CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

product-proof-saas

Create or redesign SaaS and AI product landing pages where a real workflow, interface, or deterministic demo is the central proof. Use for pale atmospheric shells, product UI in the hero, prompt-to-output stories, audience tabs, compact feature modules, honest pricing comparisons, and FAQ handoffs.

Quality

83%

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

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

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

A well-organized, token-efficient instruction skill with unusually concrete design parameters and a closing validation checklist. Its gaps are the absence of any worked example for the trickier components and the lack of explicit step sequencing or a fix-and-retry loop around validation.

DimensionReasoningScore

Conciseness

The body is a lean set of terse directives with exact values ("Use 160–220ms for control feedback and 420–700ms for interface state changes", "Stagger cards by 45–70ms") and no explanation of concepts Claude already knows. Every line instructs rather than teaches, matching the anchor-5 example of assuming Claude's competence.

5 / 5

Actionability

Most guidance is concrete and executable for an instruction-only skill (12-column grids, 12–16px radii, enumerated UI states, named page sections, explicit state machines), but there is no worked example (e.g., sample markup for the comparison table or audience tabs) and a few directives remain principle-level ("Organize features around user outcomes and audiences"). Not 5 because specific examples do not cover the common cases; not 3 because the guidance is far more concrete than pseudocode-level hints.

4 / 5

Workflow Clarity

A clear section order implies the workflow (Establish the Story → Build the Visual System → Compose the Page → Implement → Motion → Validate) and the Validate section is an explicit checklist covering keyboard, state, honesty, and accessibility checks. Not 5 because steps are not explicitly sequenced and there is no fix-and-retry feedback loop; not 3 because validation checkpoints are present and the sequence is coherent.

4 / 5

Progressive Disclosure

A single-file skill (no references/, scripts/, or assets/ exist) with well-named section headers and no buried or nested references, so navigation is easy. Not 5 because the body is ~77 lines, above the under-50-line exception, and all detail lives inline with no one-level-deep references splitting deeper material.

4 / 5

Total

17

/

20

Passed

Description

75%Weight 40%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.

A solid description that clearly states what the skill builds and includes an explicit Use-for clause with distinctive, design-specific triggers. Its main weakness is that several trigger phrases are internal design vocabulary rather than natural user phrasing, and it does not surface the full scope of the skill's guidance.

DimensionReasoningScore

Specificity

"Create or redesign SaaS and AI product landing pages" names the domain and concrete actions, and the trigger list adds specific scenarios ("product UI in the hero", "honest pricing comparisons", "FAQ handoffs"). Not 5 because it omits several capabilities the body covers (visual system, motion, validation); not 3 because it lists several specific items rather than only 1-2 generic actions.

4 / 5

Completeness

Both parts are present: the "what" ("Create or redesign SaaS and AI product landing pages where a real workflow, interface, or deterministic demo is the central proof") and an explicit "Use for..." clause. Not 5 because the "when" lists design-pattern conditions rather than concrete user-request phrasing like "when the user mentions pricing or wants a landing page redesign".

4 / 5

Trigger Term Quality

Natural terms users would say are present ("SaaS", "AI product", "landing page", "pricing", "FAQ", "hero"), but some trigger phrases are design jargon users would not naturally say ("pale atmospheric shells", "prompt-to-output stories") and common synonyms like "marketing site" or "homepage" are missing. Anchor 4 fits better than 3, which expects clearly weaker keyword coverage.

4 / 5

Distinctiveness Conflict Risk

The product-proof SaaS landing page niche is clearly distinguishable with distinctive triggers ("prompt-to-output stories", "audience tabs"), but it could still overlap with generic landing-page or web-design skills. Anchor 4 (mostly distinct, minor overlap risk) is the best fit.

4 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

MengTo/Skills

Path

agent-skills/web-design/product-proof-saas/SKILL.md

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.