Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →UX copy review across buttons, errors, empty states, and form hints — critiques by default, applies only on request. Use when copy feels vague, generic, or AI-sounding, or when the user says "fix the labels", "improve error messages", or "review the copy". Invoke when the user asks for clarify on their UI, or mentions 'clarify' alongside design / UI / frontend work.
.claude/skills/educlopez-clarify/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | -22% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -8% | 0% |
| case-21 | ✓→✗ | ▼ Worse | 8% | 0% |
| case-04 | ✓→✓ | ＝ Same ✓ | 3% | 0% |
| case-05 | ✓→✓ | ＝ Same ✓ | 9% | 0% |
<!-- HARNESS MIRROR — do not edit here. Canonical source: skills/ or commands/. After editing source, copy into cli/assets/<harness>/ and repo-root harness mirrors. -->
Context: this sub-skill is one lens of the broader ui-craft skill. If the ui-craft skill is also installed, read its SKILL.md first for Discovery + Anti-Slop + Craft Test, then apply the specific lens below.
Clarify the copy in $ARGUMENTS. Load the ui-craft skill.
Default mode: critique, not edit. Return the copy diff in a Review Format table. Only apply changes if the user says "apply".
Checklist — walk the UI and flag every instance:
Knob-agnostic — clarity is not tunable. Run the full checklist regardless of CRAFT_LEVEL.
References to read: references/copy.md (microcopy voice + patterns), references/accessibility.md (error message expectations for screen readers).
Output format — the Review Format table:
| Before | After | Why | | --- | --- | --- |
Prioritize by impact (errors and destructive actions first, then CTAs, then helper copy). End with a one-paragraph summary of the overall voice shift. If the user says "apply", edit the code and re-print the table with file paths.
Next step: /critique — copy changes shift hierarchy; re-read the surface after (rung 1).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-16 | fail→fail | 3,945 | 5,561 | +41% | 1 | 1 | 0% | 204 | 928 | +355% | 0 | 0 | — |
case-01 | fail→fail | 10,718 | 14,538 | +36% | 1 | 1 | 0% | 2,094 | 889 | -58% | 0 | 0 | — |
case-02 | fail→fail | 10,613 | 15,140 | +43% | 1 | 1 | 0% | 1,822 | 3,203 | +76% | 0 | 0 | — |
case-03 | fail→fail | 4,361 | 5,625 | +29% | 1 | 1 | 0% | 277 | 897 | +224% | 0 | 0 | — |
case-04 | pass→pass | 8,108 | 5,052 | -38% | 1 | 1 | 0% | 1,435 | 1,480 | +3% | 0 | 0 | — |
case-05 | pass→pass | 6,136 | 3,264 | -47% | 1 | 1 | 0% | 1,061 | 1,153 | +9% | 0 | 0 | — |
case-06 | pass→pass | 10,629 | 7,990 | -25% | 1 | 1 | 0% | 1,925 | 2,010 | +4% | 0 | 0 | — |
case-07 | fail→pass | 8,390 | 3,606 | -57% | 1 | 1 | 0% | 1,528 | 1,195 | -22% | 0 | 0 | — |
case-08 | pass→pass | 12,278 | 7,065 | -42% | 1 | 1 | 0% | 1,964 | 1,659 | -16% | 0 | 0 | — |
case-09 | pass→pass | 8,335 | 5,294 | -36% | 1 | 1 | 0% | 1,269 | 1,406 | +11% | 0 | 0 | — |
case-10 | pass→pass | 7,263 | 4,546 | -37% | 1 | 1 | 0% | 1,266 | 1,303 | +3% | 0 | 0 | — |
case-11 | pass→pass | 10,438 | 5,091 | -51% | 1 | 1 | 0% | 1,526 | 1,359 | -11% | 0 | 0 | — |
case-12 | pass→pass | 7,979 | 6,101 | -24% | 1 | 1 | 0% | 1,409 | 1,392 | -1% | 0 | 0 | — |
case-13 | pass→pass | 6,005 | 3,334 | -44% | 1 | 1 | 0% | 1,007 | 1,201 | +19% | 0 | 0 | — |
case-14 | fail→pass | 9,124 | 4,557 | -50% | 1 | 1 | 0% | 1,596 | 1,467 | -8% | 0 | 0 | — |
case-15 | pass→pass | 3,977 | 8,425 | +112% | 1 | 1 | 0% | 779 | 1,789 | +130% | 0 | 0 | — |
case-17 | fail→fail | 11,017 | 6,284 | -43% | 1 | 1 | 0% | 1,970 | 1,635 | -17% | 0 | 0 | — |
case-18 | pass→pass | 7,711 | 4,728 | -39% | 1 | 1 | 0% | 1,214 | 1,314 | +8% | 0 | 0 | — |
case-19 | pass→pass | 8,880 | 5,581 | -37% | 1 | 1 | 0% | 1,395 | 1,469 | +5% | 0 | 0 | — |
case-20 | pass→pass | 9,411 | 8,427 | -10% | 1 | 1 | 0% | 1,805 | 2,106 | +17% | 0 | 0 | — |
case-21 | pass→fail | 8,901 | 7,487 | -16% | 1 | 1 | 0% | 1,549 | 1,677 | +8% | 0 | 0 | — |
case-22 | pass→pass | 9,156 | 8,574 | -6% | 1 | 1 | 0% | 1,757 | 2,173 | +24% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 19 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +5 percentage points is the difference between those two pass rates over the 19 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.