Agent skill

Language Tutor

A foreign language learning full pipeline. An agent skill from revfactory/harness-100.

Apache-2.0Auto-check passedEducation

Install Language Tutor

skills CLI

$ npx skills add revfactory/harness-100 --skill language-tutor -a claude-code

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

GitHub CLI

$ gh skill install revfactory/harness-100 language-tutor --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/revfactory/harness-100.git skills-src && mkdir -p .claude/skills && cp -r skills-src/en/56-language-tutor/.claude/skills/language-tutor .claude/skills/language-tutor && 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/

Paste into Claude Code

Install the "language-tutor" agent skill from https://github.com/revfactory/harness-100/tree/main/en/56-language-tutor/.claude/skills/language-tutor into .claude/skills/language-tutor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "language-tutor", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/revfactory/harness-100/tree/main/en/56-language-tutor/.claude/skills/language-tutor

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add revfactory/harness-100 --skill language-tutor -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install revfactory/harness-100 language-tutor --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .agents/skills && cp -r skills-src/en/56-language-tutor/.claude/skills/language-tutor .agents/skills/language-tutor && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "language-tutor" agent skill from https://github.com/revfactory/harness-100/tree/main/en/56-language-tutor/.claude/skills/language-tutor into .agents/skills/language-tutor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "language-tutor", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add revfactory/harness-100 --skill language-tutor -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install revfactory/harness-100 language-tutor --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/en/56-language-tutor/.claude/skills/language-tutor .cursor/skills/language-tutor && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "language-tutor" agent skill from https://github.com/revfactory/harness-100/tree/main/en/56-language-tutor/.claude/skills/language-tutor into .cursor/skills/language-tutor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "language-tutor", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/revfactory/harness-100.git --path en/56-language-tutor/.claude/skills/language-tutor

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add revfactory/harness-100 --skill language-tutor -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install revfactory/harness-100 language-tutor --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/en/56-language-tutor/.claude/skills/language-tutor .gemini/skills/language-tutor && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "language-tutor" agent skill from https://github.com/revfactory/harness-100/tree/main/en/56-language-tutor/.claude/skills/language-tutor into .gemini/skills/language-tutor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "language-tutor", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install revfactory/harness-100 language-tutor

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add revfactory/harness-100 --skill language-tutor -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .github/skills && cp -r skills-src/en/56-language-tutor/.claude/skills/language-tutor .github/skills/language-tutor && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "language-tutor" agent skill from https://github.com/revfactory/harness-100/tree/main/en/56-language-tutor/.claude/skills/language-tutor into .github/skills/language-tutor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "language-tutor", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add revfactory/harness-100 --skill language-tutor -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install revfactory/harness-100 language-tutor --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/revfactory/harness-100.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/en/56-language-tutor/.claude/skills/language-tutor .opencode/skills/language-tutor && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "language-tutor" agent skill from https://github.com/revfactory/harness-100/tree/main/en/56-language-tutor/.claude/skills/language-tutor into .opencode/skills/language-tutor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "language-tutor", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: language-tutor
GitHub stars: 1.3k
Token cost: ~1.9k tokens
SKILL.md length: 732 words
Files: 1
Skills in repo: 464
Repo updated: Mar 22, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

A foreign language learning full pipeline. An agent skill from revfactory/harness-100.

Works in 3 steps: Preparation (Orchestrator performs… → Team Assembly and Execution → Progress Reporting
Requests like study English
SKILL.md covers Execution Mode, Agent Roster, Workflow and Task-Scale Modes, plus 4 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Language Tutor is an agent skill from revfactory/harness-100. A foreign language learning full pipeline. An agent team collaborates to provide level testing, curriculum design, lesson generation, quizzes, and review management. Use this skill for requests like 'study English', 'learn Japanese', 'learn a foreign language', 'language learning', 'English grammar', 'conversation practice', 'level test', 'vocabulary memorization', 'self-study English', 'beginner Chinese', 'TOEIC preparation', 'English conversation', and other foreign language learning needs. Also supports…

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Education, covering Language learning. The licence is Apache-2.0.

