
version
0.4.7
license
MIT

通义听悟云端转录 (tingwu-asr)

通过逆向封装通义听悟网页端内部 REST API,实现云端音频/视频文件转录,输出与 local-asr 兼容的 Markdown 格式。

功能

  • 上传本地音频/视频文件到阿里云 OSS
  • 云端转录,支持说话人分离(单人/2人/多人)
  • 支持中文、英文、日文、粤语、中英文混合
  • 输出 local-asr 兼容的 Markdown,可直接用 summary.py 注入 AI 总结

依赖

  • Python 3.8+
  • requests (必须) — HTTP 请求
  • oss2 (必须) — 阿里云 OSS SDK(STS 直传)
  • playwright (登录时) — 内置登录脚本 login_pw.py 使用(pip3 install playwright && playwright install chromium)

安装:

bash
pip3 install -r skills/tingwu-asr/config/requirements.txt

首次使用:登录(首选:内置 Playwright 脚本)

方式一(推荐):skill 内置 login_pw.py,一条命令完成"开浏览器 → 自动填凭证 → 等 登录 → cookie 落盘":

bash
python3 skills/tingwu-asr/scripts/login_pw.py
  • 凭证从 config/.env 读取(从 config/.env.example 复制填写)
  • 浏览器以可见窗口打开;若出现滑块/验证码,人工在窗口内完成即可,脚本自动轮询等待
  • 脚本通过 context.cookies() 取 cookie(含 HttpOnly 的 login_aliyunid_ticket), 直接写入 config/cookies.json,cookie 值不经过 stdout/对话记录
  • 完成后可用 check_auth.py 验证登录态

方式二(备用):Agent 用 MCP Playwright 浏览器工具手工流程:

  1. 用 MCP Playwright 打开 https://tingwu.aliyun.com/home
  2. 如果跳转到登录页,用账号密码或扫码登录
  3. 登录成功后,将提取的 cookie 保存到文件(注意 document.cookie 拿不到 HttpOnly cookie,仅作兜底):
    bash
    python3 skills/tingwu-asr/scripts/login.py --save-cookies '{"cna":"xxx",...}'

账号密码可预配置在 config/.env 文件中(从 config/.env.example 复制)。

每日签到(领取免费额度)

每天登录听悟网页可领取 2 小时免费转录额度。Agent 签到流程:

  1. 运行内置登录脚本(会打开 https://tingwu.aliyun.com/home 触发每日额度并保存 Cookie):
    bash
    python3 skills/tingwu-asr/scripts/login_pw.py
  2. 运行检查脚本确认状态:
    bash
    python3 skills/tingwu-asr/scripts/daily_checkin.py

可在 OpenClaw 中配置定时任务,让 Agent 每天自动执行此流程。

Agent 工作流

当用户要求转录音频/视频文件时,执行以下步骤:

1. 检查登录状态
bash
python3 skills/tingwu-asr/scripts/check_auth.py

如果返回"无效",先运行 login.py。

2. 执行转录
bash
# 直接给链接(自动 yt-dlp 下载,默认多人分离):小宇宙/YouTube/B站等
python3 skills/tingwu-asr/scripts/transcribe.py "https://www.xiaoyuzhoufm.com/episode/xxx"

# 单文件转录(默认多人分离)
python3 skills/tingwu-asr/scripts/transcribe.py /path/to/audio.mp3 --lang cn

# 多文件并行转录(自动保存到文件所在目录 + archive 目录)
python3 skills/tingwu-asr/scripts/transcribe.py /path/to/audio1.mp3 /path/to/audio2.mp3 /path/to/video.mp4

# 批量转录目录下所有文件(并行)
python3 skills/tingwu-asr/scripts/transcribe.py /path/to/media_folder/ --batch

# 指定并行数(默认3)
python3 skills/tingwu-asr/scripts/transcribe.py /path/to/audio1.mp3 /path/to/audio2.mp3 --parallel 5

参数说明:

