docs(refactor-plan): expand skill description and instructions#1673
docs(refactor-plan): expand skill description and instructions#1673jrkasprzyk wants to merge 2 commits into
Conversation
Clarify when to invoke the skill and require a plan-first, confirm-before-edit workflow so agents do not start changing files during planning.
![github-actions[bot]](https://avatars.githubusercontent.com/in/15368?s=60&v=4){kind=small}
There was a problem hiding this comment.
main, but PRs should target staged.
The main branch is auto-published from staged and should not receive direct PRs.
Please close this PR and re-open it against the staged branch.
You can change the base branch using the Edit button at the top of this PR,
or run: gh pr edit 1673 --base staged
github-actions
Bot
added
skills
|
🔴 Contributor Reputation Check: HIGH risk
Maintainers: please review this contributor before merging. |
github-actions
Bot
added
the
needs-review:HIGH
github-actions
Bot
added
branched-main
|
🔴 Contributor Reputation Check: HIGH risk
Maintainers: please review this contributor before merging. |
|
There's a line ending problem or something, sorry! I'll fix and try again later. |
Summary
refactor-planskill description so agents know when to invoke it (plan/sequence/scope a multi-file refactor) and that planning must precede edits.SKILL.mdinstructions: investigate first without editing, plan contracts → impl → callers → tests → cleanup, include verification + rollback, and stop for confirmation before Phase 1.docs/README.skills.mdso the catalog row matches the skill frontmatter.Why
The prior one-line description ("Plan a multi-file refactor with proper sequencing and rollback steps") gave no invocation signal and did not prevent agents from starting edits while "planning." The new copy makes the skill discoverable by intent and enforces a plan-first, confirm-before-edit workflow.
Test plan
docs/README.skills.mdrow matchesskills/refactor-plan/SKILL.mdfrontmatter description