Borrowing it
Nothing to install: this file belongs to Dynokostya/just-works. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Dynokostya/just-works/main/.claude/skills/tailwind-css-coding/SKILL.mdgit clone --depth 1 https://github.com/Dynokostya/just-worksWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dynokostya/just-works/tailwind-css-coding)<a href="https://agentmods.dev/skills/dynokostya/just-works/tailwind-css-coding"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/tailwind-css-coding/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dynokostya/just-works/tailwind-css-coding"><img src="https://agentmods.dev/badge/skills/dynokostya/just-works/tailwind-css-coding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 60 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.01477 |
| Opus 5.5 | $0.00020 | $0.00591 |
| Sonnet 5.5 | $0.00010 | $0.00295 |
| Haiku 4.5 | $0.00005 | $0.00148 |
Grade A, and why
tailwind-css-coding scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tailwind CSS Coding
Project conventions override these defaults. Read 2-3 nearby components and check the Tailwind version in package.json first. v4 signals: @tailwindcss/postcss or @tailwindcss/vite, @import "tailwindcss", @theme {} blocks. v3 signals: tailwind.config.js, @tailwind base; directives, a separate autoprefixer.
Never rules
- Never construct class names dynamically. The compiler scans source as plain text and never runs code, so
`bg-${color}-500`produces no CSS. Use a lookup map of complete static strings. For truly dynamic values (user-set colors, computed positions) use an inlinestyleprop.
const bgMap = { red: "bg-red-500", blue: "bg-blue-500" } as const;
const cls = bgMap[color];
- Never compose classes by string concatenation. When two utilities set the same property (
p-4 p-6), stylesheet order decides the winner, not class order in the string. Merge withcn()and set one value per property. Do not restate defaults (flex flex-row). - Never use an arbitrary value when a token exists.
p-[16px]isp-4,w-[100%]isw-full,text-[14px]istext-sm. Prefer semantic tokens over raw palette colors when the project defines them (bg-primary, notbg-blue-500); see shadcn-ui-coding. - Never ship interactive elements without states. Buttons need
hover:,focus-visible:,disabled:, andtransition-colors; inputs needfocus:,disabled:,placeholder:; links needhover:andfocus-visible:. Usefocus-visible:rather thanfocus:for buttons and links so mouse clicks show no ring. In v4 also addcursor-pointerto buttons; Preflight no longer sets it. - Never use
@applyfor patterns that can be a component. Reserve it for third-party library overrides, CMS or Markdown HTML, and non-component template languages. - Never leave colors unthemed in a project that supports dark mode. See Dark mode.
- Never read
sm:as "small screens". It means 640px and above; unprefixed utilities apply everywhere. Write mobile styles first, then layer breakpoints upward. - Never skip accessibility. Icon-only buttons need
<span className="sr-only">Label</span>(andaria-hiddenon the icon); skip links usesr-only focus:not-sr-only. Check contrast on hover and focus states in both color schemes.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago Changed · +3 tokens per session 8fcdc2595fed
- 17d ago Changed · -165 lines · -7 tokens per session 2e3236fe4861
- 2mo ago First seen · 256 lines · 55 tokens per session scan A dad8870dee8f
tailwind-css-coding is a skill published in the GitHub repository Dynokostya/just-works (14 stars, last pushed 10d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,477 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
tailwind-css-coding compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tailwind-css-codingDynokostya/just-works | Skill | 14 | 10d ago | Apache-2.0 | A | 51 | Claude Code |
| anti-slop-designsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 34 | Claude Code |
| chakra-ui-builderchakra-ui/chakra-ui | Skill | 41k | yesterday | MIT | A | 214 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | 3d ago | MIT | A | 52 | Codex |
| open-design-setupcompozy/compozy | Skill | 2.8k | yesterday | MIT | A | 67 | Claude Code, Codex |
| edit-sitemicrosoft/power-platform-skills | Skill | 1.1k | yesterday | MIT | A | 104 | Claude Code |
| frontend-visual-qadaymade/claude-code-skills | Skill | 1.5k | yesterday | MIT | A | 125 | Claude Code, Codex |