CtrlK
BlogDocsLog inGet started
Tessl Logo

pencil-design

使用 Pencil MCP 创建/编辑 .pen 设计文件,或导出为 React 代码。 Use when: 设计 UI、编辑 .pen 文件、从设计稿生成代码。 Not for: 纯代码实现(无设计稿)、非 Pencil 工具的设计工作。 Output: .pen 设计文件 或 React/Tailwind 组件代码。

70

Quality

86%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 highly actionable, well-sequenced design skill with strong validation feedback loops and a useful Common Mistakes table. The main weakness is progressive disclosure: the single referenced shared file does not exist and no bundle structure is present.

Suggestions

Fix or remove the broken reference to `../.cat-cafe-shared-refs/in-context-observability-checklist.md` — it does not exist in the workspace; either inline the checklist content or ensure the file is bundled and the path resolves.

Consider moving the per-tool API details (the Mode A tool table and key limits) into a references/ file linked from a short overview, reducing SKILL.md length and improving one-level-deep navigation.

Trim the narrative failure-story asides (F076, F174) into one-line rules so the body stays lean and every token earns its place.

DimensionReasoningScore

Conciseness

Dense and actionable, assuming Claude's competence with no padding of basic concepts, but includes a few narrative lesson-stories (F076, F174 '明厨亮灶') that could be trimmed, keeping it just below the lean anchor 5.

4 / 5

Actionability

Provides copy-ready concrete guidance: a specific MCP tool table, exact commands (`git rev-parse --show-toplevel`), a precise file-naming convention, and a path template — fully executable for the common cases per anchor 5.

5 / 5

Workflow Clarity

A fully sequenced workflow with explicit validation (get_screenshot → 并排对比 → 风格一致?), feedback loops (不一致/否决 → 修正 → 重新 batch_design), and a Common Mistakes checklist, satisfying the anchor 5 criteria for batch operations.

5 / 5

Progressive Disclosure

Section structure is good and the body is reasonably sized, but the only external reference (`../.cat-cafe-shared-refs/in-context-observability-checklist.md`) does not exist in the workspace and there are no bundle directories, so navigation cannot be verified and structure is only adequate.

3 / 5

Total

17

/

20

Passed

Description

87%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-structured, specific description that explicitly covers what, when, and not-for boundaries with natural trigger terms. It is slightly short of fully comprehensive action and keyword coverage.

DimensionReasoningScore

Specificity

Names the Pencil/.pen domain and several concrete actions (create/edit .pen files, export to React code, output .pen or React/Tailwind components), but coverage is not fully comprehensive — missing analysis/review actions — placing it at anchor 4 rather than 5.

4 / 5

Completeness

Explicitly answers both 'what' (create/edit .pen files, export React code) and 'when' ('Use when: 设计 UI、编辑 .pen 文件、从设计稿生成代码') with concrete trigger phrases, matching the anchor 5 example.

5 / 5

Trigger Term Quality

Includes natural terms users would say ('pencil', '.pen 文件', '设计稿', '设计 UI') plus the file extension, giving good keyword coverage, though it stops short of comprehensive synonyms and variations for a 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (Pencil MCP / .pen files) with distinct triggers and an explicit 'Not for' clause excluding non-Pencil design and pure code work, giving minimal conflict risk per anchor 5.

5 / 5

Total

18

/

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.

Validation15 / 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
zts212653/clowder-ai
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.