When your agent uses it

Requests like study English
Learn a foreign language
Language learning
English grammar

Example prompts

“study English”
“learn Japanese”
“learn a foreign language”
“/language-tutor”

Workflow steps

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

Preparation (Orchestrator performs directly)
Team Assembly and Execution
Progress Reporting

What it can do on your machine

Read from SKILL.md and the folder at commit 8e8d35c. 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
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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

Language Tutor loads about 1.9k tokens when it runs. Until then it costs about 181 tokens; SKILL.md has 732 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~181
When it runs · the whole SKILL.md, loaded when a task matches: ~1.9k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from revfactory/harness-100 at commit 8e8d35c, republished under its Apache-2.0 licence (© revfactory). 732 words, ~1,898 tokens.

Download SKILL.mdSave it as .claude/skills/language-tutor/SKILL.md (or your agent's skills folder).

name: language-tutor
description: A foreign language learning full pipeline. An agent team collaborates to provide level testing, curriculum design, lesson generation, quizzes, and review management. Use this skill for requests like 'study English', 'learn Japanese', 'learn a foreign language', 'language learning', 'English grammar', 'conversation practice', 'level test', 'vocabulary memorization', 'self-study English', 'beginner Chinese', 'TOEIC preparation', 'English conversation', and other foreign language learning needs. Also supports learning specific skill areas only. However, real-time voice conversation (STT/TTS), native speaker matching, and taking official exams on behalf of the learner are outside the scope of this skill.

Language Tutor — Foreign Language Learning Full Pipeline

An agent team collaborates to deliver level testing, curriculum design, lesson generation, quiz creation, and review management.

Execution Mode

Agent Team — 5 agents communicate directly via SendMessage and cross-verify each other's work.

Agent Roster

Agent	File	Role	Type
level-assessor	`.claude/agents/level-assessor.md`	CEFR-based level diagnosis, skill-area strength/weakness analysis	general-purpose
curriculum-designer	`.claude/agents/curriculum-designer.md`	Customized curriculum, weekly plans, learning strategies	general-purpose
lesson-tutor	`.claude/agents/lesson-tutor.md`	Grammar, vocabulary, conversation, reading, and writing lessons	general-purpose
quiz-master	`.claude/agents/quiz-master.md`	Varied quiz types, difficulty adjustment, grading	general-purpose
review-coach	`.claude/agents/review-coach.md`	Spaced repetition, weakness reinforcement, progress tracking, motivation	general-purpose

Workflow

Phase 1: Preparation (Orchestrator performs directly)

Extract from user input:
- Target language: Which foreign language the learner wants to study
- Native language: The learner's native language (default: English)
- Learning experience: Prior study experience and self-assessed current level
- Learning goal: Travel / work / exam / immigration / hobby, etc.
- Available time: Weekly hours available for study
- Existing materials (optional): Prior study materials, exam scores, etc.
Create a _workspace/ directory at the project root
Organize the input and save it to _workspace/00_input.md

Phase 2: Team Assembly and Execution

Order	Task	Agent	Depends On	Deliverable
1	Level assessment	level-assessor	None	`_workspace/01_level_assessment.md`
2	Curriculum design	curriculum-designer	Task 1	`_workspace/02_curriculum.md`
3	First lesson	lesson-tutor	Task 2	`_workspace/03_lesson_01.md`
4	First quiz	quiz-master	Task 3	`_workspace/04_quiz_01.md`
5	Review plan	review-coach	Tasks 2, 3, 4	`_workspace/05_review_plan.md`

Inter-agent communication flow:

level-assessor completes -> sends skill-area levels, strengths/weaknesses, learning goals, and available time to curriculum-designer
curriculum-designer completes -> sends Week 1 topics, grammar, and vocabulary to lesson-tutor; sends milestone criteria to quiz-master
lesson-tutor completes -> sends key learning items to quiz-master; sends learning items to review-coach
quiz-master -> sends results to review-coach -> weakness reinforcement + review schedule generated

Continuous learning cycle: Lessons, quizzes, and reviews run iteratively. When the user requests more lessons:

lesson-tutor generates the next lesson (03_lesson_02.md, 03_lesson_03.md, ...)
quiz-master creates a quiz for that lesson (04_quiz_02.md, ...)
review-coach updates the review plan + generates a progress report

