BD design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
Anti-slop frontend skill for landing pages, portfolios, and redesigns.
As a process D 46/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, consistency
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 21702 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 128): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 10Execution cost. Instruction body is 21702 tokens: crowds the task out of the window
- 30Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 18 mutating operations with no state check
- 40Consistency. Frontmatter name (design-taste-frontend) differs from the folder (taste-skill)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Steps. 479 steps, 6 vague phrases
- 100Failures and branches. 8 branches, has a failure section
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 18 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (6 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 269: enough signal without eating the budget
- +4Structure: 106 headings
- +3Step-by-step instructions: 479 items
- +4Has examples (7 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.