work learn
中文Get started

A learning layer for your AI workflow

Learn the English your work already needs.

Turn conversations with AI into a personal course you can actually reuse.

Open Work LearnConnect your agentSee how it works
saved from a real conversation
claudelearning layer on
Can we decouple the validation layer from persistence?
assistant

Yes. That keeps the domain rules independent from the database adapter and makes the module easier to test.

Worth learning01

decouple A from B

Separate two things so each can change independently.

your next use“We should decouple the API layer from the queue.”
The useful part stays close to the work.
Built for the way developers work
ClaudeChatGPTHermesOpenClawyour terminal

Connect once. Learn from every agent.

The MCP server does the saving, searching, and reviewing. The optional Skill tells your agent when and how to use it. CLI covers the terminal.

01

MCP server

Connect it once to give every agent the same memory, search, and review.

save_material()
02

Skill (optional)

Drop in SKILL.md so your agent knows when to save and how to shape it.

organize this conversation
03

CLI

Capture terminal sessions when an agent has no MCP support.

learn capture

The same learning layer, everywhere

Your agents can have different voices. Your learning history should not.

your learningone memory
Soptional
Skillguides the agent
Mserver
MCPsave and search
Cterminal
CLIcapture the terminal

A loop, not a notebook

The point is not more notes.

The point is the next time you can say it without thinking.

  1. 01

    Keep the good sentence

    Work Learn finds expressions worth reusing, not every word you happened to see.

  2. 02

    Make it yours

    See the natural version, why it works, and an example shaped around your codebase.

  3. 03

    Use it again

    The next practice starts from the language your work already made meaningful.

Start with the conversations you already have

Make your work teach you.

No new curriculum. No context switching. Just the useful English, when it matters.

Open Work LearnView SKILL.mdFull setup docs
  1. 1

    Sign in to Work Learn

    Open the web app and copy your access token from the account page.

  2. 2

    Add the MCP server

    Paste this config into your agent's MCP settings. Restart the agent afterwards.

Advanced setup — install the Skill & MCP

Grab the Skill (optional)

The Skill tells your agent when to save. Drop SKILL.md into a skills folder below, then restart the agent.

Requires the MCP server connected above.

One-line install (all detected agents):

curl -fsSL https://raw.githubusercontent.com/bayernjf/work-learn/main/scripts/install-skill.sh | bash

Installs into every detected skills folder, including shared agent folders.

Or choose one agent below.

Codex: ~/.codex/skills/work-learn/SKILL.md · Claude Code: ~/.claude/skills/work-learn/SKILL.md · CodeBuddy: ~/.codebuddy/skills/work-learn/SKILL.md

Then ask: “Save the useful English from this conversation.”

Without the Skill, the MCP tools still work — you just call them by hand.

MCP config

mcp.json
{
  "mcpServers": {
    "work-learn": {
      "command": "pnpm",
      "args": ["--filter", "@work-learn/mcp-server", "exec", "tsx", "src/server.ts"],
      "cwd": "/path/to/work-learn",
      "env": {
        "WORK_LEARN_API_URL": "https://work-learn-api.vercel.app",
        "WORK_LEARN_ACCESS_TOKEN": "<paste-your-token>"
      }
    }
  }
}

Your token stays on your machine and is sent only to the Work Learn API.