| name | continual-learning |
| description | Orchestrate continual learning by delegating transcript mining and AGENTS.md updates to the knowledge-synthesizer subagent. Use when asked to mine prior chats, maintain AGENTS.md, update learned preferences, or run the continual-learning loop. |
| disable-model-invocation | true |
When to use
- asked to mine prior chats, maintain
AGENTS.md
On-demand loading: Read this file when the task matches the triggers below.
Activation: Use this skill when asked to mine prior chats, maintain AGENTS.md, update learned preferences, or run the continual-learning loop. Do NOT use for one-off transcript reading or general preference discussion.
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
- Use the Task tool with
subagent_type: "knowledge-synthesizer". Instruct it to Read ~/.cursor/skills/workflow-from-chats/SKILL.md for transcript-mining methodology, extract durable patterns from recent sessions, and update AGENTS.md with learned preferences, conventions, and facts.
- 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.
