Learn Along
- Updated February 22, 2026
- ohbarye/ccll
Learn-along provides conversational language coaching aimed at intermediate and more advanced learners. It practices and corrects language through dialogue rather than drills. An end user uses it to improve a foreign language by conversing with the agent. It is an end-user education tool rather than a software-engineering skill, so taxonomy fit is approximate.
Key points
- Conversational language coaching
- For intermediate+ learners
Learn Along by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
/plugin marketplace add ohbarye/ccll/plugin install learn-along@ccllAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Last updated | February 22, 2026 |
|---|---|
| Repository | ohbarye/ccll ↗ |
What it does
Conversational language coaching for intermediate-and-above learners.
README.md
ccll - Claude Code Language Learning
A collection of Claude Code plugins for language learning through everyday coding sessions.
Plugins
| Plugin | Purpose |
|---|---|
| learn-along | Conversational language coaching for intermediate+ learners |
Installation
From terminal:
claude plugin marketplace add ohbarye/ccll
claude plugin install learn-along@ccll
From a Claude session:
/plugin marketplace add ohbarye/ccll
/plugin install learn-along@ccll
Learn Along
When activated, a language coaching subagent analyzes each conversational exchange and appends brief coaching notes after Claude's normal response. The coaching focuses on:
- Natural expressions — how native speakers would phrase the same intent in a professional engineering context
- Vocabulary highlights — idiomatic phrases, technical collocations, and register guidance
- Corrections — fixes for genuine errors or unnatural phrasing (not nitpicks)
The coaching is tuned for software engineering communication: PR comments, Slack messages, standups, technical docs, and pair programming dialogue.
Usage
Activate with the slash command:
/learn-along en # Target: English, native: auto-detect
/learn-along from:ja to:en # Explicit native/target
/learn-along off # Deactivate
Once active, every response includes a short coaching section (3-8 lines) after a --- separator. Your technical workflow is never interrupted — coaching is always appended after the full technical response.
Example
If you write in Japanese during a coding session:
このPRのテストが落ちてるから原因を調べて
Claude responds with the technical answer first, then appends:
---
**Learn Along** (target: English)
**Your intent in English:**
> Can you investigate why the tests in this PR are failing?
**Key phrases:**
- テストが落ちてる → "the tests are failing" -- casual; in a PR comment prefer "CI is red"
- 原因を調べて → "investigate the root cause" -- or casually, "look into why"
**Register note:** On Slack: "CI is red on this PR, can you take a look?"
Contributing
Feedback, issue reports, and contributions are welcome on GitHub.
License
MIT
Related skills
Grill MeHave an agent relentlessly pressure-test their plan or design until every decision branch is resolved and shared understanding is reached.691k196kGrill With DocsPressure-test architecture decisions against their live codebase and living documentation before writing production code.585k196k
Lark CalendarLet their coding agents read, create, and manage events inside Lark (Feishu) Calendar directly from natural language instructions.493kLark ImLet their coding agent send instant notifications, post updates, and receive commands directly inside Lark (Feishu) workspaces.493kLark ContactLet their AI coding agents read and write contacts, send messages, and manage user data inside Lark (Feishu).493kLark AttendanceAutomatically fetch and report daily attendance data from Lark (Feishu) into their own tools or agents.493k