Help us improve
Share bugs, ideas, or general feedback.
From helix
Search helix memory by meaning. Returns relevant insights ranked by relevance × causal effectiveness.
npx claudepluginhub enzokro/crinzo-plugins --plugin helixHow this skill is triggered — by the user, by Claude, or both
Slash command
/helix:helix-queryThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
```bash
Searches and retrieves memories from Cortex persistent memory using WRRF retrieval. Use for past decisions, patterns, bugs, or architecture context.
Searches memory store and threads via nmem CLI for relevant past insights on contextual signals like continuity or recurring themes. Filters by importance, labels, time.
Searches and surfaces relevant memories from past sessions to inform current work with decisions, patterns, and learnings. Supports hybrid, vector, and text search modes with namespace filtering.
Share bugs, ideas, or general feedback.
HELIX="$(cat .helix/plugin_root)"
# Semantic search (flat)
python3 "$HELIX/lib/memory/core.py" recall "$ARGUMENTS" --limit 10
# Graph-expanded search (follows relationships)
python3 "$HELIX/lib/memory/core.py" recall "$ARGUMENTS" --limit 10 --graph-hops 1
# Find related insights to a specific insight
python3 "$HELIX/lib/memory/core.py" neighbors "insight-name" --limit 5
Scoring: rrf_score * (0.5 + 0.5 * causal_adjusted_effectiveness) * recency.
Graph-expanded results have _hop: 1 — discovered via relationship edges, not direct match.
Use --help for filtering options (--min-effectiveness, --suppress-names, --min-relevance).