  • paths 音频/视频文件路径或链接(http(s) 开头自动用 yt-dlp 下载到临时目录;支持小宇宙/YouTube/B站等;支持多个混用)
  • --lang cn 语言: cn(中文,默认) / en(英文) / ja(日文) / cant(粤语) / cn_en(中英混合)
  • --speakers 说话人分离: 2=区分发言人(默认,实测唯一有效值,分 2 人) / 0=不区分 / 1=单人。注:3 与 4 实测均无效(不分离),原"4=多人"为误注
  • --batch 批量转录目录下所有文件
  • --parallel N 并行转录的最大文件数 (默认: 3)
  • --force 强制重新上传,即使该文件已有转录结果(默认会跳过已转录的文件)
  • -o output.md 指定输出路径(单文件模式)
  • --no-archive 不保存归档
  • --no-lab 不获取智能分析(关键词/议程/重点等)
  • --ppt 下载 PPT 幻灯片图片并嵌入 Markdown(仅视频有效)

关于「给链接转写」与说话人分离(重要设计取舍):传入链接时,skill 走「yt-dlp 下载 → 本地上传」路径,以保证说话人分离生效。听悟网页端的「播客链接转写」(底层 net_source 网络源通道)虽能省本地带宽,但实测其「区分发言人」选项不生效(提交时 roleSplitNum 被强制为 0,不做分离)。此外经实测,听悟 roleSplitNum 仅 2 为有效分离值(分 2 人),0/1/3/4 均不分离(原 skill 注释"4=多人"为误注,已更正)。故 skill 默认 --speakers 2 走本地上传通道,换取可靠的 2 人分离,代价是下载+上传的带宽。如只需纯文字稿不在乎分离,可自行调用听悟网页端播客链接转写。

3. 输出说明

转录结果会同时保存到两个位置:

  1. 源文件所在目录:例如 /path/to/audio.mp3 → /path/to/audio.md
  2. archive 归档目录:archive/YYYYMMDD_HHMMSS_audio/audio.md

这样做的好处是:

  • 源文件目录方便直接访问
  • archive 目录便于集中管理和备份

PPT 幻灯片: 视频文件会自动提取 PPT 幻灯片,图片保存在 {文件名}_slides/ 子目录中(每个文件独立目录,避免同目录下多视频冲突)。

Show full SKILL.md (161 more words)Show less
3. 生成 AI 总结(复用 local-asr)

转录完成后,复用 local-asr 的 summary 模块:

bash
python3 skills/local-asr/scripts/summary.py inject transcript.md summary.json
python3 skills/local-asr/scripts/summary.py verify transcript.md

文件结构

skills/tingwu-asr/
  SKILL.md              ← 本文件
  scripts/
    tingwu.py           ← 核心 API 客户端
    transcribe.py       ← CLI 入口
    format_output.py    ← 听悟 JSON → Markdown 转换
    login.py            ← Cookie 保存工具
    daily_checkin.py    ← 额度检查 + 记录
    check_auth.py       ← 认证检查
  config/
    .env                ← 账号密码凭证(gitignore,不提交)
    .env.example        ← 账号密码模板
    cookies.json        ← 登录 Cookie(gitignore,不提交)
    cookie.example.json ← Cookie 文件模板
    quota_history.jsonl ← 额度变更记录(gitignore,不提交)
    requirements.txt    ← Python 依赖
  references/           ← API 文档和决策记录
  archive/              ← 转录结果归档

异步转录模式(推荐用于长视频)

对于 1 小时以上的长视频,转录可能需要 20-30 分钟。使用异步模式上传后立即返回,后台自动轮询。

1. 异步提交
bash
python3 skills/tingwu-asr/scripts/transcribe.py /path/to/video.mp4 --async --speakers 2

上传完成后立即返回任务 ID,任务信息保存到 config/pending_tasks.json。

2. 后台监控(按 Agent 运行时选择)

监控进程的生命周期是关键差异点:Agent 的后台进程普遍随会话结束被回收(Hermes 会话切换界面、Claude Code 会话退出同理)。监控一死,Agent 就收不到"转录完成"信号,长任务静默搁浅。因此分两档:

