Stats
Actions
Tags
How this skill is triggered — by the user, by Claude, or both
Slash command
/lcars:consolidateThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Manually run pattern consolidation from accumulated session summaries. Normally this runs automatically (amortized during PreCompact), but this skill lets you trigger it on demand and see the results.
Manually run pattern consolidation from accumulated session summaries. Normally this runs automatically (amortized during PreCompact), but this skill lets you trigger it on demand and see the results.
When user runs /lcars:consolidate:
python3 ${CLAUDE_PLUGIN_ROOT}/lib/consolidate.py --consolidate
Display the result:
insufficient_data: report how many sessions exist vs. the 5-session minimumconsolidated: report patterns validated, added, and marked staleIf patterns were validated or changed, read ~/.claude/lcars/memory/patterns.json and display:
If no changes, report that current patterns are up to date.
Consolidation applies overfit gates before accepting patterns:
These gates are inspired by OpenClaw Foundry's crystallization threshold — observe before codifying.
npx claudepluginhub melek/lcars --plugin lcarsScans session logs, journals, and decisions for recurring patterns, then generates CLAUDE.md rules, concept notes, and writing seeds. Run after weekly review or when patterns harden.
Extracts session patterns into reusable learnings. Three modes: analyze (extract from history), review (edit/manage), and list (display active learnings). Requires persistence enabled in session config.
Generates Growth Map from Claude Code session patterns and insights data, integrating epistemic profile for protocol recommendations with execution and epistemic resolution.