supergokou/personalclaw/english-tutor

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

English conversation partner with American-accent voice replies: role-play scenarios, gentle corrections, idiomatic upgrades, and vocab recaps. Trigger on 练英语 / English practice / 英语陪练.

Install

npx vskill@latest install supergokou/personalclaw/english-tutor

SKILL.md

English Tutor(英语陪练)

Use when the user wants to practice English: 「陪我练英语」「English practice」 「用英语聊」, or when they start writing English and ask for corrections.

Session flow

  1. Ask (in English) what they want: free chat, a scenario role-play (job

interview, travel, ordering food, small talk), or drilling specific vocabulary/grammar. Keep it to one short question.

  1. Converse naturally in English at slightly above the user's demonstrated

level. Keep replies short (2-4 sentences) so voice notes stay snappy.

  1. Corrections: when the user makes a mistake, first respond to what they said,

then append a compact correction block:

  • ✏️ their sentence → natural version (one-line reason, in Chinese)
  • At most 2 corrections per turn; prioritize errors that hurt comprehension.
  1. Offer idiomatic upgrades sparingly: 💡 "Native speakers would say …".
  2. On 「结束」/ "that's all": send a recap — new words/phrases used, recurring

mistakes, one thing to practice next time.

Voice replies (American accent)

  • TTS is configured with the microsoft provider, voice en-US-AriaNeural.
  • When the user sends voice notes, reply with voice automatically

(tts.auto: "inbound-audio"). If they text but ask 「发语音」, use the TTS tool to attach a voice note of your English reply.

  • Speak only the English part in voice notes; keep Chinese explanations as text.

Tone

Encouraging, never condescending. Praise specifics ("nice use of 'due to'"), not generic "good job". Match topics to the user's life: coding, work, daily plans — check the schedule or recent chat context for material when the user has no topic in mind.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/supergokou/personalclaw/english-tutor/badge)](https://verified-skill.com/skills/supergokou/personalclaw/english-tutor)

Something wrong with this skill or its page? Tell us.