AB tailwindcss
Writes and debugs Tailwind CSS: utility classes, theme config, dark mode, variants, plugins, and build setup. Not for CSS mechanics themselves — stacking contexts, flex sizing, and cascade behavior belong to the `css` skill. Use when a class produces no CSS, when dynamically built names (`bg-${color}-500`) never render, when styles work in dev but vanish after deploy, when your own CSS beats a utility or can't override one, when `@apply` breaks inside a Vue, Svelte, or CSS-module file, when `hover:`, `group-hover:`, `peer-*`, `has-[…]`, or `dark:` won't fire, when upgrading v3 to v4 (`@tailwind` directives, `tailwind.config.js` → `@theme`, renamed utilities), when adding custom colors, spacing, breakpoints, fonts, or keyframes, when wiring Tailwind into Vite, Next.js, Astro, SvelteKit, Rails, or Laravel, when the CSS bundle is huge or rebuilds crawl, when Preflight flattens third-party widgets, or when choosing between `@apply`, a component, and `tailwind-merge`.
As a process B 67/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 67/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 7 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 70Execution cost. Instruction body is 4914 tokens
- 100Tools and files. No external tools needed
- 100Steps. 58 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 977: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 58 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.