session-cabinetlisted

Use when the user says "file my sessions", "session archive", "where are my old sessions", "make my Claude history searchable", "organize my Claude Code transcripts", "I can't find that session from last week", or "index my Claude sessions". Auto-files Claude Code session transcripts (~/.claude/projects/**/*.jsonl) into a human-navigable date-anchored archive with semantic SESSION.md cards, per-month _INDEX.md tables, and a master index. Idempotent — safe to run on a schedule. Free skill, stdlib only.
iansteitz1-eng/aria-skills · ★ 0 · Data & Documents · score 62

Install: claude install-skill iansteitz1-eng/aria-skills

# session-cabinet Auto-files Claude Code session transcripts into a searchable, date-anchored archive. ## What it does Claude Code stores every session as a UUID-named `.jsonl` file under `~/.claude/projects/`. These files are opaque by default — no titles, no topics, no way to find "that deploy session from three weeks ago." `session_cabinet.py` scans those transcripts and files each one into: ``` ~/Desktop/Claude Code Sessions/ 2026/ 06-June/ 2026-06-03_1420__nginx-deploy-fix/ SESSION.md ← frontmatter card + summary manifest.log ← one-line event record docs/ artifacts/ screenshots/ notes/ _INDEX.md ← per-month table (Date · Title · Projects · Folder) _INDEX.md ← master table (all sessions) ``` The folder name is derived from the AI-generated title or the first real thing you typed — not the UUID. Every session is findable by date, topic, or keyword grep on the `SESSION.md` cards. ## CLI ```sh # Dry-run (no writes — shows what would be filed) python3 session_cabinet.py --dry-run # File everything python3 session_cabinet.py # Verbose (shows each session path) python3 session_cabinet.py --verbose # Limit to N sessions (useful for testing) python3 session_cabinet.py --limit 20 # Custom cabinet location python3 session_cabinet.py --cabinet ~/Documents/SessionArchive # Or via env var CC_CABINET_DIR=~/Documents/SessionArchive python3 session_cabinet.py # Ov