AC Svelte
Builds, debugs, and reviews Svelte and SvelteKit apps: runes, stores, snippets, load functions, form actions, adapters. Use when the UI does not update after a state change, an effect loops forever ("effect_update_depth_exceeded"), props or bindings stop reacting, a Map or class field is not tracked, state leaks between users on the server, "window is not defined" breaks the build, markup mismatches on hydration, data stays stale after a mutation, a form action does nothing or returns 403, scoped CSS is pruned as an unused selector, transitions never fire, or a Node, Vercel, Cloudflare, or static adapter build fails. Also for migrating Svelte 4 to Svelte 5 runes, converting export let to $props, $: to $derived, createEventDispatcher to callback props, slots to snippets and on:click to onclick, typing props and route data in TypeScript, testing components with Vitest or Playwright, and cutting bundle size and rerender cost. Not for Vue or Nuxt, React, or plain browser JavaScript semantics.
As a process C 64/100 · Has gaps — 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: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 64/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 11 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web, node) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4633 tokens
- 100Steps. 51 steps
- 100Failures and branches. 4 branches, has a failure section
- 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 13 top-level sections: this looks like several domains in one skill
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
- +3Description length 1003: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 13 headings
- +3Step-by-step instructions: 51 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.