CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

skillhub-design

SkillHub 页面、主题和组件视觉工作的入口。读取仓库随附的主题、完整组件契约、设计规范和实际 React API,按需加载并核对正文完整性。

Quality

72%

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 ./.agents/skills/skillhub-design/SKILL.md
SKILL.md
Quality
Evals
Security

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 a lean, highly actionable dispatch document: exact spec paths, a copy-paste verification command, per-task reading branches, and an explicit re-read feedback loop for missing or truncated sources. Its main weaknesses are the unresolved script references (the bundle contains no scripts/ directory) and slight redundancy in the body-verification rules. Workflow ordering is discernible but requires the reader to interleave task-type and process bullets.

Suggestions

Ship the referenced scripts in the skill bundle (scripts/read-design-system.py, scripts/read-context.py) or rewrite the paths to wherever they actually resolve, so the navigation promises in the body are fulfillable.

Show one full example invocation of scripts/read-design-system.py (with typical arguments) matching the level of detail already given for the read-context.py check command.

Consolidate the body-integrity verification rules stated in both the 检查 bullet and the closing paragraph into a single location.

DimensionReasoningScore

Conciseness

The ~20-line body is dense and imperative with no explanation of concepts Claude already knows (uses 'contractData', '受控状态' without elaboration), but the body-integrity verification rule is repeated across the 检查 bullet ('只读审查同样核对必需正文') and the closing paragraph ('核对正文送达…替代当前完整正文'), a minor redundancy that could be trimmed — anchor 4, not the fully lean anchor 5.

4 / 5

Actionability

Gives exact paths ('.trellis/spec/frontend/index.md', 'web/src/index.css', 'web/tailwind.config.ts') and a copy-paste command ('python3 scripts/read-context.py check --source .trellis/spec/frontend/design-system.md'), but 'scripts/read-design-system.py' is named without a full invocation and how to read component contractData is left unspecified — concrete commands with minor gaps, fitting anchor 4.

4 / 5

Workflow Clarity

A sequence is present ('先读…' then per-task reads, then '检查' with engineering checks and browser acceptance) with an explicit validation checkpoint (read-context.py check) and a feedback loop ('来源缺失、截断或变化时先补读'), but task-type bullets (主题/组件/页面) are interleaved with process bullets (读取/检查), so the reader must assemble the global order — anchor 4 rather than 5.

4 / 5

Progressive Disclosure

The body is short and organized with a deliberate on-demand loading design ('按任务选择…逐页补齐'), but the referenced 'scripts/read-design-system.py' and 'scripts/read-context.py' do not exist in the skill bundle (no scripts/ directory present), and the detailed content lives in repo-external '.trellis/' paths rather than bundled references — structure exists but navigation does not fully resolve, fitting anchor 3.

3 / 5

Total

15

/

20

Passed

Description

61%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 domain-specific and reasonably concrete about what it reads, anchored by the distinctive 'SkillHub' name, but it completely lacks any 'use when' trigger guidance, which both caps completeness and weakens its usefulness for skill selection. Keyword coverage is good though missing common synonyms like 'UI' or '样式'.

Suggestions

Add an explicit trigger clause, e.g. 'Use when working on SkillHub pages, themes, or component styling/UI changes' (使用本 Skill 当任务涉及 SkillHub 页面、主题或组件的视觉/UI 改动时).

State at least one concrete deliverable action beyond reading/verifying inputs, e.g. 'implements or reviews visual changes' rather than only describing what is read.

Include common synonym terms users would say, such as 'UI', '样式', or 'CSS', alongside 页面/主题/组件.

DimensionReasoningScore

Specificity

Names the domain ('SkillHub 页面、主题和组件视觉工作的入口') and concrete input actions ('读取仓库随附的主题、完整组件契约、设计规范和实际 React API', '按需加载并核对正文完整性'), but all actions are reading/verifying inputs — the actual deliverable actions of the visual work are never made concrete, matching anchor 3 rather than 4.

3 / 5

Completeness

The 'what' is reasonably clear (entry point that reads and verifies design resources), but there is no 'Use when…' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines — it is not a 4 because 'when' is entirely absent rather than just imprecise.

3 / 5

Trigger Term Quality

'页面', '主题', '组件', '视觉', '设计规范', 'React' are exactly the natural terms a user would say for this work, giving good keyword coverage; common synonyms like 'UI', '样式', or 'CSS' are missing, so it fits anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

The named project 'SkillHub' plus scoping to visual work gives a clear niche with minimal conflict risk against unrelated skills, but '视觉工作' broadly spans pages, themes, and components and could overlap with a closely related frontend skill, fitting anchor 4 rather than 5.

4 / 5

Total

14

/

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

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Repository

iflytek/skillhub

Path

.agents/skills/skillhub-design/SKILL.md

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.