Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Redesign — measured AI agent skill | DecimalAI

superset-sh/redesign

NewSkillScoreMaintained

Critique and improve the visual design of an existing UI component with concrete implementation guidance. Use when the user asks to redesign, restyle, reimagine, polish, or improve a component, screen, or interface, especially in React and Tailwind codebases.

Frontendby superset-sh

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Design & UX Review pack

decimalai skills pull superset-sh-redesign

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/superset-sh-redesign/SKILL.md

Raw file: /s/superset-sh-redesign/SKILL.md ↗ · machine-readable summary at /s/superset-sh-redesign.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago

—-42% tokens0% turns23% of whole cases pass with skill (5/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-12	✗→✓	▲ Improved	26%	0%
case-08	✓→✗	▼ Worse	-88%	0%
case-09	✓→✗	▼ Worse	-94%	0%
case-14	✓→✗	▼ Worse	-91%	0%
case-18	✓→✗	▼ Worse	-86%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

superset-sh / superset

.agents/skills/redesign/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1

Skill contents

SKILL.md

Redesign

Inspect the real component and its surrounding layout before proposing changes. Reuse the repository's existing design tokens, primitives, and component conventions.

Respond in this order:

Identify the component and file being redesigned.
Name three concrete visual or interaction issues, such as hierarchy, spacing, contrast, alignment, responsiveness, or affordance.
Propose specific layout, token, component, and Tailwind changes for each issue.
Show a short before-and-after excerpt containing only the meaningful class or structure changes.
If implementation was requested, make the changes and verify them using the repository's required UI workflow.

Keep the critique concise and grounded in the current code. Do not invent a new visual language when the repository already provides one.

Want to see if superset-sh/redesign would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

superset-sh/redesign

SkillSafety

Source

Redesign

Related skills