CB multi-step-form-design
Designing forms with multiple steps, progress indicators, conditional logic, and save-and-resume mechanics. The discipline of breaking complex data collection into stages that respect cognitive load while maintaining completion intent. Honest about kitchen-sink-single-page (overwhelms before the user starts), progress-theater (steps without genuine staging), and genuinely-staged (each step earns its own page) patterns. Triggers on multi-step form, multi-page form, form wizard, signup wizard, lead form, application form, intake form, configurator, onboarding form. Also triggers when a long form is converting poorly, when an audience is dropping off mid-form, or when a multi-step form is being scoped for the first time.
Designing forms with multiple steps, progress indicators, conditional logic, and save-and-resume mechanics.
As a process B 73/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
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: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5215 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "catalog_summary" - note
frontmatter-keyunknown frontmatter key "display_order"
Process rating: all ten parameters 73/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 29 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Failures and branches. 4 branches
- 70Execution cost. Instruction body is 5215 tokens
- 100Tools and files. No external tools needed
- 100Steps. 91 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 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
- +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
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 727: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 91 items
- +4Reference files are cited in the instructions (9 of 9)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.