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

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./design-templates/kami-landing/SKILL.md

Quality

Content

71%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 well-organized, concise, and actionable with a strong validation checklist, but it depends on referenced files (example.html, README.md, DESIGN.md) that are missing from the bundle, which breaks the progressive-disclosure model and leaves the canonical copy-paste rendering unavailable.

Suggestions

Ship the referenced bundle files (example.html and README.md) alongside SKILL.md, or inline a minimal complete HTML/CSS template so the skill is actionable without external files that may be absent.

Make the self-check a true feedback loop: after the checklist add "If any check fails, fix the issue and re-run the checklist before delivering" to make the validation/retry cycle explicit.

Either include design-systems/kami/DESIGN.md in the bundle or inline the essential token table the skill says to use, so the "source of truth" it instructs the agent to read is actually reachable.

Dimension	Reasoning	Score
Conciseness	The body is dense and high-signal (concrete tokens, sizes, a language table, a primitive list) and assumes competence without explaining basics, but the editorial intro ("good content on good paper, not modern app UI") and repetition between the self-check and Boundaries sections are minor trims keeping it off 5.	4 / 5
Actionability	It supplies concrete executable spec (hex tokens, px sizes, line-heights, shadow values, breakpoints, a font-stack table, named component primitives), but the canonical copy-paste source (example.html) is referenced rather than inlined and is absent from the bundle, leaving a gap versus fully copy-paste-ready code.	4 / 5
Workflow Clarity	A clear four-step sequence ends in an explicit nine-item self-check validation checklist, but the fix-and-recheck feedback loop is only implicit ("Self-check before delivering" does not state "if a check fails, fix and re-run"), which is a minor validation gap below 5.	4 / 5
Progressive Disclosure	The SKILL.md is well-sectioned and references are clearly signaled (the blockquote naming DESIGN.md as source of truth, the "Files in this skill" list, "See also"), but the declared bundle files example.html and README.md and the critical DESIGN.md token source are not present in the bundle, so the one-level-deep disclosure structure is not actually realized.	3 / 5
	Total	15 / 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.

The description is concrete, specific, and carves a distinctive niche, but it omits any explicit "Use when..." trigger guidance, which caps completeness at 3 and leaves the activation conditions implicit.

Suggestions

Append a "Use when..." clause naming concrete trigger phrases (e.g. "Use when the user asks for a white paper, one-pager, parchment landing page, or print-grade editorial document") so both what and when are explicit.

Broaden trigger terms with common synonyms and the file extension (e.g. "one-pager, single-pager, brochure, .html") to lift trigger-term coverage toward comprehensive.

Lead with the single primary action plus 1-2 more concrete verbs (e.g. "Produce and style a self-contained HTML one-pager") to move specificity from one action toward multiple concrete actions.

Dimension	Reasoning	Score
Specificity	The description gives one concrete action ("Produce a print-grade single-page kami document") plus highly concrete deliverable properties ("warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays", "One self-contained HTML file, zero dependencies"), which is well above the generic score-3 anchor but not a list of multiple distinct actions as required for a 5.	4 / 5
Completeness	It clearly answers "what" but provides no "Use when..." clause or equivalent trigger guidance, so per the rubric cap completeness cannot exceed 3; the "what" is explicit so it is not a 2.	3 / 5
Trigger Term Quality	Natural niche terms are present ("white paper", "studio one-pager", "parchment", "print-grade", "kami"), giving good coverage a user would say, but it stops short of comprehensive synonym/extension coverage (no "brochure", "landing page", or ".html").	4 / 5
Distinctiveness Conflict Risk	The niche is unmistakably distinct ("print-grade single-page kami (\u7d19 / \u7eb8) document", "parchment canvas, ink-blue accent", "not an app UI"), giving minimal overlap 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: d4138ea

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.