organize-files

Organize Files

Restructure the shared notes directory so every agent can find what they need quickly.

For a complete before/after walkthrough on a realistic messy notes/ tree — including the dedup pass, naming fixes, subdirectory creation, link repair, and audit-log entry — see references/worked-example.md. Read it once before your first reorganization; it makes the abstract steps below concrete.

For recovery procedures and judgment calls (move script aborted partway, false-positive duplicates, files that look misplaced in _synthesis/, contradicting _open-questions.md, races between agents…), see references/edge-cases.md.

When to Use

• Too many flat files in research/ or experiments/
• Duplicate or near-duplicate notes
• Inconsistent naming (spaces, uppercase, agent IDs in filenames)
• After a deep-research or consolidate phase that created many files
• You can't find a note you know exists

Notes Directory Structure

notes/
├── index.md          ← table of contents (research + experiments only)
├── raw/              ← immutable sources (DON'T touch)
├── research/         ← deep-research findings (organize within)
│   ├── <topic>/      ← group by topic or theme
│   └── ...
├── experiments/      ← eval reflections and results (organize within)
│   ├── <approach>/   ← group by approach or technique
│   └── ...
├── _synthesis/       ← consolidate owns this (DON'T touch)
├── _connections.md   ← consolidate owns this
├── _open-questions.md
└── _organization-log.md  ← append-only log of what you changed

Process

1. Audit

Get the current state:

bash .coral/public/skills/organize-files/scripts/audit.sh

Or manually: ls -R {shared_dir}/notes/ and count files per directory.

Also check for content-level issues:

• Contradictions — do any notes claim opposite things? Update or flag them in _open-questions.md.
• Stale info — research notes that experiments have disproven. Update with actual results.
• Orphan pages — notes not listed in index.md. Add them.
• Missing cross-references — related notes that don't link to each other.
• Gaps — techniques mentioned but never researched, or researched but never tried.