Save Thread

nowledge-co/community/nowledge-mem-copilot-cli-plugin/skills/save-thread

by nowledge-co1f4d7eb61466dbfc93ce8d7a0a806c4d4a196dd0No licenseListed Oct 9, 2026Updated Oct 9, 2026

Save a summary of the Copilot CLI session on explicit user request. Copilot lifecycle hooks already capture full transcripts automatically — this skill creates a concise summary thread.

Instructions onlyProductivity & Workflow
AI-generated overview

Saves a concise summary of a Copilot CLI session to an nmem thread on explicit user request.

What it does
This skill instructs the agent to write a concise summary of the current Copilot CLI conversation and store it as a thread using the nmem command-line tool. It covers when to save, the exact command form with a title and source tag, and a short confirmation response including the thread ID. It also notes the difference between automatic lifecycle transcript capture, summary threads, and distilled memory.
When to use it
Use it when the user explicitly asks to save, checkpoint, or record the current session. It is intended for on-demand summary saves rather than automatic transcript capture.
Requirements
Requires the nmem CLI (nmem-cli) available on PATH and a reachable nmem server; installation is suggested via pip or Arch Linux package managers. Ships no scripts; instructions only.

Save Thread

When to Save

Only when user explicitly says: "Save this session" | "Checkpoint this" | "Record conversation"

Lifecycle hooks capture full session transcripts automatically after responses, before compaction, and at session end. This skill is for on-demand summary saves.

Tool Usage

Create a summary thread via nmem t create:

bash
nmem t create "A concise summary of this session: what was discussed, what was built, and key decisions made" \  --title "Copilot CLI: <short title from first user message>" \  -s copilot-cli

Important: Write the summary yourself from the current conversation context. Do NOT try to invoke the stop hook script directly — it requires hook payload from Copilot CLI internals.

Thread vs Memory

Automatic lifecycle capture stores real session messages. This skill stores a concise summary thread. Memory stores distilled insights. They are different purposes, and a valuable session can use more than one.

Response

text
✓ Thread savedSummary: {summary}Thread ID: {thread_id from nmem output}

Troubleshooting

If nmem is not in PATH: pip install nmem-cli, or on Arch Linux yay -S nmem-cli / paru -S nmem-cli

Run nmem status to check server connection.

Source and attribution

Source:nowledge-co/communityinnowledge-mem-copilot-cli-plugin/skills/save-threadat commit1f4d7eb

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal