Agent skill

Yichen Asr

by mcncarl in 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…

Custom licenceAuto-check passedAI & LLM Engineering

Install Yichen Asr

skills CLI
$ npx skills add mcncarl/yichen-skills --skill yichen-asr -a claude-code

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

GitHub CLI
$ gh skill install mcncarl/yichen-skills yichen-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/mcncarl/yichen-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/yichen-asr .claude/skills/yichen-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
yichen-asr
GitHub stars
4.4k
Token cost
~780 tokens
SKILL.md length
143 words
Files
6 (incl. scripts, references)
Skills in repo
19
Repo updated
First seen
Licence
Custom licence

At a glance

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…

  • Works in 5 steps: 用户指定服务商:失败后只报告该服务商的错误和恢复路径,不自动换服务商。 → 自动路由且尚未提交:若默认后端缺少脚本、密钥或必要能力,可改用满足输出要求的另一后… → 自动路由且已经提交:不得跨服务商重提;优先用 request ID、缓存或… → …
  • Video file needs transcription and the correct ASR backend is unclear
  • SKILL.md covers 路由规则, 执行前体检, Step ASR and 豆包 ASR, plus 3 more sections
  • Runs Python scripts from its folder; calls python3; needs VOLC_ASR_TRIAL_TOKEN and VOLC_ASR_PAID_TOKEN

What it does

Yichen Asr is an agent skill from 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 ASR backend is unclear, or when the user explicitly invokes $yichen-asr.

Its SKILL.md is about 780 tokens, which your agent loads only when the skill is triggered. The skill folder holds 9 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/providers.md` and `scripts/asr_doctor.py`).

It sits in AI & LLM Engineering, covering Speech recognition and synthesis and Transcription.

When your agent uses it

  • Video file needs transcription and the correct ASR backend is unclear
  • The user explicitly invokes $yichen-asr

Example prompts

  • “/yichen-asr”

Requirements

  • Python 3
  • A credential in VOLC_ASR_TRIAL_TOKEN
  • A credential in VOLC_ASR_PAID_TOKEN

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 用户指定服务商:失败后只报告该服务商的错误和恢复路径,不自动换服务商。
  2. 自动路由且尚未提交:若默认后端缺少脚本、密钥或必要能力,可改用满足输出要求的另一后端,并明确说明。
  3. 自动路由且已经提交:不得跨服务商重提;优先用 request ID、缓存或 --resume 恢复。
  4. 豆包余额未知:不得说成“余额充足”或“余额不足”。只有费用中心、账单或明确的接口欠费错误可确认。
  5. 精确 SRT 需求不能因豆包不可用而悄悄降级为 Step 的分块 Markdown;应说明能力差异。

What it can do on your machine

Read from SKILL.md and the folder at commit 9bd7898. 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 2 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

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

  • Network

    Links to these hosts (documentation or services it may open):

    • console.volcengine.com
    • volcengine.com

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • VOLC_ASR_TRIAL_TOKEN
    • VOLC_ASR_PAID_TOKEN

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

Context cost

Yichen Asr loads about 780 tokens when it runs, and up to ~1.2k if it reads all its reference files. Until then it costs about 70 tokens; SKILL.md has 143 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~780
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.2k

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 passed

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); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 143 words (~780 tokens).

“这是一个统一路由层,不是第三套 ASR 引擎。Step ASR 与豆包 ASR 继续作为底层执行器,由本 Skill 负责选择、体检、失败收敛和交接。”

— opening of SKILL.md by mcncarl, Custom licence
name
yichen-asr

Read the full SKILL.md on GitHub

Files

SKILL.md and 5 other files (scripts, references) in yichen-asr of mcncarl/yichen-skills.

  • SKILL.md
  • agents/openai.yaml
  • references/providers.md
  • scripts/asr_doctor.py
  • scripts/route_asr.py
  • tests/test_contract.py

Open the folder on GitHubat commit 9bd7898

Compare with similar skills

Yichen 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.

Yichen Asr compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Yichen Asr this skillmcncarl/yichen-skills4.4k—~780Automated safety check: PassCustom licence
Youtube FetcherJimmySadek/youtube-fetcher-to-markdown485—~3.1kAutomated safety check: PassMIT
Ax Audiodosco/aithy107—~2.5kAutomated safety check: PassApache-2.0
Stt Integrationrapidaai/voice-ai745—~778Automated safety check: PassCustom licence
Watchoxbshw/watch-skill469—~1.3kAutomated safety check: NotesMIT
Whisper Speech RecognitionOrchestra-Research/AI-Research-SKILLs13k7 repos~1.9kAutomated safety check: NotesMIT

Similar skills

  • 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 2 days ago
    AI & LLM EngineeringAuto-check passed
  • Ax Audio

    dosco/aithy

    This skill helps an LLM generate correct audio code with @ax-llm/ax.

    107 GitHub stars~2.5k tokensUpdated 1 mo ago
    AI & LLM EngineeringAuto-check passed
  • Stt Integration

    rapidaai/voice-ai

    Add or modify speech-to-text providers in assistant-api with transport-aware ingestion (WS/SDK/HTTP), transcript packet correctness, and UI/provider wiring.