档位 A — 会话无关监控(推荐,长任务首选):让监控完全脱离 Agent 会话,进度写日志文件,Agent 回来只读状态、不持有进程。

bash
# Claude Code / 任意运行时:nohup 脱离会话,日志落盘
nohup python3 skills/tingwu-asr/scripts/poll_tasks.py --monitor --timeout 7200 --interval 120 \
  >> /tmp/tingwu_monitor.log 2>&1 &

# 单任务高频盯梢(含 macOS 原生通知):watch_active.sh 本身就是会话无关的
nohup bash skills/tingwu-asr/scripts/watch_active.sh <task_id> >> /tmp/tingwu_watch.log 2>&1 &

Agent 恢复会话后按此顺序接管(不重新提交任务):

  1. cat skills/tingwu-asr/config/pending_tasks.json — 非空即有未完任务,拿 trans_id
  2. python3 skills/tingwu-asr/scripts/poll_tasks.py(一次性)— 已完成则当场触发 finish_task 收尾(下载 PPT/生成 Markdown/归档),未完成则打印状态与预计剩余时间
  3. finish_task 收尾可能耗时数分钟(185 张幻灯片下载+压缩实测约 3 分钟):用后台运行且不要设短超时,或改用 watch_active.sh 接管
  4. 需要持续监控再启动档位 A/B,重跑安全幂等(flock 防并发重复归档)

档位 B — Agent 托管后台进程:适合 Agent 会话确定存续的短等待。

  • Claude Code:Bash 工具 run_in_background: true + timeout: 600000(必须 10 分钟,默认 2 分钟会掐断 finish_task)
  • Hermes:terminal(background=true) 提交 + process_manage 轮询等待;会话切界面/退出后进程会被回收,此时回到恢复流程第 1 步

无论哪档,重跑 poll_tasks.py 都是安全的:任务状态以云端为准,pending_tasks.json 有 flock 互斥,不会重复转录、不会重复归档。进程丢失≠任务丢失。

3. 手动查询
bash
# 检查所有待处理任务的状态(已完成会当场收尾并打印输出路径)
python3 skills/tingwu-asr/scripts/poll_tasks.py

# 阻塞式监控
python3 skills/tingwu-asr/scripts/poll_tasks.py --monitor

注意事项

  • Cookie 会过期,过期后需重新运行 login.py
  • 网页端免费额度有限,大文件或高频使用可能触发风控
  • 支持格式: mp3/wav/m4a/wma/aac/ogg/amr/flac/aiff/mp4/wmv/mov/mkv/webm/avi 等
  • 音频最大 500M,视频最大 6G,单文件最长 6 小时
  • 代理环境下 OSS 上传已自动直连(v0.4.6):shell 常驻 HTTP_PROXY/HTTPS_PROXY(如 Clash 系)时, oss2 分片上传曾走代理被掐断长连接(实测 771MB 视频在 50% 处 ProxyError: Cannot connect to proxy)。现上传 session 默认 trust_env=False 忽略环境代理直连国内 OSS 节点;确需经代理出海时设 TINGWU_OSS_USE_PROXY=1 恢复。 注意:yt-dlp 下载链接(小宇宙/YouTube/B站)不受此改动影响,海外源仍按环境代理走
  • macOS Apple Silicon 上 cryptography<=41 的 _rust.abi3.so 在 OpenSSL CPU 探测 (_armv8_sve_probe)时会死循环挂起,症状是任何 import oss2 的脚本无输出卡死。 已在 tingwu.py 入口自动设置 OPENSSL_armcap=0 绕过;若仍遇到,运行前手动 export OPENSSL_armcap=0,或升级 cryptography>=42。

© cat-xierluo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 25 other files (scripts, references) in skills/tingwu-asr of cat-xierluo/legal-skills.

