BC impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or…
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
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 · 4
✓ No critical or high findings
Medium and low: 4
-
medium Exfiltration
net-credential-usescripts/live-browser.js:4067Credential used in a network call (verify the destination is the intended service)fetch(`http://localhost:${PORT}/design-system.json?token=… { cache: 'no-store' }), -
medium Exfiltration
net-credential-usescripts/live-browser.js:4068Credential used in a network call (verify the destination is the intended service)fetch(`http://localhost:${PORT}/design-system/raw?token=… { cache: 'no-store' }), -
low Exfiltration
exfil-secret-in-urlscripts/live-browser.js:4067Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)fetch(`http://localhost:${PORT}/design-system.json?token=… { cache: 'no-store' }),placeholder -
low Exfiltration
exfil-secret-in-urlscripts/live-browser.js:4068Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)fetch(`http://localhost:${PORT}/design-system/raw?token=… { cache: 'no-store' }),placeholder
Files scanned: 52. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 56): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 40Consistency. Frontmatter name (impeccable) differs from the folder (frontend-design-polish)
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 100Steps. 30 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 3197 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (5 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 895: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -311 of 14 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 15 headings
- +3Step-by-step instructions: 30 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (25 of 35)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.