# Do It Retrospective

> Use when the user asks to reflect on an observed collaboration or engineering outcome and identify useful lessons.

- Skill: `tdwhere123/do-it-retrospective` (Agent Skill)
- Install (CLI): `npx skillmds@latest add tdwhere123/do-it-retrospective`
- Raw SKILL.md: https://api.skillmd.com/api/skills/tdwhere123/do-it-retrospective/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: tdwhere123 (https://skillmd.com/u/tdwhere123)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/tdwhere123/do-it-retrospective

---


# Retrospective

Reason from the observed episode: what outcome was intended, what happened,
which cause best explains the difference, and what change would address it.
Distinguish evidence from conjecture and recurring causes from one-off friction.

Keep lessons proportional to the evidence. A useful conclusion may be a local
code or documentation fix, a better question, or no policy change. Retrospective
reasoning does not enable automatic recording, personalization, or policy
promotion. Use native host instructions or memory for preferences only when the
user requests persistence; do not access or modify old do-it profiles by default.