Phase 3: Progress Reporting

review-coach periodically generates progress reports:

_workspace/06_progress_report.md — Overall progress, skill-area growth, quiz trends, study patterns

Task-Scale Modes

User Request Pattern	Execution Mode	Agents Deployed
"I want to start learning English"	Full Pipeline	All 5 agents
"Test my English level"	Diagnostic Mode	level-assessor only
"Give me an English grammar lesson"	Lesson Mode	lesson-tutor (+ level-assessor if needed)
"Quiz me on this unit"	Quiz Mode	quiz-master only
"Create a review plan"	Review Mode	review-coach only
"Create a TOEIC prep curriculum"	Exam-Specific Mode	level-assessor + curriculum-designer + quiz-master

Automatic level detection: If the user does not know their level, provisionally estimate it from the expressions they use in conversation and suggest a diagnostic test.

Show full SKILL.md (303 more words)Show less

Data Transfer Protocol

Strategy	Method	Purpose
File-based	`_workspace/` directory	Store and share major deliverables
Message-based	SendMessage	Real-time key information exchange, difficulty adjustment requests
Task-based	TaskCreate/TaskUpdate	Track progress, manage learning cycles

File naming convention: {order}_{deliverable}_{number}.{extension}

Error Handling

Error Type	Strategy
Target language not specified	Default to English, but ask for confirmation
Level diagnosis refused	Set provisional level via self-assessment; adjust in first lesson
Agent failure	Retry once -> proceed without that deliverable if still failing
Difficulty mismatch	Adjust immediately based on learner feedback; update curriculum
Limited support for rare languages	Inform the user of supported range; focus on major languages (English, Japanese, Chinese, Spanish, French, German)

Test Scenarios

Normal Flow

Prompt: "I want to get better at English speaking. I travel abroad often for work, and I can study about 5 hours per week." Expected Results:

Level assessment: Adaptive diagnostic test administered; CEFR level determined per skill area
Curriculum: 12-week business English plan focused on conversation + emails + presentations
First lesson: Business greetings and self-introduction patterns + 20 key vocabulary items
Quiz: 15 items based on Lesson 1 content
Review plan: Spaced repetition schedule + weakness reinforcement activities

Existing File Flow

Prompt: "Build a weakness-focused curriculum based on this TOEIC score report" + score report attached Expected Results:

Score report copied as reference material in _workspace/01_level_assessment.md
level-assessor determines skill-area levels based on the score report (streamlined diagnostic test)
curriculum-designer + lesson-tutor + quiz-master + review-coach deployed

Error Flow

Prompt: "Maybe I will try learning a language" Expected Results:

Target language not specified -> suggest English by default + offer alternatives
Learning goal unclear -> propose 3 goals (travel / work / hobby) and ask user to choose
After selection, execute full pipeline

Agent Extension Skills

Extension skills that enhance each agent's domain expertise:

Agent	Extension Skill	Role
review-coach	`spaced-repetition`	SM-2 algorithm, Ebbinghaus forgetting curve, review session design
level-assessor	`cefr-assessment`	CEFR 6-level descriptors, adaptive diagnostic tests, CEFR-to-exam mapping

Files

Just SKILL.md in en/56-language-tutor/.claude/skills/language-tutor of revfactory/harness-100.

Open the folder on GitHubat commit 8e8d35c

Compare with similar skills

Language Tutor 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.

Language Tutor compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Language Tutor this skillrevfactory/harness-100	1.3k	—	~1.9k	Automated safety check: Pass	Apache-2.0	6 mo ago
Pronunciation Specialistbitwize-music-studio/claude-ai-music-skills	536	1 repos	~2.3k	Automated safety check: Pass	CC0-1.0	14 days ago
Fluent Progressm98/fluent	420	—	~1.5k	Automated safety check: Notes	MIT	3 mo ago
Fluent Sm2 Calculatorm98/fluent	420	—	~1.2k	Automated safety check: Pass	MIT	3 mo ago
Duolingo Playpockebot/openpocket	847	—	~1.1k	Automated safety check: Pass	MIT	3 mo ago
Study Companion Enmingchen666/Reviva	236	—	~5.7k	Automated safety check: Pass	None	16 days ago

