W Retro

by blockmatic7e05e2abd052dc6b526e8a28e36d102d42bfd635No license1 starsListed Oct 9, 2026Updated Oct 9, 2026Repository updated 6 days ago

After finishing work, answer what you would do better next time.

AI-generated overview

Guides a short post-task retrospective that names gaps and suggests up to three concrete improvements for next time.

What it does: This skill provides a chat-only retrospective procedure to run after a task is finished. It has the agent restate what was requested versus what shipped, identify process or evidence gaps such as skipped checks, unclear requirements, extra scope, or missing documentation, and propose at most three concrete changes for the next similar task, citing the specific task rather than generic advice. It produces a written reflection in conversation and explicitly does not implement, commit, or open a pull request.
When to use it: Use it after completing a task, plan, or set of checks when you want a structured look back at how the work went. It fits situations where you want to surface process gaps and capture a few actionable improvements for similar future work.
Requirements: No tools, packages, or credentials are required; it is instructions only and ships no scripts. It runs as a chat-only reflection, so no repository access or network access is needed.

Look back at the completed task, plan, and checks. Chat only. Do not implement, commit, or open a PR.

Restate what was requested versus what shipped.
Name process or evidence gaps: skipped checks, unclear requirements, extra scope, missing docs.
Suggest at most three concrete changes for the next similar task. Cite this task, not generic advice.

Source and attribution

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.