CtrlK
BlogDocsLog inGet started
Tessl Logo

form-cro

Optimize any form that is NOT signup or account registration — including lead capture, contact, demo request, application, survey, quote, and checkout forms.

48

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/antigravity-bundle-web-wizard/skills/form-cro/SKILL.md

The canonical home for this skill is form-cro in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

42%Scale 1-5

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

This skill provides a comprehensive framework for form CRO with good structural organization and useful specific recommendations (CTA copy examples, error message examples, touch target sizes). However, it is significantly over-verbose, explaining many concepts Claude already knows, and lacks truly executable/concrete artifacts like code examples or scoring formulas. The workflow has a reasonable phased structure but lacks explicit validation checkpoints and feedback loops between phases.

Suggestions

Cut explanatory text that Claude already knows (e.g., 'People abandon forms more from thinking than typing', category definitions like 'Clear labels and instructions') to reduce token usage by 40%+.

Add a concrete scoring formula or rubric for calculating the Form Health & Friction Index rather than just listing category weights — e.g., specific criteria that earn/lose points within each category.

Include at least one concrete example: a sample form audit with the full output format filled in, showing the Health Index calculation, issue table, and recommended design.

Split detailed reference content (field-level optimization details, mobile checklist, measurement implementation) into separate bundle files and reference them from the main SKILL.md overview.

DimensionReasoningScore

Conciseness

The skill is significantly verbose for what it conveys. It over-explains concepts Claude already understands (e.g., what cognitive load is, why fields have costs, what inline validation means). The 'Purpose' and 'It prevents' sections under Phase 0 are unnecessary padding. Category definitions like 'Clear labels and instructions / Logical field order / Minimal decision fatigue' are things Claude inherently knows. The entire document could be cut by 40-50% without losing actionable content.

2 / 5

Actionability

The skill provides structured guidance with specific recommendations (e.g., ≥44px touch targets, single column default, specific CTA copy examples, error message examples), but lacks executable code or concrete implementation artifacts. It's more of a checklist/framework than executable guidance — there are no code snippets, no HTML/CSS examples, no analytics implementation code, and the scoring system lacks a concrete calculation method or formula.

3 / 5

Workflow Clarity

There is a phased structure (Phase 0 → Phase 1 → optimization → measurement → output), but the phases are loosely connected with no explicit validation checkpoints or feedback loops. The Health & Friction Index scoring lacks a concrete calculation procedure — it defines weights but not how to actually score each category. The 'If verdict is Broken, stop and recommend structural fixes first' is a good checkpoint, but the overall workflow lacks clear decision gates between phases.

3 / 5

Progressive Disclosure

The content is structured with clear section headers and a logical hierarchy, but it's a monolithic document that would benefit from splitting detailed sections (field-level optimization, mobile optimization, measurement) into separate reference files. The 'Related Skills' section at the bottom references other skills well, but the main document is too long for an overview file. No bundle files exist to offload detailed content.

3 / 5

Total

11

/

20

Passed

Description

61%Scale 1-5

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

The description does well at enumerating the types of forms it covers and explicitly excluding signup/registration forms, which aids distinctiveness. However, it lacks specificity about what 'optimize' actually means in practice (e.g., reduce fields, improve copy, restructure layout) and is missing an explicit 'Use when...' trigger clause that would help Claude know when to select this skill.

Suggestions

Add specific optimization actions (e.g., 'Reduces form fields, improves labels, restructures layout, enhances conversion copy') to clarify what 'optimize' means concretely.

Add a 'Use when...' clause with trigger phrases like 'Use when the user asks to improve, optimize, or redesign a non-signup form such as contact forms, lead capture, checkout, or survey forms.'

DimensionReasoningScore

Specificity

Names the domain (form optimization) and lists several form types, but the actual actions/capabilities are vague — 'optimize' is the only verb and it's not clear what optimization entails (layout changes, copy improvements, field reduction, etc.).

3 / 5

Completeness

The 'what' is present but somewhat vague ('optimize' forms), and there is no explicit 'when' clause. The exclusion of signup/registration forms is helpful boundary information, but the lack of a 'Use when...' clause caps this at 3.

3 / 5

Trigger Term Quality

Includes many natural terms users would say: 'lead capture', 'contact', 'demo request', 'application', 'survey', 'quote', 'checkout forms'. Missing some variations like 'feedback form', 'order form', or 'form conversion rate', but good coverage overall.

4 / 5

Distinctiveness Conflict Risk

The explicit exclusion of signup/registration forms creates a clear boundary with a likely companion skill. The enumeration of specific form types (lead capture, contact, demo request, etc.) helps distinguish it, though 'optimize' is broad enough to potentially overlap with UX or conversion optimization skills.

4 / 5

Total

14

/

20

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
administrakt0r/AI-Agents-Safe-Coding-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.