ワンクリックで
local-session-handoff
Use when a local Copilot/Qwen chat is too long and needs compaction, checkpointing, restart, or a handoff summary.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Use when a local Copilot/Qwen chat is too long and needs compaction, checkpointing, restart, or a handoff summary.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when local Copilot/Qwen/LLM Gateway hits prompt bloat, context limits, slow prefill, timeouts, or 24GB GPU token-budget issues.
Use when local Qwen, llama-server, or ik_llama.cpp dies, stalls, times out, OOMs, cancels, or needs log-based failure diagnosis.
Use when a local-agent coding task needs minimal repo context, targeted file discovery, compact search, or a small implementation brief.
Use when local Qwen/Copilot should delegate isolated research, review, or summarization to subagents without bloating parent context.
Use when local Copilot/Qwen tool calls fail, malformed tool JSON appears, tools are skipped, or LLM Gateway agent mode is flaky.
| name | local-session-handoff |
| description | Use when a local Copilot/Qwen chat is too long and needs compaction, checkpointing, restart, or a handoff summary. |
| argument-hint | [current work to checkpoint] |
Compress a long local-agent session into a short checkpoint for a fresh chat.
/memories/session/ file so a future chat can re-read it without paying for the whole transcript.Return a handoff using these headings, in this order: