Continual Learning

by cursorccb5507cec15No license10K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated today

Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to `agents-memory-updater`.

Instructions onlyAI & Agents
AI-generated overview

Orchestrates a continual-learning loop by delegating transcript mining and AGENTS.md updates to a subagent.

What it does
This skill defines an orchestration-only workflow for keeping an AGENTS.md file current. It instructs the agent to call the agents-memory-updater subagent and return that subagent's result. The parent flow is explicitly barred from mining transcripts or editing files itself.
When to use it
Use it when the user asks to mine prior chats, maintain AGENTS.md, or run the continual-learning loop. It is intended as a thin delegation layer rather than a direct editor.
Requirements
Requires the agents-memory-updater subagent to be available. Ships no scripts; instructions only.

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.

Source and attribution

Source:cursor/pluginsincontinual-learning/skills/continual-learningat commitccb5507

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

More from cursor/plugins

Unslop

cursor

Edits text to remove AI writing tells, following a numbered list of patterns to detect and fix.

Writing & Content10Kupdated today

Setup Pstack

cursor

Writes a Cursor rule that sets pstack's model per role and reasoning budget.

AI & Agents10Kupdated today

Principle Type System Discipline

cursor

Guides agents to use static type systems to make illegal states unrepresentable and eliminate runtime failures.

Software Development10Kupdated today

Thermo Nuclear Review

cursor

Audits a checked-out branch or PR diff for bugs, breaking changes, security issues, devex regressions and feature-gate leaks.

Security10Kupdated today

Run Learning Retrospective

cursor

Guides a learning retrospective to review progress, find blockers, and adjust a learning plan.

Learning & Education10Kupdated today

Ralph Loop Help

cursor

Explains the Ralph Loop plugin, its iterative technique, options, cancellation, and when to use it.

AI & Agents10Kupdated today

More in AI & Agents

Skill Development

anthropics

Featured

Guides creation of Claude Code plugin skills, covering structure, descriptions, progressive disclosure and validation.

AI & Agents37Kupdated today

Plugin Structure

anthropics

Featured

Guides the structure, manifest, and component layout of Claude Code plugins.

AI & Agents37Kupdated today

Command Development

anthropics

Featured

Guides creation of Claude Code slash commands, covering structure, YAML frontmatter, arguments and plugin features.

AI & Agents37Kupdated today

Claude Md Improver

anthropics

Featured

Audits CLAUDE.md files in a repository, scores their quality, and applies approved targeted improvements.

AI & Agents37Kupdated today

Google Cloud Solution Agentic Ai Data Science Workflow

google

Featured

Guides design of a multi-product agentic data science architecture on Google Cloud, from requirements to deployment and validation.

AI & Agents21Kupdated today

Google Cloud Solution Agentic Ai Borderless Data Lakehouse

google

Featured

Guides design of a borderless multicloud open data lakehouse on Google Cloud, from requirements discovery to deployment and validation.

AI & Agents21Kupdated today