---
name: docxology/continual-learning
source: https://app.decimal.ai/s/docxology-continual-learning@1/SKILL.md
source_sha256: 49394948401d
---

# Continual Learning (template repo)

Keep durable agent memory in **local JSON**, not in root `AGENTS.md`.

## Trigger

Use when the user asks to mine prior chats, maintain agent memory, or run the continual-learning loop (including stop-hook followups).

## Workflow

1. Call the `agents-memory-updater` subagent (repo override at `.cursor/agents/agents-memory-updater.md`).
2. Return the updater result verbatim.

## Target file

- Memory: `.cursor/hooks/state/continual-learning-memory.json`
- Schema example: `.cursor/hooks/state/continual-learning-memory.example.json`
- Optional helpers: `infrastructure.core.agent_memory`

## Guardrails

- Keep this skill orchestration-only — do not mine transcripts or edit files in the parent flow.
- Do not bypass the subagent.
- **Never** add or edit `## Learned User Preferences` or `## Learned Workspace Facts` in root `AGENTS.md` (public-repo contract).
- Do not commit `continual-learning-memory.json` or `continual-learning-index.json`.