Locus Palace Init

Step 3 — Parse each memory file

For each source memory file, extract:

Keep each extraction to the first 150 lines of the file — do not load the full file if avoidable.

Step 4 — Sort and group projects

Assign each project to a group using these heuristics (first match wins):

Sort within each group alphabetically by slug.

Report the grouping plan (slug → group) before writing anything.

Step 5 — Create the palace structure

5a — Check for existing palace

1. Check if <palace>/INDEX.md already exists.
2. If it does and --overwrite was NOT passed:
   • Read the existing INDEX.md.
   • Only add rooms for slugs not already listed.
   • Preserve existing rows in the index tables.
3. If it does not exist (or --overwrite): start fresh from the template below.

5b — Write room files

For each project (in group order, then alphabetical):

1. Determine the room path:

   • infra, tools, data, docs groups → <palace>/global/<slug>/
   • projects group → <palace>/projects/<slug>/

2. Check if the room already exists (<room-path>/<slug>.md). If it does and --overwrite is not set, skip it with a note.

3. Create the room directory and write <slug>.md:

# <title>

<summary>

## Overview

<!-- Imported from auto-memory on YYYY-MM-DD. Review and prune. -->

<paste the first 60 lines of the source MEMORY.md, indented as a blockquote or verbatim section>

## Key Files

<!-- Populated from auto-memory import. Verify paths are still current. -->

<key_files extracted in step 3, one per table row>

## References

<!-- Specialty files imported alongside MEMORY.md, if any. -->

<one line per specialty file, or "(none)" if none>

<!--
SOURCE: <memory_path>
IMPORTED: YYYY-MM-DD
STATUS: imported — review and reformat before treating as canonical
-->

4. Copy any specialty .md files from memory/ into the room directory as-is.

5c — Write INDEX.md

Build the index by iterating groups in this order: infra, tools, data, docs, projects.

Use the template below, omitting any section whose group has no rooms:

# <Palace Name>

Memory palace auto-initialized from <N> project memory files on YYYY-MM-DD.
Review imported rooms and reformat to canonical style before treating as final.

## Global Rooms

| Room | Description | Path |
|---|---|---|
| `<slug>` | <summary, truncated to 80 chars> | `global/<slug>/` |

## Project Rooms

| Room | Description | Path |
|---|---|---|
| `<slug>` | <summary, truncated to 80 chars> | `projects/<slug>/` |

---
_Initialized: YYYY-MM-DD — review imported rooms before first use_

<!--
NAVIGATION: Read this file first. Identify the relevant room(s), then read
only those. Do not load the full palace.
SIZE LIMIT: Keep this file under 50 lines.
-->

Step 6 — Report

Emit a summary:

locus-palace-init complete:
  Source: <source dir>  (<N> memory files found)
  Palace: <palace dir>
  Rooms created: <N>
  Rooms skipped (already exist): <N>
  Groups: infra=N  tools=N  data=N  docs=N  projects=N

Next steps:
  1. Review each room file — imported content is verbatim, not canonical.
  2. Reformat to palace conventions (remove the SOURCE/IMPORTED comment block).
  3. Run /locus-consolidate on busy rooms once you start using the palace.

If --dry-run was passed, prefix every write action with [dry-run] and skip all file I/O.

Notes

• This skill creates a first-pass palace. Imported content is verbatim from auto-memory files, which are themselves auto-generated and may contain stale facts. Always review imported rooms before relying on them.
• Run locus-consolidate on any room immediately if it has sessions/ logs that were also imported.
• The --source and --palace defaults assume the standard Claude Code auto-memory layout. Adjust if your setup differs.
• This skill is intentionally write-safe by default: it skips existing rooms rather than overwriting them. Use --overwrite explicitly to re-import.