AD fabrica-design-md
Use when someone asks to build a brand design system file, extract their visual identity, or create a DESIGN.md. Dispara con "hazme mi DESIGN.md", "arma mi sistema visual", "extrae mi identidad de marca", "quiero que todo lo que haga con IA se vea mío", "mis diseños salen genéricos", "define mi paleta y mi tipografía", "crea el archivo de marca", "design system para mi negocio". EXTRAE el sistema de las piezas que ya le funcionan a la persona (capturas, código de su web, o entrevista si no tiene archivos) en vez de inventarlo o copiar el de otra marca. Mide el contraste en vez de estimarlo, entrega el DESIGN.md y una página de prueba con el sistema aplicado y medida en móvil. NO usar para diseñar una pieza suelta ni para auditar accesibilidad de una página ya hecha.
md. Dispara con "hazme mi DESIGN.md", "arma mi sistema visual", "extrae mi identidad de marca", "quiero que todo lo que haga con IA se vea mío", "mis diseños…
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 46/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 100Steps. 27 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2534 tokens
- 100Running it twice. No mutating operations
- low 15 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
- +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
- +5Description quotes 8 example trigger phrases
- +3Description length 776: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 27 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.