frontend

用于前端工程面试出题；覆盖 JavaScript、React/Vue、浏览器原理和性能优化，强调业务实战与工程化能力。

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./app/src/main/resources/skills/frontend/SKILL.md

Quality

Content

72%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 concise and mostly actionable behavioral guidance, but it reads as a principles checklist without validation checkpoints, and its Additional Resources reference bundle files that are not present, breaking progressive disclosure.

Suggestions

Create the missing referenced files (references/javascript.md, references/react-vue.md, references/browser.md) or remove the broken references and inline the essential question prompts.

Reframe the Instructions as a sequenced interview workflow with explicit checkpoints (e.g. warm-up → depth-probing → quantifiable-metric request → wrap-up) rather than standalone principles.

Add one or two concrete sample questions per category inline so the skill is immediately usable without the (currently absent) reference files.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient — five tight directives and a short resources section with no padding and no explanation of concepts Claude already knows, matching 'lean and efficient; every token earns its place'.	5 / 5
Actionability	Directives are concrete and executable with specific examples ('FCP/LCP、错误率、包体积', '结合简历项目，追问复杂页面、性能瓶颈'), fitting 'mostly executable guidance; minor gaps'; below 5 because no sample question templates or concrete question bank are provided inline.	4 / 5
Workflow Clarity	A numbered 1–5 list gives a rough sequence, but items are principles rather than a checkpointed workflow with explicit validation/feedback steps, matching 'steps listed but validation gaps; checkpoints missing or implicit'.	3 / 5
Progressive Disclosure	Section structure (Overview/Instructions/Additional Resources) is clean with one-level-deep categorized references, but the referenced files (javascript.md, react-vue.md, browser.md) do not exist in any bundle directory, so navigation is broken; this pulls an otherwise good structure down to 'some structure but references not clearly usable'.	3 / 5
	Total	15 / 20 Passed

Description

58%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 clearly states its purpose and coverage areas with a distinct niche, but lacks an explicit 'Use when...' trigger clause, which caps completeness and weakens trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when preparing or conducting frontend engineering interviews, or when the user asks for frontend interview questions.'

Expand trigger terms with synonyms and file/role cues users actually say (e.g. '前端面试题', 'React 面试', '前端校招/社招', 'mock interview').

Lead with the concrete action (出题/追问) before the coverage list so the 'what' is unambiguous in the first phrase.

Dimension	Reasoning	Score
Specificity	Names the domain ('前端工程面试出题') and lists several concrete coverage areas ('JavaScript、React/Vue、浏览器原理和性能优化'), fitting the 'several specific actions; minor gaps' anchor; below 5 because actions are coverage topics rather than a comprehensive action list.	4 / 5
Completeness	The 'what' is clear (generates frontend interview questions across named topics) but there is no 'Use when...' clause or explicit trigger guidance, so completeness is capped at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Includes relevant natural terms a user would say ('JavaScript', 'React/Vue', '前端面试') but misses common variations/synonyms and any explicit trigger phrasing, fitting 'some relevant keywords but missing common variations'.	3 / 5
Distinctiveness Conflict Risk	The niche '前端工程面试出题' is clearly distinguishable with distinct triggers and only minor overlap risk with related interviewing skills; not 5 because no concrete trigger phrases lock it in.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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: Snailclimb/interview-guide
Path: app/src/main/resources/skills/frontend/SKILL.md
Commit: b2d1ca0

Reviewed: 19 days ago

Table of Contents

Discovery Implementation Validation

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.