loop-retrospectivelisted

# Loop retrospective Loop retrospectives turn observed friction into durable process improvements. The output is never private memory; every retained lesson becomes reviewed text in the repo or a task record a later agent can discover. This skill is **parked and optional**. It is not part of [[task-closeout]] and does not gate it. Run it only when a human explicitly asks for a retrospective, and only when there is enough recorded signal to work from. Its primary inputs are the local event logs and blocked/needs_context events – not task completion summaries, which are written for a different purpose. Until event logging matures into routine use, this skill will usually have nothing durable to act on; that is expected. ## Workflow 1. **Gather signals.** Read the local `.agenticloop/logs/<TASK-ID>.jsonl` event log entries (when event logging is enabled and files exist), blocked and needs_context events, recorded block categories, review-result events across rounds, and recurring follow-up task topics. Do not reconstruct friction from task completion summaries or copy raw agent exchanges into docs. 2. **Find recurring patterns.** Treat repeated check failures, repeated block categories, repeated review rounds, and repeated follow-up themes as candidates. Do not turn one-off noise into new process. One directly evidenced required-gate bypass, fabrication, or material misordering is the narrow serious-incident exception: create one durable improvement proposal without waiting