From claude-eureka
Auto-save context when the agent learns something — triggers on: remember, convention, always do, note for future, learned that, from now on, never do, experiment completion, bug resolution
How this skill is triggered — by the user, by Claude, or both
Slash command
/claude-eureka:auto-memoryThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Activate when any of these occur:
Activate when any of these occur:
Route entries to the appropriate context file:
| Content type | File |
|---|---|
| Conventions, preferences, workflows | .claude/context/conventions.md |
| Experiment results, metrics, findings | .claude/context/experiments.md |
| Architecture discoveries, code patterns | .claude/context/architecture.md |
Create the file if it does not exist. Use a # Context heading at the top.
Each entry is a dated, concise line:
- **YYYY-MM-DD**: <short description of what was learned or decided>
Append new entries under the appropriate section heading. Keep descriptions to one or two sentences.
Before adding an entry:
(updated YYYY-MM-DD)npx claudepluginhub gaaaavin/claude-eureka --plugin claude-eurekaSaves key project knowledge explicitly to MEMORY.md via /si:remember for reliable recall. Checks duplicates, warns on size, suggests CLAUDE.md promotion.
Persists learnings into a 5-layer memory hierarchy (CLAUDE.md files, memory/MEMORY.md) and consolidates by pruning outdated entries and promoting recurring patterns. Triggers on 'extract learnings', 'remember', 'dream'.
Extracts reusable strategic knowledge from session history (architecture, patterns, ops) and updates local CLAUDE.md. Triggers on 'learn', 'save knowledge', or session ends.