CtrlK
BlogDocsLog inGet started
Tessl Logo

build-product-and-tool-interfaces

为浏览器内需要持续操作对象、推进多步状态并产生可检查结果的产品与专业工具设计、实现、重构或诊断完整界面。用于运营与审核工作台、任务流业务产品、创作与编辑工具、分析与管理工具、资产或文件处理器、监控处置台及其目标环境工作流;核心覆盖对象模型、状态机、真实输入输出、专业引擎、错误恢复、信息密度与任务连续性。不用于主要供阅读的内容网站、只展示组件与 token 的设计系统样张、单张数据图或以理解模型为目的的交互演示。

59

Quality

67%

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 ./plugins-dist/design-engine/raven_design/skills/build-product-and-tool-interfaces/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

60%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 thorough, well-structured instruction skill with concrete procedures, validation checkpoints, and a well-signaled one-level reference file. Its main weakness is verbosity: the body is long and repeats core invariants across sections rather than consolidating them.

Suggestions

Consolidate the repeated N/A philosophy, "do not fake backend/persistence/permissions", and "derive everything from one authoritative object" invariants into a single invariants section and reference it instead of restating in every section.

Move the detailed visual-rule enumeration (font-size thresholds, decoration-rail rules, border-left/角括号 lists) into references/patterns.md, keeping only the testable checks (skin-stripping test, 去控件检查) inline.

Add a short top-of-body quick-start that names the three work modes and links to the contract template and 实施与验收 sequence, so the core workflow is reachable without scrolling the full prose.

DimensionReasoningScore

Conciseness

At ~180 lines of dense prose the body is noticeably verbose, with the same invariants (mark N/A + reason, never fake backend/persistence/permissions, derive from one authoritative object) restated across many sections; these padded repetitions could be consolidated without losing guidance.

2 / 5

Actionability

Provides concrete, executable guidance for an instruction-only skill: product-type/mode/applicability tables, a one-page contract template with named fields, a per-judgment line template ("current object / primary evidence / decision input / available command / completion evidence"), and specific tests (skin-stripping test, 去控件检查, ≥14 CSS px rule).

4 / 5

Workflow Clarity

The "实施与验收" section gives a 7-step sequence with validation checkpoints (blocker check before proceeding, representative non-empty state render, vertical closed-loop, environment/density testing, command→state→output mapping) plus a final "交付前确认" checklist; the workflow is somewhat fragmented across other sections rather than one self-contained flow.

4 / 5

Progressive Disclosure

Core flow is inline with clear section headers, and detailed patterns are offloaded to a real one-level-deep reference ([references/patterns.md](references/patterns.md), verified present with its own TOC and sectioned contents); the body itself remains long and could move more detail into the reference.

4 / 5

Total

14

/

20

Passed

Description

75%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 states concrete capabilities, lists target product domains, and uses explicit inclusion/exclusion scope to define when to use the skill. It is dense and abstract in places and lacks a canonical 'Use when…' trigger phrasing with synonyms.

DimensionReasoningScore

Specificity

Names several concrete actions ("设计、实现、重构或诊断完整界面") and enumerates specific product domains plus core coverage (object model, state machine, real I/O, error recovery), but the action verbs stay somewhat high-level rather than enumerating many distinct concrete operations.

4 / 5

Completeness

Answers both what (design/implement/refactor/diagnose complete interfaces) and when via explicit "用于…/不用于…" inclusion and exclusion lists, which is equivalent trigger guidance; not in a canonical "Use when…" form and the when is product-type enumeration rather than user-utterance triggers, so not a 5.

4 / 5

Trigger Term Quality

Uses natural domain phrases a target user would say ("运营与审核工作台", "任务流业务产品", "创作与编辑工具", "分析与管理工具"), with good coverage; missing common synonyms or lightweight variations of those terms.

4 / 5

Distinctiveness Conflict Risk

The explicit "不用于" exclusions (content sites, design-system token samples, single data charts, model-understanding demos) carve a clear niche and reduce conflict with sibling skills; minor overlap risk remains with general frontend-build skills.

4 / 5

Total

16

/

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
EverMind-AI/Raven
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.