/crisp-review
A design grade and three fixes in thirty seconds.
(What it does)
A thirty-second design check. /crisp-review looks at a screen across all five CRISP dimensions and returns a grade from A to F, the three issues that most affect users, and a specific fix for each.
It is a quick diagnosis, not a report. It does not score each dimension separately; that is what /crisp-audit is for. The output is short enough to read at a glance and act on in your next commit.
(When to use it)
Use it when you need direction, not documentation:
- Mid-iteration, between changes, when a full audit would break your flow
- Before committing a screen, to catch what you have stopped noticing
- Checking UI that an AI agent generated before you accept it
- Deciding whether a screen needs a full
/crisp-audit
(What you get)
- Grade A–F and a one-line verdict
- Top 3 issues ranked by impact
- A specific fix for each issue
- Quick wins list
(Example output)
Illustrative example only. This is not a real audit.
(The grading scale)
- A: World-class. Ship it. Minor polish only.
- B: Good. One or two fixable issues.
- C: Works, but frustrating. Several P1 issues.
- D: Users will struggle. The core experience is broken.
- F: Blocks users completely. Do not ship.
(Common questions)
What input does it need?
A screenshot, a component file, or a plain description of the screen. If .crisp.md exists, it is loaded automatically, so the grade reflects your users and priorities rather than a generic standard.
Why only three issues?
A limit of three forces an honest ranking by impact. Fifteen findings in the middle of iterating is noise. The three issues that most affect users, each with a specific fix, are what change your next commit. Smaller issues go in the quick wins list.
Will it soften the verdict?
No. The skill's tone rules are explicit: direct and specific, with no softening. If a design fails, the review says so and explains exactly why. The aim is a better next iteration, not a comfortable one.
When should I upgrade to a full audit?
When the same screen keeps grading poorly, when you need severity ratings and a benchmark comparison to justify priorities, or when a milestone calls for the full scorecard. Use /crisp-review while you iterate and /crisp-audit at checkpoints.
(Install)
Installs all fourteen CRISP skills and detects which AI coding tool you use. Run /crisp-teach once per project, before the other skills.
(Related skills)