CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ipollowork-plugin-ui

为 iPolloWork 新插件或插件工作区复用 UI 组件、颜色、字体及交互规范。按 Figma 成熟状态和代码清单优先采用已确认组件,区分宿主 React 与独立 HTML/iframe 的接入方式;适用于插件表单、导航、浮层、反馈、状态和进度设计及实现,不改变用户作品的视觉风格。

Quality

78%

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 ./.codex/skills/ipollowork-plugin-ui/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

An information-dense, well-referenced body that gives precise, executable repo-specific guidance with real validation checkpoints and a genuine one-level reference structure. Its weaknesses are token efficiency — inline version/date minutiae and run-on paragraphs that belong in references — and the lack of an explicitly ordered top-level workflow.

Suggestions

Move the per-component minor-version requirements (Badge 5, form controls 6, table composition 7, resource cards 8) and the date-stamped verification records (2026-10-10 identity checks, 历史1.2整合记录) into references/plugin-contract.md or a dedicated changelog section, keeping only the current runtime version and one example call in SKILL.md.

Break the run-on paragraph in 固定接入规则 · v1 into a short list or table (entry, iframe rule, build mode, version check) so each rule is scannable instead of embedded in a wall of text.

Replace the repeated unspecified "共享包 README" pointer with the actual file path, and add one minimal copy-paste sample of the standard host-React and iframe import patterns.

DimensionReasoningScore

Conciseness

Almost every token is repo-specific fact rather than explanation of known concepts, which is efficient in kind, but the body is packed with time-sensitive details — runtime version "1.8.0", per-component minor requirements (5, 6, 7, 8), and date-stamped verification notes ("2026-10-10 核对", "历史1.2整合记录") — inline rather than in a reference or dedicated changelog section. The run-on paragraph in 固定接入规则 mixing entry rules, version negotiation, and status bookkeeping clearly could be tightened, matching anchor 3 rather than 4.

3 / 5

Actionability

Guidance is highly concrete and executable: exact import paths (`@/components/ui/*`, `@ipollowork/ui/controls`, `requireRuntime(1)`), exact API call signatures (`requireRuntime(1, ['Badge', 'Icon'], 5)`), exact token values (#1FBAC0, 32px/28px, 14/16/20px), and per-use-case component decision rules (Select vs Autocomplete vs RadioGroup). It stays below anchor 5 because a few pointers lack explicit paths ("共享包 README" appears several times with no file path) and there is no minimal copy-paste sample of the standard host-React import, though per the scoring notes the absence of code blocks per se is not penalized for an instruction-only skill.

4 / 5

Workflow Clarity

A clear implicit sequence runs through section order: determine environment → read the contract's entry/build/version sections → select components by evidence tier (推荐/待验证/候选/历史) → apply colors/typography/interaction constraints → implement → verify, with explicit validation checkpoints ("实施前按共享包README的固定验收矩阵列出本次适用状态", "旧版本或缺组件时停止初始化并提示更新客户端", "校验真实选择值、草稿保留和重试写盘"). Not a 5 because the global ordering must be inferred from section order — there is no single ordered workflow listing — and some checkpoints are scattered across sections.

4 / 5

Progressive Disclosure

The body is an overview with one-level-deep, well-signaled references that all exist in the bundle: references/plugin-contract.md (with section anchors like #主题与-token), references/component-catalog.md, and references/component-mapping.json hold the bulk detail (202/291/901 lines). Minor gaps: dense inline blocks such as the full 资源卡复用 spec and per-component minor-version requirements could live in the contract or catalog, and several repo files (docs/, evals/, examples/) are cited without verifying their placement for a reader landing in the skill directory.

4 / 5

Total

15

/

20

Passed

Description

78%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 strong, third-person description that clearly states what the skill does and when it applies, with good natural trigger vocabulary and near-zero conflict risk. Its main gap is that the 'when' clause enumerates domains rather than mirroring phrases a user would actually type.

DimensionReasoningScore

Specificity

The description names several concrete capability areas — "复用 UI 组件、颜色、字体及交互规范", "插件表单、导航、浮层、反馈、状态和进度设计及实现" — plus a concrete selection rule ("按 Figma 成熟状态和代码清单优先采用已确认组件") and two integration modes. It sits between anchor 4 and 5: broad and concrete coverage, but a couple of actions (component selection workflow, environment distinction) are stated abstractly rather than enumerated as done-for-you actions.

4 / 5

Completeness

Both 'what' and 'when' are explicitly present: what — reuse UI components, colors, typography, and interaction specs; when — "适用于插件表单、导航、浮层、反馈、状态和进度设计及实现". It is not a 5 because the 'when' clause enumerates design domains rather than phrasing concrete user triggers (e.g., 'when the user asks to build a plugin form or restyle plugin controls').

4 / 5

Trigger Term Quality

Natural terms a user would say are present: 插件 (plugin), UI, 组件, 表单 (forms), 导航 (navigation), 浮层 (overlay), 反馈 (feedback), 状态 (status), 进度 (progress), plus the product name iPolloWork. A few natural synonyms are missing (e.g., 对话框/弹窗/dialog, 按钮/button, 样式/主题 are absent), keeping it just below the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

It is tightly scoped to "iPolloWork 新插件或插件工作区" UI component reuse with a stated boundary ("不改变用户作品的视觉风格"), giving it a clear niche with distinct triggers and minimal overlap with generic UI or code-quality skills.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Devin-AXIS/iPolloWork

Path

.codex/skills/ipollowork-plugin-ui/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.