lavra-learn

<project_root>

All .lavra/ paths are relative to the project root. If you cd into a subdirectory during work, resolve the project root first:

PROJECT_ROOT=$(git rev-parse --show-toplevel 2>/dev/null || echo "$PWD")

Then prefix all .lavra/ paths with "$PROJECT_ROOT/" when invoking them via Bash.

</project_root>

Knowledge flow:

Work session -> inline bd comments (raw) -> /lavra-learn (structured) -> auto-recall (future sessions)

Raw comments logged during work are often terse, context-dependent, and untagged beyond auto-detection. This command reviews them with full context, produces well-titled entries with accurate tags, deduplicates against existing knowledge, and synthesizes higher-level patterns where entries connect.

This command improves capture quality. It does not perform shared-memory history cleanup or rewrite older entries in knowledge.jsonl. Any future shared curation workflow is separate and review-gated.

Usage:

/lavra-learn                       # Process all beads closed today
/lavra-learn BD-042                # Process specific bead
/lavra-learn BD-042 BD-043 BD-044  # Process multiple beads

Step 1: Gather Raw Entries

Collect all knowledge comments from the target beads.

If bead IDs provided:

bd show {BEAD_ID} --json
# Extract comments matching LEARNED:|DECISION:|FACT:|PATTERN:|INVESTIGATION: prefixes

If no bead IDs, find beads closed today:

bd list --status=closed --json | jq '[.[] | select(.updated_at >= "'$(date +%Y-%m-%d)'")]'

For each bead, collect:

• All comments with knowledge prefixes
• Bead title and description (for context)
• Related bead IDs from dependencies

If no knowledge comments are found in the target beads, report that and exit.