web-prototype

General-purpose desktop web prototype. Single self-contained HTML file built by copying the seed `assets/template.html` and pasting section layouts from `references/layouts.md`. Default for any landing / marketing / docs / SaaS page when no more specific skill matches.

Quality

83%

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

Quality

Content

92%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.

The body is an exemplary overview: a tight imperative workflow (Steps 0-5) with real validation checkpoints and user-feedback loops, concrete executable guidance throughout, and well-signaled one-level-deep references to bundle files that all exist and match their advertised contents. The only weakness is mild verbosity in the imagery rules, which could be trimmed without losing clarity.

Dimension	Reasoning	Score
Conciseness	The body is imperative and directive throughout with no explanations of concepts Claude already knows — it assumes competence ("The seed already encodes good defaults ... Your job is to compose it"). Anchor 4 rather than 5 because the imagery hard rules run long with layered conditionals ("For a named real-world referent ... prefer suitable fetched real photography and use image generation only as a fallback") that could be tightened.	4 / 5
Actionability	Fully executable instruction-only guidance: exact file paths, concrete operations ("Replace the six `:root` variables", "the seed's media query at 920px", "`data-od-id` on every `<section>`"), and it points to verified copy-paste-ready material — the 8 paste-ready section skeletons and class inventory confirmed present in `references/layouts.md`. This is the copy-paste-ready anchor.	5 / 5
Workflow Clarity	Steps 0-5 are clearly sequenced with explicit validation checkpoints and feedback loops: mandatory pre-flight reads, "State the chosen list in one sentence to the user before writing" so they can redirect, and "Every P0 item must pass before you move on" against the real P0/P1/P2 checklist in `references/checklist.md`. Not anchor 4, because both a validation step and a user feedback loop are explicit, not implicit.	5 / 5
Progressive Disclosure	The body is a lean overview with a resource map, and its references are one level deep, well-signaled, and all real: `assets/template.html`, `references/layouts.md` (verified to contain the advertised 8 skeletons and class inventory), and `references/checklist.md` (verified P0/P1/P2 structure). Content is appropriately split with nothing that belongs in a bundle file inlined.	5 / 5
	Total	19 / 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.

The description clearly answers both what the skill does and when to use it, with concrete, verifiable actions and useful natural keywords. Its main weakness is that it deliberately positions itself as a broad general-purpose fallback, which raises overlap risk with more specific web/page skills, and the action list is minimal rather than comprehensive.

Suggestions

Enumerate the concrete build actions in the description (e.g., 'build a single self-contained HTML page: copy the seed, swap design tokens, paste section layouts, self-check against a P0/P1/P2 checklist') to lift specificity above the 1-2-action level.

Fold one or two high-frequency natural trigger words from the `triggers` list (e.g., 'mockup' or 'homepage') into the description text itself so keyword coverage does not depend on a separate field.

Narrow the claimed default territory slightly or name the specific skill families it defers to (e.g., 'use before dataviz or brand-specific skills') to reduce catch-all overlap risk.

Dimension	Reasoning	Score
Specificity	The description names the domain ("General-purpose desktop web prototype") and exactly two concrete actions ("copying the seed `assets/template.html`" and "pasting section layouts from `references/layouts.md`"). This matches the anchor for 1-2 concrete actions without comprehensive coverage; anchor 4 would require several enumerated actions.	3 / 5
Completeness	It explicitly answers both questions: the 'what' ("Single self-contained HTML file built by copying the seed ... and pasting section layouts") and the 'when' with concrete trigger phrases ("Default for any landing / marketing / docs / SaaS page when no more specific skill matches"). Not anchor 4, because the 'when' clause is fully explicit rather than merely present.	5 / 5
Trigger Term Quality	The description itself contains natural terms users would say — "web prototype", "landing", "marketing", "docs", "SaaS page" — giving good keyword coverage. A few natural variations ("mockup", "homepage", "website") appear only in the separate `triggers` field, not the description, so coverage is not comprehensive.	4 / 5
Distinctiveness Conflict Risk	"General-purpose" and "Default for any landing / marketing / docs / SaaS page" claim broad catch-all territory that overlaps with more specific page-building, branding, and docs skills. The fallback clause ("when no more specific skill matches") mitigates but does not eliminate the overlap, matching the 'somewhat specific but could still overlap' anchor.	3 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: nexu-io/open-design
Path: design-templates/web-prototype/SKILL.md
Commit: 1b47e60

Reviewed: 3 days 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.