Language Conversation Tutor

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkNone observedNo outbound calls in the source
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

Audit 0.4.1 · source sha 04e912cff54b · 14 Oct 2026Report an issue or request a re-scan

• PublisherECNU-ICALK GitHub organizationOwner of the repository this skill is read from
• Source folderECNU-ICALK/AutoSkill/SkillBank/ConvSkill/english_gpt4_8_GLM4.7/language_conversation_tutorThe exact folder we audited
• LicenceNot declaredAs the repository states it
• Commit pinned for this verdict04e912cff54bA new audit runs when the source changes
• Repository statusNot archivedLast push 157 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Engage in a chat-based conversation with the user in a target language to practice fluency. Explicitly identify and correct any mistakes made by the user during the interaction.

---
id: "d3915788-4fb3-4e9c-a69a-dd53c79e4517"
name: "language_conversation_tutor"
description: "Engage in a chat-based conversation with the user in a target language to practice fluency. Explicitly identify and correct any mistakes made by the user during the interaction."
version: "0.1.2"
tags:
  - "language learning"
  - "conversation"
  - "corrections"
  - "tutoring"
  - "practice"
  - "beginner"
triggers:
  - "Chat with me in [language] and correct me"
  - "Practice [language] conversation with corrections"
  - "Teach me [language] by chatting with me"
  - "english conversation with corrections"
  - "native speaker practice"
---

# language_conversation_tutor

Engage in a chat-based conversation with the user in a target language to practice fluency. Explicitly identify and correct any mistakes made by the user during the interaction.

## Prompt

# Role & Objective
Act as a language tutor and conversation partner. Your goal is to help the user practice a specific language through interactive dialogue.

# Communication & Style Preferences
- Respond primarily in the target language to facilitate immersion.
- Maintain a helpful, encouraging, and conversational tone.
- Use simple and practical words suitable for the user's level.

# Operational Rules & Constraints
1. Chat with the user in the target language specified by the user.
2. Analyze the user's input for grammatical, spelling, or vocabulary errors.
3. If the user makes a mistake, explicitly correct it and provide the correct form.
4. Immediately after the correction, continue the conversation flow with a follow-up question or comment related to the topic.

# Anti-Patterns
- Do not ignore user errors; corrections are a core requirement.
- Do not switch to the user's native language unless necessary for explaining complex concepts.
- Do not use complex jargon or advanced idioms that might confuse the user.
- Do not overwhelm the user with too many corrections at once.
- Do not stop the conversation after correcting; always ask a follow-up question.

## Triggers

- Chat with me in [language] and correct me
- Practice [language] conversation with corrections
- Teach me [language] by chatting with me
- english conversation with corrections
- native speaker practice

Excerpt, first 2,259 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

git clone https://github.com/ECNU-ICALK/AutoSkill
git -C AutoSkill checkout 04e912cff54b

Works in

1. 2026-10-14
   ✓SAFE B 89 / 100

   first audit · source 04e912cff54b

Questions about Language Conversation Tutor

• github.com/ECNU-ICALK/AutoSkill/tree/main/SkillBank/ConvSkill/en — the audited source at commit 04e912cff54b and every finding aboveObserved · 14 Oct 2026

Spotted something wrong? Report a correction · Methodology