CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

58

Quality

67%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/multi-step-form-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong, well-crafted skill description that clearly defines its domain (multi-step form design), lists concrete capabilities and design patterns, and provides comprehensive trigger terms covering both explicit keywords and situational use cases. The description is distinctive enough to avoid conflicts with adjacent UI/form skills while being thorough in its coverage of when it should be selected.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and concepts: multiple steps, progress indicators, conditional logic, save-and-resume mechanics, breaking data collection into stages, cognitive load management. Also names specific patterns (kitchen-sink-single-page, progress-theater, genuinely-staged).

3 / 3

Completeness

Clearly answers both 'what' (designing multi-step forms with progress indicators, conditional logic, save-and-resume, cognitive load staging) and 'when' (explicit trigger list plus situational triggers like poor conversion and drop-off scenarios). The 'Triggers on...' and 'Also triggers when...' clauses serve as explicit 'Use when' guidance.

3 / 3

Trigger Term Quality

Excellent coverage of natural terms users would say: 'multi-step form', 'form wizard', 'signup wizard', 'lead form', 'application form', 'intake form', 'configurator', 'onboarding form', 'long form converting poorly', 'dropping off mid-form'. These are highly natural phrases a user would actually use.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive niche focused specifically on multi-step/wizard form design with clear domain-specific triggers. Unlikely to conflict with general form styling, single-page form, or generic UI skills due to the emphasis on staging, progress, and multi-step mechanics.

3 / 3

Total

12

/

12

Passed

Implementation

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill reads more like a comprehensive blog post or handbook chapter than a concise, actionable skill file. Its strengths are strong conceptual frameworks (the three-pattern taxonomy, the 12-consideration checklist, and clear anti-patterns), but it is severely undermined by verbosity—repeating key concepts multiple times, explaining things Claude already knows, and inlining content that should live in the referenced files. The lack of concrete deliverable templates (e.g., a sample form spec, a step-architecture worksheet) limits actionability for a design-oriented skill.

Suggestions

Cut the content by 50-60%: remove the closing section (restates everything), trim the 'what this skill covers' scope section to 3-4 lines, eliminate repeated explanations of the three-pattern taxonomy, and trust Claude to understand concepts like cognitive load and progress bars without explanation.

Add a concrete, copy-paste-ready artifact: a sample multi-step form specification template showing step names, fields per step, conditional logic rules, and validation rules in a structured format (table or YAML) that Claude can adapt for specific use cases.

Move the detailed pattern descriptions (progress indicators, conditional logic, save-and-resume, validation) into the referenced files and keep only the decision criteria and key principles in the main SKILL.md, actually leveraging the progressive disclosure structure already set up.

Add explicit workflow checkpoints: e.g., 'After defining step architecture, apply the coherence test to each step before proceeding to conditional logic design' with a clear pass/fail gate.

DimensionReasoningScore

Conciseness

Extremely verbose at ~300+ lines. Extensively explains concepts Claude already understands (what cognitive load is, what a progress bar is, what validation means). The keystone framing section is repeated multiple times. The closing section restates everything already said. Significant portions could be cut without losing actionable value.

1 / 3

Actionability

Provides structured frameworks, decision criteria, and named patterns (kitchen-sink, progress-theater, genuinely-staged) that give concrete mental models. However, there are no executable code examples, no wireframe specifications, no concrete field-by-field form examples, and no copy-paste-ready templates. The guidance is specific enough to act on but remains at the conceptual/strategic level rather than providing concrete deliverables.

2 / 3

Workflow Clarity

The 12-consideration framework provides a clear checklist, and the step architecture section gives a logical sequence. However, there are no explicit validation checkpoints or feedback loops in the design process itself—no 'test this before proceeding' gates. The drop-off measurement section mentions instrumentation but doesn't sequence it into the design workflow with verification steps.

2 / 3

Progressive Disclosure

References to 9 separate reference files are well-organized and clearly signaled with one-level-deep links. However, no bundle files were provided, so the references point to non-existent content. The main SKILL.md itself is a monolithic wall of text that inlines substantial detail that could have been pushed to the reference files, undermining the progressive disclosure structure it sets up.

2 / 3

Total

7

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
rampstackco/claude-skills
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.