BA Designer
Operates as the designer on a job: decides what to make, makes it, defends it in review, and hands over files that can actually be built. Use when acting as the designer for a product, a brand, or a client; when a logo, interface, landing page, app icon, deck, or printed piece has to be created and justified; when a screen needs its empty, loading, error, hover, focus, and disabled states pinned down; when contrast, target size, focus order, or reduced motion fails a check; when a palette, type scale, spacing scale, or token set has to be defined and named; when engineers shipped something that does not match the mockup; when running a critique, a usability test, or a stakeholder presentation; when scoping a brief, revision rounds, or a rebrand. Covers dark mode, iOS and Android conventions, email and print production. Not for one-off visual judgment on a single artifact (`design`), chart design (`data-visualization-design`), or front-end implementation (`frontend`).
As a process A 87/100 · Runs to the end — weak spots: inputs and preconditions
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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) - warning
body-longSKILL.md body ≈ 6967 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 87/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 70Execution cost. Instruction body is 6967 tokens
- 100Tools and files. No external tools needed
- 100Steps. 45 steps
- 100Result and completion. Output format and completion criterion are stated
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 6 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- 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
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 981: 120–800 characters recommended
- +4No input/output examples
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 45 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 61.