CtrlK
BlogDocsLog inGet started
Tessl Logo

design-system-picker

根据风格描述从内置设计系统库中匹配最合适的设计系统,提供设计规范供后续设计工作使用。

53

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./crews/content-producer/skills/design-system-picker/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

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 and concise with genuinely actionable command examples, but its quality is undermined by missing bundle files: the referenced design-systems/ directory and index.json are absent, so the core workflow and pick.sh cannot run as shipped. Validation in the import flow is also only implicit.

Suggestions

Bundle the referenced ./design-systems/ directory with the 15 .md files and index.json the skill promises, or note that they must be generated/seeded before first use.

Add an explicit validation checkpoint to the import flow, e.g. after registering to index.json run ./scripts/pick.sh "<name>" and confirm the new entry appears before declaring success.

Clarify what happens when pick.sh finds no match (current fallback only prints the raw JSON) so the failure path is actionable.

DimensionReasoningScore

Conciseness

The body is lean and information-dense — a command + examples, a compact design-system table, and a concrete import flow — without explaining concepts Claude already knows; nearly every token earns its place.

3 / 3

Actionability

It gives concrete, copy-paste commands and bundles a real pick.sh, but the primary command chain depends on ./design-systems/index.json and .md files that are not present in the bundle, so it cannot execute end-to-end as shipped.

2 / 3

Workflow Clarity

The search and import flows are clearly numbered and sequenced, but validation checkpoints are only implicit ('如果不完整,应基于下载内容补全') rather than explicit validate→fix→retry steps.

2 / 3

Progressive Disclosure

Structure is clean with one-level-deep, clearly signaled references to ./design-systems/<file> and index.json, but those referenced bundle files (15 .md files + index.json) do not actually exist, breaking the promised navigation.

2 / 3

Total

9

/

12

Passed

Description

57%

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 conveys a clear, distinct niche and uses appropriate third-person voice, but it only states 'what' without an explicit 'when to use' trigger and offers just two fairly general actions. Adding a 'Use when...' clause with natural trigger terms would lift the weaker dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when starting a web/UI design task and you need to pick a matching design system or brand style.'

Enumerate more concrete actions (e.g. 'search the built-in library, read the matched DESIGN.md spec, register a custom design system') to raise specificity.

Include natural user-facing terms users would actually say ('品牌风格', '配色方案', '类似 Stripe 的风格') to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain and two actions — '匹配最合适的设计系统' and '提供设计规范' — but these are general rather than a comprehensive list of multiple concrete actions, so it stops short of a 3.

2 / 3

Completeness

It clearly answers 'what' (match a design system, provide specs) but gives no 'Use when...' clause or equivalent explicit 'when' trigger, which caps completeness at 2 per the guidelines.

2 / 3

Trigger Term Quality

Contains relevant terms like '风格描述' and '设计系统' a user might say, but misses common natural variations (e.g. brand names, '配色/风格') and explicit trigger phrasing.

2 / 3

Distinctiveness Conflict Risk

The niche — matching a design system from a built-in library by style description — is specific and unlikely to conflict with other skills; third-person voice is used correctly.

3 / 3

Total

9

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
TeamWiseFlow/xiaobei
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.