kami-landing

Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.

Quality

76%

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 ./design-templates/kami-landing/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 skill with concrete tokens, a clear workflow, and a validation checklist. The only meaningful gap is that several referenced files (example.html, README.md, DESIGN.md) are not present in the skill bundle, slightly weakening progressive disclosure and inlined executable guidance.

Suggestions

Include example.html (and README.md) in the skill bundle so the 'mirror the structure of example.html' instruction and the 'Files in this skill' tree resolve to real files.

Inline a minimal canonical index.html skeleton (or a representative component snippet) so the actionability is copy-paste ready even when the external example is unavailable.

Add an explicit 'if a self-check fails, fix and re-run' feedback loop after the checklist to strengthen the validation checkpoint.

Dimension	Reasoning	Score
Conciseness	Lean throughout — every section earns its place via token tables, a language→font mapping table, and a self-check checklist, with no padding explaining HTML/CSS concepts Claude already knows.	5 / 5
Actionability	Highly executable: exact hex tokens, font stacks, a drop-in component-primitive list, the `data-od-id` convention, and a concrete self-check; the main code rendering is deferred to the mirrored example.html rather than inlined, leaving a minor gap.	4 / 5
Workflow Clarity	A clear numbered sequence — Gather brief, Pick language stack, Write index.html, Self-check — with an explicit validation checkpoint (the delivery checklist); not a destructive/batch operation so no cap applies, though an explicit fix-and-retry loop is absent.	4 / 5
Progressive Disclosure	Well-organized sections with one-level-deep references to the design-system DESIGN.md and a 'Files in this skill' tree; however the locally-listed README.md and example.html are not present in the skill bundle and DESIGN.md lives outside it, so some referenced paths don't resolve in-bundle.	4 / 5
	Total	17 / 20 Passed

Description

70%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 specific, distinctive description with strong concrete constraints and a clear niche, weakened only by the absence of an explicit 'when to use' clause inside the description field (mitigated by a separate triggers block). Voice is appropriately imperative/third-person.

Suggestions

Add an explicit 'Use when...' clause naming the trigger situations (e.g., 'Use when producing a white paper, studio one-pager, or editorial landing page in the kami aesthetic') to lift completeness above 3.

Include a file extension or concrete artifact reference (e.g., 'outputs a single .html file') to broaden natural trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Concrete actions and constraints — 'Produce a print-grade single-page kami document', 'One self-contained HTML file, zero dependencies', with specific design tokens (warm parchment canvas, ink-blue accent, serif at one weight) — list several specific actions with only minor coverage gaps.	4 / 5
Completeness	A clear 'what' (produce a print-grade kami one-pager, self-contained HTML) is present, but an explicit 'Use when...' / when clause is absent from the description and only weakly implied by 'white paper or studio one-pager'; the guideline caps a missing when-clause at 3.	3 / 5
Trigger Term Quality	Natural user-facing terms appear — 'white paper', 'studio one-pager', 'print-grade', 'multilingual' — with good but not exhaustive synonym coverage and no file extensions in the description itself.	4 / 5
Distinctiveness Conflict Risk	The 'kami (紙 / 纸)' niche, 'parchment canvas / ink-blue accent / no cool grays', and trilingual scope form a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing, 3 suspicious	Warning

	Total	14 / 16 Passed

Repository: nexu-io/open-design
Path: design-templates/kami-landing/SKILL.md
Commit: 1a7a23d

Reviewed: about 5 hours 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.