  • SKILL.md
  • .gitignore
  • CHANGELOG.md
  • LICENSE.txt
  • archive/.gitkeep
  • config/.env.example
  • config/.gitkeep
  • config/cookie.example.json
  • config/requirements.txt
  • references/api-capture.md
  • scripts/browser_auth.py
  • scripts/check_auth.py
  • scripts/daily_checkin.py
  • scripts/fix_archive_slides.py
  • scripts/format_output.py
  • scripts/login.py
  • scripts/login_pw.py
  • … and 9 more

Open the folder on GitHubat commit db2c58c

Compare with similar skills

Tingwu Asr 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.

Tingwu Asr compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tingwu Asr this skillcat-xierluo/legal-skills720—~1.7kAutomated safety check: NotesMIT
Render Myth Vs Factgooseworks-ai/goose-skills1.2k—~2.2kAutomated safety check: PassMIT
TriageTalAter/annyang6.8k—~810Automated safety check: NotesMIT
Yichen Asrmcncarl/yichen-skills4.4k—~780Automated safety check: PassCustom licence
Dingtalk MinutesDingTalk-Real-AI/dingtalk-workspace-cli3.2k—~2.3kAutomated safety check: PassApache-2.0
Youtube FetcherJimmySadek/youtube-fetcher-to-markdown485—~3.1kAutomated safety check: PassMIT

Similar skills

  • Render Myth Vs Fact

    gooseworks-ai/goose-skills

    Assemble a myth-vs-fact kinetic-typography explainer video ad (≈29.5s, 9:16) from N myth/fact pairs + hook / turn / punch copy + palette + a brand end-card PNG + a VO track — a hook, 3 red-strike…

    1.2k GitHub stars~2.2k tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • Triage

    TalAter/annyang

    Triage and close GitHub issues on TalAter/annyang. An agent skill from TalAter/annyang.

    6.8k GitHub stars~810 tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check: notes
  • Yichen Asr

    mcncarl/yichen-skills

    逸尘自用的统一音视频转写入口,在 StepFun Step ASR 与火山引擎豆包 ASR 之间按输出需求、安全边界和可用状态路由。用于本地音频或视频的纯文本转写、时间戳、SRT 字幕、口播粗剪,以及转写前体检;用户明确指定服务商时不得静默切换。Use when a local audio or video file needs transcription and the correct…

    4.4k GitHub stars~780 tokensUpdated 7 days ago
    AI & LLM EngineeringAuto-check passed
  • Dingtalk Minutes

    DingTalk-Real-AI/dingtalk-workspace-cli

    钉钉 AI 听记。Use when 查询或修改听记摘要、完整逐字稿、关键词、标签、行动项、录音、上传、思维导图、发言人洞察、ASR 热词/识别词配置或分享权限。写文档走 dingtalk-doc;建待办走 dingtalk-todo;日程走 dingtalk-calendar。命令前缀:dws minutes。

    3.2k GitHub stars~2.3k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed
  • Youtube Fetcher

    JimmySadek/youtube-fetcher-to-markdown

    Retrieve transcripts from YouTube, Instagram, TikTok, X, Vimeo and other video sites, summarize or analyze what was said (and shown on screen), or save an Obsidian-ready Markdown knowledge-base note…

    485 GitHub stars~3.1k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed
  • Yichen Web Research

    mcncarl/yichen-skills

    逸尘自用的互联网研究总入口。用于跨平台且跨阶段、用户尚未确定工具,或明确要求对公司、产品、人物、技术、行业和领域做横纵分析、发展史加现状对比或有来源约束的系统深度研究;先生成有截止日期和证据闸门的计划,再把搜索发现、候选核验、有限归档、按需转写和证据综合路由到…

    4.4k GitHub stars~1.9k tokensUpdated 7 days ago
    AI & LLM EngineeringAuto-check passed

More from cat-xierluo/legal-skills

All 62 skills in this repo
  • Elements-Style Complaint Generator

    cat-xierluo/legal-skills

    Converts a lawyer's ordinary complaint or a described case into the Supreme People's Court's elements-style Word template, with layout checks on the result.

