Individual skill

keep-why-retrospective

Use when an existing repository needs its unexplained rationale recovered into topic files. Don't use for remote, credential, publish, deploy, or irreversible changes.

.devin/skills/keep-why-retrospective/SKILL.md

Read pinned source

Source commit b0e8ce89a19fac880251dc3ea1babfeb4503a4fe

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Instructions only
Last checked
Nov 4, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
55
Repository last updated
Sep 28, 2026
License
Apache-2.0

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Keep why retrospective

## Contract

| Field | Bound contract |
|---|---|
| Trigger | User asks to document an existing/legacy repository or recover why-knowledge the code cannot explain. |
| Authority | Reversible local: writes only rationale topic files inside the target repository; rollback is version control or undo. No remote mutation. Never stages, commits, pushes, or publishes. |
| Side effect | Creates/updates topic files with reconstructed rationale, explicit Evidence levels, open-question statuses, and unknown markers for unrecoverable items. |
| Done | Every code-unexplainable area in scope is enumerated; each entry carries an evidence classification; what could not be recovered is stated as unknown, never guessed; conflicts between code and docs/maintainers are flagged open. |

## Inputs

- Target repository path: required; taken from the request.