Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Production-readiness pass — audits and implements the full non-happy-path matrix: loading skeletons, empty states, error messages, partial data, i18n, offline, permissions, and first-run guidance. Use when preparing a surface for production or when the user says "it crashes on empty data" / "there's no loading state" / "harden this". Invoke when the user asks for harden on their UI, or mentions 'harden' alongside design / UI / frontend work.
.claude/skills/educlopez-harden/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 312% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 12% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 53% | 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.
Harden the UI at $ARGUMENTS for production. Load the ui-craft skill.
Coverage matrix — check every key surface:
— (em dash) for missing metrics, never N/A or null or 0 when the value is truly unknown.title tooltip, text-overflow: ellipsis, container queries for constrained regions. Test with a 120-character name.Knob-agnostic — correctness is not tunable. Run the full matrix regardless of CRAFT_LEVEL / MOTION_INTENSITY / VISUAL_DENSITY.
Then run the archetype's coverage parts. The nine items above are cross-cutting; they do not know what kind of screen this is. Name the archetype (data table, settings, search, detail view, first-run, billing, pricing, docs page, checkout, onboarding, destructive confirm, invite/share) and pull its parts:
ux_coverage with the archetype. It returns that archetype's parts and the reporting contract.references/coverage.md.Each part carries what present looks like, the ui-craft rule for building it, and what the user loses without it. Report the cost, not just the absence — "no export" is a status, "the user expects the 24 rows on screen and receives 10,000" is the reason it matters.
References to read: references/accessibility.md (keyboard + screen reader paths), references/copy.md (error and empty-state voice), references/motion.md Rendering Performance section (skeleton motion + reduced-motion).
Output: two sections, reported side by side and never combined.
not-needed requires a stated reason; if you cannot say why it does not apply here, it is missing. unknown says whether more input would settle it.No score, no count, no percentage on either section. "7 of 9" makes not-needed read as a failure and turns a hardening pass into a grade. Coverage never gates: it reports, and the build still ships.
Then edit the code to fix what's missing. Print the Review Format table showing fixes. End with a "still at risk" list for anything you couldn't safely auto-fix (requires backend, requires design decision, requires translation files).
Next step: /finalize — the pre-ship gate (rung 3).
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-05 | pass→pass | 13,196 | 14,471 | +10% | 1 | 1 | 0% | 2,620 | 3,859 | +47% | 0 | 0 | — |
case-06 | pass→pass | 14,400 | 8,884 | -38% | 1 | 1 | 0% | 2,561 | 2,409 | -6% | 0 | 0 | — |
case-07 | pass→pass | 12,464 | 16,060 | +29% | 1 | 1 | 0% | 1,641 | 3,717 | +127% | 0 | 0 | — |
case-08 | fail→fail | 11,668 | 4,721 | -60% | 1 | 1 | 0% | 1,807 | 1,757 | -3% | 0 | 0 | — |
case-09 | fail→pass | 12,318 | 4,810 | -61% | 1 | 1 | 0% | 2,025 | 1,847 | -9% | 0 | 0 | — |
case-01 | fail→fail | 31,410 | 8,493 | -73% | 1 | 1 | 0% | 6,237 | 1,229 | -80% | 0 | 0 | — |
case-02 | fail→fail | 3,002 | 4,388 | +46% | 1 | 1 | 0% | 193 | 1,224 | +534% | 0 | 0 | — |
case-03 | fail→fail | 27,690 | 6,731 | -76% | 1 | 1 | 0% | 6,233 | 1,341 | -78% | 0 | 0 | — |
case-04 | pass→pass | 13,202 | 10,644 | -19% | 1 | 1 | 0% | 2,577 | 3,042 | +18% | 0 | 0 | — |
case-10 | fail→pass | 9,273 | 29,163 | +214% | 1 | 1 | 0% | 1,745 | 7,183 | +312% | 0 | 0 | — |
case-11 | fail→pass | 6,232 | 3,041 | -51% | 1 | 1 | 0% | 1,092 | 1,398 | +28% | 0 | 0 | — |
case-12 | fail→pass | 14,667 | 10,729 | -27% | 1 | 1 | 0% | 2,612 | 2,930 | +12% | 0 | 0 | — |
case-13 | fail→pass | 9,648 | 8,081 | -16% | 1 | 1 | 0% | 1,661 | 2,538 | +53% | 0 | 0 | — |
case-14 | pass→pass | 11,317 | 6,090 | -46% | 1 | 1 | 0% | 1,838 | 1,979 | +8% | 0 | 0 | — |
case-15 | fail→pass | 7,211 | 6,377 | -12% | 1 | 1 | 0% | 1,258 | 2,054 | +63% | 0 | 0 | — |
case-16 | fail→pass | 7,853 | 1,429 | -82% | 1 | 1 | 0% | 1,374 | 1,276 | -7% | 0 | 0 | — |
case-17 | fail→pass | 12,690 | 21,292 | +68% | 1 | 1 | 0% | 2,384 | 5,197 | +118% | 0 | 0 | — |
case-18 | fail→fail | 13,937 | 11,418 | -18% | 1 | 1 | 0% | 2,490 | 3,273 | +31% | 0 | 0 | — |
case-19 | fail→fail | 10,187 | 5,072 | -50% | 1 | 1 | 0% | 1,645 | 1,823 | +11% | 0 | 0 | — |
case-20 | fail→pass | 3,590 | 23,273 | +548% | 1 | 1 | 0% | 623 | 5,471 | +778% | 0 | 0 | — |
case-21 | fail→fail | 6,627 | 10,072 | +52% | 1 | 1 | 0% | 1,449 | 2,974 | +105% | 0 | 0 | — |
case-22 | fail→fail | 17,042 | 28,172 | +65% | 1 | 1 | 0% | 3,497 | 7,162 | +105% | 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 +41 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.