packet-memory-export

Convert session-distill packets into structured draft memory entries with review queues.

1|Updated Jun 10, 2026
One-click install
npx skills add https://github.com/manhua-man/session-distill-skills --skill packet-memory-export-manhua-man
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: packet-memory-export
Source: https://github.com/manhua-man/session-distill-skills/tree/main/helpers/packet-memory-export
Command: npx skills add https://github.com/manhua-man/session-distill-skills --skill packet-memory-export-manhua-man

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? After distilling AI session transcripts into packets, teams still need a controlled way to turn those packets into candidate memory entries for systems like Codex-mem without blindly syncing unverified claims. This Skill exports structured draft memory JSON from packets, labels each entry, and gates promotion through a human review workflow. ## Core Features & Use Cases - Packet-to-Draft Export: Parses packets/<session-id>.md and produces memory-drafts/<session-id>.json with labeled entries (new, refine, confirm, conflict, ephemeral) and readiness levels (ready-candidate, needs-raw-review, needs-conflict-review, local-only). - Review Queue Management: Supports approve, reject, defer, note, plus batch operations, writing review status, notes, and audit logs back into the draft JSON. - Sync List Generation: Derives sync-lists/<session-id>.json containing only approved, ready candidates, gated by the session's Final Session Review promotion check. - Use Case: After running session-distill on a Codex session, export the packet to memory drafts, review conflicts against existing memory, approve ready candidates, and generate a sync list for manual Codex-mem synchronization. ## Quick Start Ask the assistant to export memory drafts from the latest session packet and show the review queue so you can approve or reject each candidate.

Frequently Asked Questions about packet-memory-export

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I export memory drafts from a session packet?▼

Run the export command with a session ID, for example `packet-memory-export.py export --session <session-id>`. It reads the packet from the packets directory and writes a structured draft JSON to the memory-drafts directory with labels and readiness counts.

What is the difference between session-distill and packet-memory-export?▼

session-distill converts raw transcripts like .jsonl files into packets, while packet-memory-export works on already-generated packets to produce draft memory entries. If you only have raw transcripts, run session-distill first.

How does conflict detection against existing memory work?▼

Pass an existing memory export with `--memory existing-memory.json`. Each statement is compared using sequence similarity; high similarity with negation mismatches is labeled `conflict`, near-duplicates become `confirm`, and moderate matches become `refine`.

Does packet-memory-export write directly to Codex-mem?▼

No. It only produces structured draft JSON and a sync-list of approved ready candidates. Actual synchronization into Codex-mem is a separate manual step, and partial-coverage packets are blocked from automatic sync candidacy.

Why are my exported entries marked needs-raw-review?▼

Entries are marked needs-raw-review when the packet's Coverage is `partial`, meaning the packet audit indicates incomplete rendering. These drafts require reviewing the raw transcript before they can become ready candidates for sync.

When should I use mem-distill instead of packet-memory-export?▼

Switch to mem-distill when your goal is organizing observations already synced into Codex-mem rather than exporting new drafts from packets. packet-memory-export is the promotion gate before sync, not a tool for maintaining existing memory stores.