Design forms that convert, validate well, resist spam, and integrate cleanly with downstream systems. Use this skill when designing or auditing any form (contact, signup, checkout, multi-step, embedded), planning validation logic, fighting spam, choosing form tooling, or improving form conversion. Triggers on form design, form validation, form conversion, multi-step form, form spam, captcha, honeypot, form abandonment, signup form, contact form. Also triggers when form completion rates are low or spam is overwhelming.
67
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
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 an excellent skill description that clearly articulates what the skill does, when to use it, and includes comprehensive trigger terms covering both specific keywords and problem-based scenarios. It uses proper third-person voice, is well-structured, and carves out a distinct niche around form design and optimization that would be easy for Claude to distinguish from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Design forms that convert, validate well, resist spam, and integrate cleanly with downstream systems.' It also mentions specific sub-tasks like planning validation logic, fighting spam, choosing form tooling, and improving form conversion. | 3 / 3 |
Completeness | Clearly answers both 'what' (design forms that convert, validate, resist spam, integrate with downstream systems) and 'when' (explicit 'Use this skill when...' clause with detailed trigger scenarios, plus a 'Triggers on' list and problem-based triggers). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'form design, form validation, form conversion, multi-step form, form spam, captcha, honeypot, form abandonment, signup form, contact form.' Also includes problem-based triggers like 'form completion rates are low or spam is overwhelming.' | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to form design and related concerns (validation, spam, conversion, tooling). The specific mention of form types (contact, signup, checkout, multi-step, embedded) and form-specific concepts (honeypot, captcha, form abandonment) make it highly distinctive and unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, well-structured form strategy skill with a clear framework (5 dimensions) and a well-sequenced 8-step workflow. Its main weaknesses are length (could be more concise by moving failure patterns and detailed dimension guidance into reference files) and lack of executable code examples for key concepts like honeypot fields, validation patterns, and autocomplete attributes. The cross-referencing to other skills is a strength.
Suggestions
Add concrete code snippets for key patterns: a honeypot field HTML example, a blur-validation JavaScript snippet, and autocomplete attribute usage in a form element.
Move the 'Failure patterns' section to a reference file (e.g., `references/form-antipatterns.md`) and summarize the top 3-4 in the main skill to reduce length.
Consider condensing the 5 dimensions section by removing guidance Claude likely already knows (e.g., 'single column layouts', 'labels above inputs') and focusing on the decision rules and non-obvious recommendations.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is generally well-written and avoids explaining basic concepts Claude already knows, but it's quite long (~250 lines) with some sections that could be tightened. The failure patterns section, while useful, is verbose and could be condensed into a table. Some guidance (e.g., 'labels above inputs beat placeholders') is common UX knowledge that Claude likely already knows. | 2 / 3 |
Actionability | The skill provides concrete, specific guidance (e.g., 'validate on blur not keystroke', 'honeypot + time check + Turnstile') and clear decision rules for field strategy. However, it lacks executable code examples—no HTML snippets for honeypot fields, no validation code, no autocomplete attribute examples in context. For a form strategy skill this is more instructional than code-heavy, but concrete implementation examples would strengthen it. | 2 / 3 |
Workflow Clarity | The 8-step workflow is clearly sequenced with logical progression from audit → define success → cut fields → spam defense → validation → accessibility → test downstream → monitor. Step 7 includes explicit verification/testing of downstream integrations, and Step 4 includes a monitor-and-tune feedback loop. The multi-step form guidance includes state preservation and per-step validation. | 3 / 3 |
Progressive Disclosure | The skill references a checklist file (`references/form-anatomy-checklist.md`) and cross-references other skills (`cro-optimization`, `accessibility-audit`, `email-deliverability`), which is good. However, the bundle file doesn't actually exist (no bundle files provided), and the main document is quite long—the failure patterns section and parts of the 5 dimensions could be split into reference files to keep the main skill leaner. | 2 / 3 |
Total | 9 / 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
8e70d03
Table of Contents
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.