mcpField
C
continual-learning

continual-learning

github.com/cursorAgent workflows14.5k1.5k installsUpdated today
Repository

About continual-learning

A skill that delegates updates to `AGENTS.md` to the `agents-memory-updater` subagent. It is for requests to mine prior chats, maintain `AGENTS.md`, or run the continual-learning loop, while keeping the parent workflow limited to orchestration.

Key features

  1. 01Trigger-based continual-learning workflow
  2. 02Delegate updates to `agents-memory-updater`
  3. 03Return the updater result
  4. 04Keep transcript analysis out of parent flow

Use cases

  1. 01Mine prior chats to maintain `AGENTS.md`
  2. 02Run a continual-learning update loop
  3. 03Delegate memory updates without parent-side file edits

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/cursor/plugins --skill continual-learning

After installing, type/continual-learningin Claude Code to confirm it loaded.

Details

From the project README

Continual Learning

Keep AGENTS.md current by delegating the memory update flow to one subagent.

Trigger

Use when the user asks to mine prior chats, maintain AGENTS.md, or run the continual-learning loop.

Workflow

  1. Call agents-memory-updater.
  2. Return the updater result.

Guardrails

  • Keep the parent skill orchestration-only.
  • Do not mine transcripts or edit files in the parent flow.
  • Do not bypass the subagent.

Comments

Markdown supported