Speech Recognition Engineer, Xiulan AI skill by KissMySkills, cover
What's inside the Speech Recognition Engineer, Xiulan AI skill: Model evaluation, Reproducible pipeline, Failure mode notes, Deployment checklist
How the Speech Recognition Engineer, Xiulan AI skill works in three steps: download, drop it into your AI chat, done
The Speech Recognition Engineer, Xiulan AI skill works with Claude, ChatGPT, Gemini and any AI chat, 30-day money-back guarantee

Skill fileClaude Skills for Data & AI Teams

Speech Recognition Engineer AI Skill - Xiulan

Ship speech that works: tune ASR for your domain, measure WER by accent and condition, and hold the latency budget.…

$9· one file, yours to keep

Yours to keep · instant download

All-in-one

Or all of them, $6.99/mo

Xiulan and 2,500+ other specialists, in your AI. Ask for any of them by name.

Subscribe · $6.99/mo

7 days free, then $6.99/mo · cancel anytime

  • Visa
  • Mastercard
  • American Express
  • Apple Pay

30-day money-back · secure checkout by Stripe

Read the opening lines
# Xiulan - Speech & Audio ML Engineer

## Who Xiulan Is
Drop Xiulan into Claude and get a Senior Speech and Audio ML Engineer who owns the
audio modality end to end: from the microphone, the codec and the sample rate,
through voice activity detection and diarization, to a transcript accurate enough
that a business can act on it. She does not start by picking a model. She starts by
building an evaluation set that is stratified by accent, dialect, noise condition
and channel, measuring word error rate inside each stratum, and showing the client
the subgroup their aggregate number was hiding. Every recommendation she makes
arrives attached to a measured before and after on that same set.

Skill file · 239 lines · the first 12 shown

How it works

  1. Buy or subscribeAdd it to your cart for $9 and the file is yours to keep. Or subscribe: every file in the store, $6.99/mo.
  2. Open in your AIDownload the file and add it to Claude (Settings → Capabilities → Skills → Upload) or paste it into a ChatGPT project. Subscribers connect their AI once instead:

    Claude

    Anthropic's AI chat, on the web, desktop and phone · about 3 minutes

    Works on every Claude plan, Free included.

    • Team or Enterprise plan: the workspace owner adds it once in Organization settings, then everyone clicks Connect.
    • Nothing happens when you click Connect? Allow pop-ups for claude.ai and try again.

    On a phone? Set it up once on a computer. It then shows up in the Claude phone app by itself. Email me the link

    After you buy a file
    1. Download your .skill file from the order email or your account.

    2. In Claude, turn on code execution in Settings › Capabilities, then go to Customize › Skills › + › Create skill › Upload a skill.

    3. Start a new chat and ask for the specialist by name.

    Open full guide

  3. Ask by nameStart a chat and ask for Speech Recognition Engineer AI Skill by name. It works like the specialist from the first message.

What's inside

  • xiulan-speech-audio-ml-engineer.skillSkill file · 239 lines · instant download
  • ASR tuning: domain adaptation, custom vocabulary, biasing
  • WER measured by accent, noise condition and speaker, not headline
  • Diarization, speaker ID, VAD and channel separation
  • Streaming pipelines, latency budgets, TTS and consent limits

What your AI will do

See a real example
You ask

Our transcription accuracy looks fine on paper but agents say it is unusable. Find out why.

Your AI answers

Xiulan returns a WER breakdown by accent, noise condition, channel and speaker that exposes what the headline number hid, a preprocessing and channel-separation fix, a domain adaptation and contextual biasing plan with measured gains, a diarization design, a streaming latency budget, and an explicit statement of which user groups are still underserved.

// faq

Questions before you buy

What does the Xiulan skill do?+

Ship speech that works: tune ASR for your domain, measure WER by accent and condition, and hold the latency budget. Load it once into Claude Projects and you get a configured Speech & Audio ML Engineer without re-explaining context at the start of every session. Check every number against a known-good source and an honest holdout before anyone builds a decision on it, and state the uncertainty instead of shipping a single confident point estimate.

How do I install this skill file?+

Download the .skill package (it contains SKILL.md), then, in Claude, turn on code execution in Settings → Capabilities and add it under Customize → Skills → + → Create skill → Upload a skill (in ChatGPT, Gemini or another AI, open it as a .zip and paste SKILL.md into Project instructions or custom instructions), add your own context and start your first session. Works with Claude, ChatGPT, or any AI chat that accepts system prompts.

Which AI tools does this skill work with?+

Works with Claude (recommended), ChatGPT, Gemini, Perplexity and Copilot, and any AI chat that accepts system prompts. Claude Projects gives the best results.

How is this different from using Claude without the Xiulan skill?+

Without a skill file your AI starts every session as a general assistant. With Xiulan loaded it applies Speech & Audio ML Engineer methodology from the first message, with consistent quality every time. Check every number against a known-good source and an honest holdout before anyone builds a decision on it, and state the uncertainty instead of shipping a single confident point estimate.

How do I open it?+

Download your .skill file from the order email or your account. In Claude, turn on code execution in Settings › Capabilities, then go to Customize › Skills › + › Create skill › Upload a skill. Start a new chat and ask for the specialist by name.

Using ChatGPT, Gemini or another AI? See How it works