    745 GitHub stars~778 tokensUpdated 2 days ago
    AI & LLM EngineeringAuto-check passed
  • Watch

    oxbshw/watch-skill

    Watch any video (URL, stream, or local path) via Watch Skill.

    469 GitHub stars~1.3k tokensUpdated 24 days ago
    AI & LLM EngineeringAuto-check: notes
  • Whisper Speech Recognition

    Orchestra-Research/AI-Research-SKILLs

    Transcribes audio with OpenAI's Whisper: 99 languages, translation to English, language detection, six model sizes and word-level timestamps, from Python or the CLI.

    13k GitHub starsUsed in 7 repos~1.9k tokens
    AI & LLM EngineeringAuto-check: notes
  • Dy Note

    Rimagination/dy-note

    DyNote: systematically and efficiently extract raw Douyin/DY video data and analyze videos, comments, accounts, hashtags, and short-video scenes into evidence-graded learning notes, summaries…

    172 GitHub stars~4.5k tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

More from mcncarl/yichen-skills

All 19 skills in this repo
  • Yichen Mac Wechat Dual Open

    mcncarl/yichen-skills

    Create, inspect, repair, and polish a second WeChat app on macOS by copying WeChat, changing the bundle identifier, ad-hoc re-signing, preparing it for the user to open manually, setting Chinese…

    4.4k GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-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 5 days ago
    Auto-check passed
  • Yichen Wechat Mp Batch Exporter

    mcncarl/yichen-skills

    批量下载微信公众号文章正文、历史文章列表、原创文章筛选、历史计数口径、阅读量、点赞/转发等指标、评论和评论回复。Use when the user asks to batch fetch mp.weixin.qq.com articles, export WeChat public-account history, distinguish publish groups vs expanded…

    4.4k GitHub stars~1.5k tokensUpdated 5 days ago
    Auto-check passed
  • Yichen Wecom Local Vault

    mcncarl/yichen-skills

    Read, decrypt, query, search, and export local WeCom/企业微信 5.x desktop databases on macOS into a private read-only vault.

    4.4k GitHub stars~1.3k tokensUpdated 5 days ago
    Auto-check passed
  • Yichen X Slicer

    mcncarl/yichen-skills

    将公开 X 推文、Quote 或同作者 Thread 转为 1080×1440 图片切片和 MP4;也支持显式 source-only 素材桥接。保留所选原生视频及对应音频,不发布。

    4.4k GitHub stars~2.2k tokensUpdated 5 days ago
    Auto-check passed
  • Yichen Bookmarks Export

    mcncarl/yichen-skills

    在用户当轮明确授权后,只读导出其小红书收藏、抖音收藏或 X/Twitter 书签为本地链接文件;本 Skill 直接完成收藏页滚动、链接提取、去重、数量核验、Field Theory GraphQL-only 导出和抽样验证。用于“导出/备份/同步我的收藏或书签链接”等私人数据导出任务;不得用于公开搜索、收藏内容分析、媒体下载、正文归档、推荐发现或未获当轮授权的私人读取。

    4.4k GitHub stars~1.1k tokensUpdated 5 days ago
    Auto-check passed

Questions about Yichen Asr

What does Yichen Asr do?

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…. Yichen Asr is an agent skill from 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 ASR backend is unclear, or when the user explicitly invokes $yichen-asr.

When should I use Yichen Asr?

Yichen Asr fits situations like: video file needs transcription and the correct ASR backend is unclear; the user explicitly invokes $yichen-asr.

How do I install Yichen Asr in Claude Code?

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

How do I install Yichen Asr in Codex?

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

Can I use Yichen 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 mcncarl/yichen-skills --skill yichen-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/yichen-asr, .gemini/skills/yichen-asr, .github/skills/yichen-asr and .opencode/skills/yichen-asr in your project.

What does Yichen Asr need to run?

Going by SKILL.md and its folder, Yichen Asr needs Python for the scripts in its folder, the command-line tools its instructions call (python3) and credentials named VOLC_ASR_TRIAL_TOKEN and VOLC_ASR_PAID_TOKEN. Our summary lists: Python 3; A credential in VOLC_ASR_TRIAL_TOKEN; A credential in VOLC_ASR_PAID_TOKEN.

Does Yichen Asr access the network?

SKILL.md names 2 domains. As links in the text: console.volcengine.com and volcengine.com. This is read from the text; nothing was executed.

Is Yichen Asr safe to install?

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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Yichen Asr use?

Yichen Asr has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Yichen Asr use?

About 780 tokens (SKILL.md is roughly 3.1k 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 410 tokens, read only when the agent opens those files.

What are the alternatives to Yichen Asr?

Skills that share tags, products or a category with Yichen Asr: Youtube Fetcher (JimmySadek/youtube-fetcher-to-markdown, 485 stars), Ax Audio (dosco/aithy, 107 stars), Stt Integration (rapidaai/voice-ai, 745 stars) and Watch (oxbshw/watch-skill, 469 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Yichen Asr?

mcncarl (a GitHub user) maintains it in mcncarl/yichen-skills, which has 4,352 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 4, 2026.

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