Similar skills

Pronunciation Specialist
bitwize-music-studio/claude-ai-music-skills
Scans lyrics for pronunciation risks and prevents Suno mispronunciations.
536 GitHub starsUsed in 1 repo~2.3k tokens
EducationAuto-check passed
Fluent Progress
m98/fluent
Show the learner's language learning progress, statistics, mastery levels, streak, and achievements.
420 GitHub stars~1.5k tokensUpdated 3 mo ago
EducationAuto-check: notes
Fluent Sm2 Calculator
m98/fluent
SM-2 spaced-repetition algorithm reference for the Fluent language learning system.
420 GitHub stars~1.2k tokensUpdated 3 mo ago
EducationAuto-check passed
Duolingo Play
pockebot/openpocket
Help users complete Duolingo language lessons. An agent skill from pockebot/openpocket.
847 GitHub stars~1.1k tokensUpdated 3 mo ago
EducationAuto-check passed
Study Companion En
mingchen666/Reviva
General study companion for learning, review, exam prep, exam-point analysis, syllabus/exam-outline interpretation, finals speedrun teaching, concept explanation, problem solving, homework coaching…
236 GitHub stars~5.7k tokensUpdated 16 days ago
EducationAuto-check passed
Fluent Learn
m98/fluent
Main adaptive language-learning session that mixes skills (writing, speaking, vocabulary, reading) and exercise types based on the learner's current level, weak patterns, and due reviews.
420 GitHub stars~1.8k tokensUpdated 3 mo ago
EducationAuto-check: notes

Questions about Language Tutor

What does Language Tutor do?

A foreign language learning full pipeline. An agent skill from revfactory/harness-100. Language Tutor is an agent skill from revfactory/harness-100. A foreign language learning full pipeline.

When should I use Language Tutor?

Language Tutor fits situations like: requests like study English; learn a foreign language; language learning; english grammar.

How do I install Language Tutor in Claude Code?

Run `npx skills add revfactory/harness-100 --skill language-tutor -a claude-code`. Or copy the skill folder (en/56-language-tutor/.claude/skills/language-tutor in revfactory/harness-100) into .claude/skills/language-tutor in your project. Claude Code loads it when a task matches its description.

How do I install Language Tutor in Codex?

Run `npx skills add revfactory/harness-100 --skill language-tutor -a codex`. Or copy the skill folder (en/56-language-tutor/.claude/skills/language-tutor in revfactory/harness-100) into .agents/skills/language-tutor in your project. Codex loads it when a task matches its description.

Can I use Language Tutor 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 revfactory/harness-100 --skill language-tutor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/language-tutor, .gemini/skills/language-tutor, .github/skills/language-tutor and .opencode/skills/language-tutor in your project.

What does Language Tutor need to run?

SKILL.md names no scripts, command-line tools or credentials: Language Tutor is instructions for the agent only.

Does Language Tutor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Language Tutor 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. Review the folder before installing.

What licence does Language Tutor use?

Language Tutor is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Language Tutor use?

About 1.9k tokens (SKILL.md is roughly 7.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Language Tutor?

Skills that share tags, products or a category with Language Tutor: Pronunciation Specialist (bitwize-music-studio/claude-ai-music-skills, 536 stars), Fluent Progress (m98/fluent, 420 stars), Fluent Sm2 Calculator (m98/fluent, 420 stars) and Duolingo Play (pockebot/openpocket, 847 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Language Tutor?

revfactory (a GitHub user) maintains it in revfactory/harness-100, which has 1,290 GitHub stars. The repository holds 464 skills in this directory. The repository was last updated on March 22, 2026.

Source: revfactory/harness-100 on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Language Tutor

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Language Tutor — Foreign Language Learning Full Pipeline

Execution Mode

Agent Roster

Workflow

Phase 1: Preparation (Orchestrator performs directly)

Phase 2: Team Assembly and Execution

Phase 3: Progress Reporting

Task-Scale Modes

Data Transfer Protocol

Error Handling

Test Scenarios

Normal Flow

Existing File Flow

Error Flow

Agent Extension Skills

Files

Compare with similar skills

Similar skills

More from revfactory/harness-100

Related

Questions about Language Tutor