CtrlK
BlogDocsLog inGet started
Tessl Logo

doc-kami-parchment

Warm parchment canvas (#f5f4ed), monochrome ink-blue accent (#1B365D), one serif family, and editorial-grade typography.

58

Quality

67%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/_official/examples/doc-kami-parchment/SKILL.md

The canonical home for this skill is doc-kami-parchment in nexu-io/open-design

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 dense template spec: every constraint is concrete (hex values, font stacks, line-heights, forbidden effects) and organization is tight. Its only gaps are a few aesthetic-abstraction directives and the lack of any validation checkpoint or minimal HTML skeleton.

DimensionReasoningScore

Conciseness

The body is a lean, dense spec — exact hex values, per-language font stacks with fallbacks, line-height ranges, and explicit prohibitions ("绝不: drop-shadow / blur / 圆角 ≥ 8px / 渐变 / 霓虹色") — with zero padding and no explanation of concepts Claude already knows. Every token earns its place, matching anchor 5.

5 / 5

Actionability

Mostly executable guidance: exact colors, font stacks, Tailwind CDN, single-file HTML, and platform gotchas ("tag 用 solid hex 背景方块 (因为 WeasyPrint 不渲染 rgba 好)"). It falls short of anchor 5 because a few directives remain abstract ("简洁到只有'被印出来'的感觉", "用 CSS 块绘制占位") and no skeleton HTML or concrete code sample is given.

4 / 5

Workflow Clarity

As a simple single-purpose skill (render user content in the template), the doc-type catalog (One-Pager through Changelog) gives an unambiguous selection structure, and the Long Doc entry lays out an internal page sequence. It scores 4 rather than 5 because document-type selection is delegated to judgment ("按用户内容判断") and there is no output validation checkpoint.

4 / 5

Progressive Disclosure

The body is ~31 lines organized into four clearly labeled sections (intent, hard visual signature, document types, design guidelines) with no bundle files present and nothing inlined that belongs elsewhere. Per the rubric, an under-50-line skill with no need for external references scores 5 with well-organized sections.

5 / 5

Total

18

/

20

Passed

Description

48%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 a precise visual specification but reads as a style label rather than a skill description: it never states what the skill does and provides no 'Use when...' trigger guidance, capping completeness and weakening trigger-term quality. Its saving grace is a distinctive aesthetic niche that minimizes conflict risk.

Suggestions

State the action explicitly, e.g. "Renders content as a warm parchment one-pager, report, letter, or resume with monochrome ink-blue accents (#1B365D), one serif family, and editorial-grade typography."

Add a 'Use when...' clause covering the document types the body already supports: "Use when the user asks for a one-pager, long report, letter, resume, changelog, portfolio, or equity report with a printed-paper look."

Include the natural trigger nouns (document, report, letter, resume, one-pager) in the description itself rather than only in frontmatter tags, so they surface at trigger time.

DimensionReasoningScore

Specificity

The description gives concrete visual parameters ("#f5f4ed", "#1B365D", "one serif family") but names no actions at all — it never says what the skill does (render documents in this style). It names the domain with specifics, matching 'names the domain but actions are minimal or generic', and falls short of anchor 3 which requires concrete actions.

2 / 5

Completeness

It has a clear 'what' (the visual signature: warm parchment canvas, single ink-blue accent, one serif family, editorial typography) but no 'when' clause whatsoever, which caps completeness at 3 per the judging guideline. It is not a 4 because the 'when' is not merely implicit — it is entirely absent.

3 / 5

Trigger Term Quality

Some natural terms are present ("parchment", "serif", "editorial", "typography"), but the common nouns users would actually say — document, report, letter, resume, one-pager — are absent from the description (they only appear in frontmatter tags). This matches 'some relevant keywords but missing common variations or synonyms', below anchor 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

The parchment + ink-blue + serif + editorial combination is a narrow, clearly distinguishable visual niche, so overlap risk is minor — matching anchor 4. It is not a 5 because without any trigger phrasing, overlap with generic typography/styling skills remains plausible.

4 / 5

Total

12

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
nexu-io/open-design
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.