reflectlisted

# Reflect Mine the current conversation for durable learnings, then route them into skill edits. ## When to invoke - The user said "reflect" or "/poteto:reflect". - A complex task (5+ tool calls) just landed cleanly and the recipe is worth keeping. - The agent hit dead ends, found the working path, and the path generalizes. - The user corrected the agent's approach mid-task. - A non-trivial workflow emerged that isn't captured anywhere. Skip when the conversation is trivial, off-topic, or already covered by an existing skill the parent followed correctly. One-offs are not learnings. ## Process ### 1. Locate the active transcript The parent finds its own transcript file before fanning out. Claude Code stores transcripts under `~/.claude/projects/<slug>/`, where `<slug>` is the active workspace path encoded with `/` replaced by `-`. Use only the active workspace's directory. Do not glob across `~/.claude/projects/*/`. That crosses workspace boundaries and reads private chats from unrelated projects. ```bash ls -t ~/.claude/projects/<slug>/*.jsonl ~/.claude/projects/<slug>/*/subagents/*.jsonl 2>/dev/null | head -10 ``` Two transcript layouts: the session (`<session>.jsonl`) and its subagents (`<session>/subagents/agent-<id>.jsonl`). For each candidate, grep its first user message for the conversation's opening prompt (the first lines may be `queue-operation` records; skip those). Take the matching path. If no path resolves, write a tight digest of the session and pass