    721 GitHub stars~2.6k tokensUpdated yesterday
    Auto-check: notes
  • Lecture Performance Review

    cat-xierluo/legal-skills

    Analyzes raw lecture transcripts for verbal tics, pacing, time use and promise follow-through, with optional slide-by-slide comparison and cross-session tracking.

    721 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check passed
  • De-AI Polish for Chinese Articles

    cat-xierluo/legal-skills

    Detects and rewrites machine-sounding patterns in the body text of Chinese articles while keeping the author's facts, headings and legal terms intact.

    721 GitHub stars~2.9k tokensUpdated yesterday
    Auto-check passed
  • GitHub Star Manager

    cat-xierluo/legal-skills

    Finds GitHub projects mentioned in articles or screenshots and stars them, tracks updates to your starred repos, and builds an HTML dashboard to browse them.

    721 GitHub stars~2k tokensUpdated yesterday
    Auto-check: notes
  • Legal Harness Initializer

    cat-xierluo/legal-skills

    Sets up or incrementally updates AGENTS.md and CLAUDE.md for legal professionals, with a minimal safety baseline and a check that a new session loads and follows the rules.

    721 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed
  • Moot Court Simulation Builder

    cat-xierluo/legal-skills

    Chinese-language skill that organizes a case file into a multi-role mock trial with judge, parties and clerk, producing a transcript, issue review and a to-strengthen list.

    721 GitHub stars~1.4k tokensUpdated yesterday
    Auto-check passed

Works with

Questions about Tingwu Asr

What does Tingwu Asr do?

使用阿里云通义听悟进行云端音频/视频转录。本技能应在用户需要云端语音转文字、长音频转录、本地 ASR 不可用或需要更高精度时使用。不适用于无网络环境或需要完全离线的场景。. Tingwu Asr is an agent skill from cat-xierluo/legal-skills.

When should I use Tingwu Asr?

Tingwu Asr fits situations like: tasks that involve Speech recognition and synthesis.

How do I install Tingwu Asr in Claude Code?

Run `npx skills add cat-xierluo/legal-skills --skill tingwu-asr -a claude-code`. Or copy the skill folder (skills/tingwu-asr in cat-xierluo/legal-skills) into .claude/skills/tingwu-asr in your project. Claude Code loads it when a task matches its description.

How do I install Tingwu Asr in Codex?

Run `npx skills add cat-xierluo/legal-skills --skill tingwu-asr -a codex`. Or copy the skill folder (skills/tingwu-asr in cat-xierluo/legal-skills) into .agents/skills/tingwu-asr in your project. Codex loads it when a task matches its description.

Can I use Tingwu Asr in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cat-xierluo/legal-skills --skill tingwu-asr -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tingwu-asr, .gemini/skills/tingwu-asr, .github/skills/tingwu-asr and .opencode/skills/tingwu-asr in your project.

What does Tingwu Asr need to run?

Going by SKILL.md and its folder, Tingwu Asr needs Python for the scripts in its folder and the command-line tools its instructions call (python3, pip3, bash and playwright). Our summary lists: Python 3.

Does Tingwu Asr access the network?

SKILL.md names 2 domains. In commands or code: tingwu.aliyun.com and xiaoyuzhoufm.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Tingwu Asr safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), 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.

What licence does Tingwu Asr use?

Tingwu Asr is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Tingwu Asr use?

About 1.7k tokens (SKILL.md is roughly 6.9k 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 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Tingwu Asr?

Skills that share tags, products or a category with Tingwu Asr: Render Myth Vs Fact (gooseworks-ai/goose-skills, 1.2k stars), Triage (TalAter/annyang, 6.8k stars), Yichen Asr (mcncarl/yichen-skills, 4.4k stars) and Dingtalk Minutes (DingTalk-Real-AI/dingtalk-workspace-cli, 3.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tingwu Asr?

cat-xierluo (a GitHub user) maintains it in cat-xierluo/legal-skills, which has 720 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on October 10, 2026.

Source: cat-xierluo/legal-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.