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

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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 tight, well-structured instruction-only design skill: lean, highly specific quantitative guidance, a clear sequenced workflow, and a comprehensive validation checklist. Its main gap is the absence of worked examples and an explicit error-recovery feedback loop, plus no reference structure to demonstrate progressive disclosure.

Suggestions

Add one short worked example (e.g., a minimal hero input->processing->publish state sketch) to lift actionability toward 5.

Insert an explicit validate->fix->re-validate feedback loop in the Validate section (e.g., "If a sample is unlabeled or a claim is unverified, fix it and re-check before shipping") to strengthen workflow clarity.

If the state and motion-detail lists grow, move them into a single one-level reference file (e.g., STATES.md) referenced from the body to exercise progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is a lean set of prescriptive bullets that assumes Claude's competence and never explains concepts Claude already knows (no "what a SaaS landing page is" padding); every token earns its place.	5 / 5
Actionability	Guidance is concrete and quantitatively specific ("12-column product grids", "12-16px radii", "160-220ms for control feedback", "one cool signal color"), giving directly applicable specs; it stops short of 5 because there are no worked end-to-end examples demonstrating the common cases.	4 / 5
Workflow Clarity	"Establish the Story" gives a numbered 1-5 sequence and a dedicated "Validate" section provides a thorough checklist (keyboard controls, quota/moderation/network/error states, focus/contrast/zoom); it lacks an explicit validate->fix->retry feedback loop, capping it below 5.	4 / 5
Progressive Disclosure	The skill is self-contained with clean, well-labeled sections and no nested references (no bundle files exist, none are referenced); at ~77 lines it slightly exceeds the under-50-line simple-skill threshold and demonstrates no reference-splitting pattern, so it sits at 4 rather than 5.	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 well-crafted description that names a specific niche, concrete actions, and an explicit "Use for" trigger list covering many relevant scenarios. It is strong across all dimensions but sits just below top marks because its triggers are scenario-oriented rather than the most natural user phrasings.

Suggestions

Add an explicit "Use when the user asks to..." phrasing with natural verbs (e.g., "Use when redesigning a SaaS landing page or building an AI product homepage") to push trigger quality and completeness toward 5.

Include a couple of common synonyms or colloquial triggers users actually say (e.g., "marketing site", "product page", "demo page") to broaden natural keyword coverage.

Lead with the primary concrete action(s) before the scenario list so the "what" reads as a crisp capability statement.

Dimension	Reasoning	Score
Specificity	Names the domain ("SaaS and AI product landing pages") with concrete create/redesign actions and enumerates several specific feature scenarios (product UI in the hero, prompt-to-output stories, audience tabs, compact feature modules, pricing comparisons, FAQ handoffs); stops short of the fully comprehensive action coverage of a 5.	4 / 5
Completeness	It states a clear "what" (create/redesign proof-driven landing pages) and an explicit "Use for..." trigger clause answering "when"; the triggers are concrete but lean more toward scenario labels than the fully natural "when the user asks for X" phrasing of a 5.	4 / 5
Trigger Term Quality	The "Use for..." clause surfaces several natural domain triggers (landing pages, pricing comparisons, FAQ handoffs, feature modules) a designer would plausibly say; a few common synonyms or phrasings are missing, so it falls just below comprehensive.	4 / 5
Distinctiveness Conflict Risk	The proof-driven SaaS/AI landing-page niche is specific and distinct, with only minor overlap risk against broader landing-page or general design skills, fitting "mostly distinct; minor overlap risk."	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

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
Commit: 4c716b5

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.