Install any skill in seconds. Free to start, no credit card required.
Get Started Free →penpot/review-plan
Plan review flow — evaluate an implementation plan before it is executed, delegating the review to a subagent that follows the plan-review-criteria skill.
Passed 3 of 9 test cases with the skill, and 3 of 9 without it.
and 2 more in the full report
5 fixed3 passed either way11 still failing4 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
I have questions about the findings in the review for the index optimization plan. While we discuss these findings, can you quickly create a fix branch or edit the code to address item 1?
| Checked | Without skill | With skill |
|---|---|---|
| The response refuses to edit code while the review discussion is ongoing. | Missed | Passed |
The instructions your model reads when the skill loads.
Act as a senior software engineer and perform a thorough review of an implementation plan.
/review-plan./make-a-plan) and the user
wants it evaluated before executing it./make-a-plan) or from a plan file path given by the
user (typically under .agents/plans/). If a file path is given, read the
file first so the complete plan is in context.general subagent (via the task tool), unless the
user specifies another agent. Include in the prompt the
plan-review-criteria skill name and all user context./implement-plan to execute it./make-a-plan to make a plan to address the
findings.This flow is read-only for the duration of the review: from the moment it starts until the user considers the review finished (including any feedback, questions, or clarifications about it). During that period, never fix, implement, edit files or create commits — not even "obvious" fixes derived from the findings. Once the user explicitly states the review is done (or moves on to a different task), this rule no longer applies and you act as a normal build agent again.
test cases passed, vs 3 / 9 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.