Menu
Rebuild the Local Brain Search FAISS index to reflect vault changes
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Autonomous AI crystallization - synthesizes converged thinking topics into ai-inferred notes in a dedicated folder. Never touches the human-curated permanent knowledge base and never changes a topic's status, so manual crystallization stays available to the user.
Analyze knowledge base structure and update the knowledge-base-analysis.md report
Discover non-obvious cross-domain connections through random sampling and pattern analysis
Run a full coherence sweep across the Brain Dependency Graph - computes staleness, lifecycle transitions, structural health, and generates a report
Compute lifecycle scores for all insight and framework notes - detect which notes are crystallizing or becoming generative
Create long-form articles from knowledge base insights. Use when writing articles, blog posts, Substack content, or synthesizing knowledge into publishable content. Includes tone of voice, structure templates, and knowledge base integration.
| name | refresh-index |
| description | Rebuild the Local Brain Search FAISS index to reflect vault changes |
| automation | autonomous |
| schedule | 0 5 * * * |
| allowed-tools | Bash |
Rebuild the Local Brain Search vector index to ensure semantic search reflects current vault state.
The FAISS index is not auto-updated. This playbook rebuilds it so semantic search stays accurate.
| Source | Location | Read | Write | Description |
|---|---|---|---|---|
| Brain notes | Brain/**/*.md | โ | Source content to index | |
| Index script | resources/local-brain-search/run_index.sh | โ | Indexer | |
| FAISS index | resources/local-brain-search/brain_index/ | โ | Output index |
resources/local-brain-search/Check indexer exists:
test -f resources/local-brain-search/run_index.sh && echo "OK" || echo "MISSING"
If missing, abort.
resources/local-brain-search/run_index.sh
The indexer rebuilds the FAISS index and the connection graph in full on every
run, and writes a build manifest to data/manifest.json stamping the edge
formula (cosine_ip) and builder_version. After any change to the indexing
or edge logic (e.g. the semantic-edge similarity formula), pass --force to
make the full rebuild explicit and bump BUILDER_VERSION in memory_config.py
so the manifest records the new build:
resources/local-brain-search/run_index.sh --force
Confirm index works:
resources/local-brain-search/run_connections.sh --stats --json
Should return valid JSON with note count > 0.
The BDG enrichments depend on the LBS graph. After reindexing, re-classify nodes and edges:
resources/brain-graph/run_brain_graph.sh bootstrap --force
Verify:
resources/brain-graph/run_brain_graph.sh status
Should show enriched nodes matching the new index count.
resources/local-brain-search/data/resources/brain-graph/data/graph_enrichments.json| Error | Recovery |
|---|---|
| Script missing | Abort - check Local Brain Search installation |
| Index fails | Check Python env, disk space |
| Stats return 0 notes | Re-run indexer, check Brain path |
| BDG bootstrap fails | Non-critical - LBS index still works without BDG |