CtrlK
BlogDocsLog inGet started
Tessl Logo

tinyvue-develop-spec

tinyvue组件库开发规范

51

Quality

56%

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/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 content is a well-organized, concise overview that correctly indexes work to module directories and signals one-level-deep references, but it provides no executable guidance itself and every referenced ./xxx.skill.md file is missing from the bundle, undermining both actionability and navigation.

Suggestions

Ship the 11 referenced ./xxx.skill.md files (vue, renderless, theme, design, common, icon, i18n-workflow, hooks, directive, utils, testing-guide) so the '参考规范' links resolve.

Add a short numbered development workflow with a validation checkpoint, e.g. 1. write template in packages/vue, 2. write logic in packages/renderless, 3. write styles in packages/theme, 4. run tests in __tests__, 5. validate before committing.

Include at least one concrete, copy-paste-ready example (e.g. the required file layout for a new component) directly in SKILL.md so the skill is actionable even before following a reference.

DimensionReasoningScore

Conciseness

The body is a lean overview/index: '使用时机', '适用场景', and the architecture table each earn their place, and the '重要术语' entries (跨端模板 pc.vue/mobile-first.vue, 无渲染逻辑层 packages/renderless) convey tinyvue-specific domain knowledge Claude does not already have. It matches 'Lean and efficient; assumes Claude's competence; every token earns its place' and is not score 2 because there is no general-knowledge padding.

3 / 3

Actionability

The architecture table gives concrete pointers ('packages/vue', 'packages/renderless', './vue.skill.md'), but the actual executable guidance is deferred to 11 referenced files that do not exist in the bundle, leaving the skill itself without actionable detail. This matches 'Some concrete guidance but incomplete... missing key details' and is not 3 because nothing is copy-paste or directly executable.

2 / 3

Workflow Clarity

The architecture table implies a structural workflow (template→packages/vue, logic→packages/renderless, styles→packages/theme) but no numbered development sequence or validation/verification checkpoint is given. This matches 'Steps listed but... checkpoints missing or implicit' and is not 1 because module organization is present, not 3 because there is no explicit sequenced workflow with validation.

2 / 3

Progressive Disclosure

The body follows the intended progressive-disclosure pattern — a concise overview with a '参考规范' column clearly signaling one-level-deep references to 11 ./xxx.skill.md files — but all 11 referenced files are missing from the bundle, so navigation leads nowhere. Per the guideline to score against the actual bundle structure, the broken references prevent a 3; it is not 1 because the signaling and organization are clear and references are only one level deep.

2 / 3

Total

9

/

12

Passed

Description

47%

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 appropriately niched to the tinyvue component library but is too terse: it names the domain yet describes no concrete actions and omits any 'Use when...' trigger guidance, capping specificity and completeness.

Suggestions

Add concrete actions, e.g. 'tinyvue组件库开发规范:新增/修改 UI 组件、主题、国际化与测试脚本时遵循的目录与编码约定'.

Append an explicit trigger clause such as 'Use when developing, refactoring, or testing tiny vue components, themes, i18n, or test scripts in this repo.'

Include natural trigger terms users would actually say (新增组件、修改组件逻辑、Renderless 模式、主题开发、国际化).

DimensionReasoningScore

Specificity

The phrase 'tinyvue组件库开发规范' names the domain (tinyvue component library) but provides no concrete actions — '开发规范' (development specification) is an abstract noun, not a verb like 'extract', 'fill', or 'merge'. This matches the score-1 anchor 'Vague or no actions; abstract language' and falls below score 2, which requires naming 'some actions'.

1 / 3

Completeness

It states what the skill is (a development specification for the tinyvue component library) but gives no 'when to use' trigger clause, so per the guideline a missing 'Use when...' caps completeness at 2 ('Has what, but when is missing or only implied'). It is not 1 because the 'what' is at least stated, and not 3 because no explicit trigger guidance exists.

2 / 3

Trigger Term Quality

'tinyvue组件库' and '开发规范' are natural terms a developer in this repo would say, but common variations (e.g. '新增组件', '修改组件', 'Renderless', '主题开发') are absent, matching 'Some relevant keywords but missing common variations'. It is not score 3 because coverage of natural trigger phrasings is thin.

2 / 3

Distinctiveness Conflict Risk

Naming the specific product 'tinyvue' carves out a clear niche unlikely to conflict with unrelated skills, matching 'Clear niche with distinct triggers; unlikely to conflict'. It is not 2 because the product-scoped domain is more specific than the generic 'Works with document files' anchor.

3 / 3

Total

8

/

12

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

description_field

'description' is very short (14 chars), consider making it more detailed

Warning

Total

15

/

16

Passed

Repository
opentiny/tiny-vue
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.