retrospective-weapon

The retrospective surface end-to-end: choosing the right format, creating the conditions for honesty, facilitating the session, and enforcing follow-through. Built from 2026 research into what makes retros actually change behavior rather than generate a board no one reads.

The most important finding from the research: only 50% of retro action items ever get completed (survey of 419 professionals across 5 countries, 2026-05-15). The format is almost irrelevant if no one does anything differently next sprint. This weapon is calibrated around the follow-through problem, not the facilitation aesthetics problem.

When this weapon applies

Load when retrospective-guardian is invoked. Trigger on:

• "Run a retro" / "plan our retrospective" / "help us do a sprint retrospective"
• "Which retro format should we use?"
• "Our retros produce no change" / "action items never get done" / "retro theater"
• "How do we do an async retro?" / "remote retrospective"
• "We need better psychological safety in our retros"
• "Review last sprint's action items"

Do NOT load for: