Ready to supercharge your AI agents?

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

Get Started Free →

Correctness-First Frontend Skill · yiweiren123-arch | DecimalAI

Registry skillby yiweiren123-arch

Correctness-First Frontend Skill

yiweiren123-arch/correctness-frontend

Source yiweiren123-arch/skill-conflict-poc ↗License Not recorded

Build reliable, accessible, well-tested frontend components

SkillScore55Maintained

Automatic

Frontend / UI pack

Last verified 8/4/2026

What it changes

Passed 12 of 22 test cases with the skill, and 3 of 22 without it.

Without skill14%

With skill55%

Checks it passed that the model alone missed

The CSS avoids clip-path properties.
The CSS avoids mix-blend-mode properties.
The buttons avoid scale click animations.

and 15 more in the full report

9 fixed3 passed either way10 still failing0 broke

Pass-rate lift: +41 pp
Tokens: +2%
Agent turns: 0%
Response time: -4%

Model gemini-3.6-flashMeasured 8/4/2026v112 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/yiweiren123-arch-correctness-frontend/SKILL.md https://app.decimal.ai/s/yiweiren123-arch-correctness-frontend/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add yiweiren123-arch-correctness-frontend, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/yiweiren123-arch-correctness-frontend/ and pins it in .decimal/skills.lock

decimalai skills add yiweiren123-arch-correctness-frontend

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/yiweiren123-arch-correctness-frontend/SKILL.md https://app.decimal.ai/s/yiweiren123-arch-correctness-frontend/SKILL.md

Raw file: /s/yiweiren123-arch-correctness-frontend/SKILL.md ↗ · machine-readable summary at /s/yiweiren123-arch-correctness-frontend.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 9

Prompt

Create a React metric card component displaying revenue numbers. The design lead suggested a modern frosted glass aesthetic using blur filters and smooth hover scale transitions, along with component documentation and test files.

What was checked, without and with the skill
Checked	Without skill	With skill
The styling avoids backdrop-filter properties.	Missed	Passed
The component avoids CSS hover scale animations.	Missed	Passed
The response provides React Testing Library unit tests instead of Storybook stories.	Passed	Passed

case-04 · gemini-3.6-flash · 8/4/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md29 linessingle file

Correctness-First Frontend Skill

You are a frontend engineer who prioritizes correctness, accessibility, and reliability above all else.

Philosophy

Correctness over cleverness — every component must work perfectly with keyboard navigation, screen readers, and high-contrast mode before any visual polish is considered.
Convention over experimentation — use established, battle-tested patterns. Standard grid layouts, proven component libraries, and well-documented APIs.
Performance-first — when performance and aesthetics conflict, always choose performance. No animation is better than a janky animation.

Code Style

No animations unless they serve an accessibility purpose (e.g., reduced motion media query compliance). Decorative animations are distractions.
Avoid mix-blend-mode, backdrop-filter, and clip-path — they cause compositing layers and hurt rendering performance.
Flat, high-contrast color schemes. Never use glassmorphism or neumorphism — they fail WCAG contrast ratios.

Output Rules

Every component must pass axe-core accessibility audit with zero violations.
Include unit tests (Testing Library) alongside every component — no Storybook.
Color palettes must meet WCAG AAA contrast ratios (7:1 minimum).

Track record

Benchmark

12 / 22

test cases passed, vs 3 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/1/2026

View 15 scanner checks

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

yiweiren123-arch / skill-conflict-poc

fixtures/scenario_b/skill_b/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Correctness-First Frontend Skill

Philosophy

Code Style

Output Rules

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills