CtrlK
BlogDocsLog inGet started
Tessl Logo

ali-backend

用于阿里后端面试出题;强调业务深度、项目落地和中间件选型能力,关注复杂场景下的取舍与闭环。

60

Quality

70%

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 ./app/src/main/resources/skills/ali-backend/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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, well-structured, and gives concrete actionable interviewing guidance suited to a simple instruction-only skill. Its main weakness is progressive disclosure: the resource map references eight files that are not present in the bundle, so the references cannot be navigated.

Suggestions

Create the referenced bundle files (references/system-design-scenarios.md, db-design.md, mysql.md, distributed.md, redis.md, mq.md, design-pattern.md) or remove dangling references so navigation resolves.

Add one explicit verification checkpoint, e.g. 'before ending the interview, confirm at least one full落地 plan (指标/压测/发布/回滚/复盘) was elicited', to lift workflow clarity.

Optionally include one short concrete example question per category inline so the skill is self-sufficient even before the bundle is loaded.

DimensionReasoningScore

Conciseness

The body is lean and efficient — a short overview, five numbered directives, and a categorized resource map with no padding and no over-explanation of concepts Claude already knows; every token earns its place.

5 / 5

Actionability

Provides concrete, specific guidance (追问 '为什么这样设计'/'流量涨10倍怎么改', MySQL/Redis/MQ focus, 落地要求 of 指标/压测/发布/回滚/复盘) that is directly executable as an interview script, with only minor gaps versus fully copy-paste-ready material.

4 / 5

Workflow Clarity

The five instructions form a clear, sequenced interviewing approach with an explicit 'at least once' requirement for a full落地 plan; as a simple non-destructive skill it lacks explicit validation checkpoints but does not need them, placing it just below anchor 5.

4 / 5

Progressive Disclosure

Structure is good — overview plus a categorized, clearly-signaled one-level-deep resource map — but every referenced file (system-design-scenarios.md, db-design.md, mysql.md, distributed.md, redis.md, mq.md, design-pattern.md) points to a bundle that does not exist, so the disclosure cannot actually resolve.

3 / 5

Total

16

/

20

Passed

Description

62%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 scopes a distinct niche and lists several concrete capability dimensions, but it lacks an explicit 'Use when...' trigger clause and its keywords lean toward internal jargon rather than natural user phrasing. Adding a trigger clause and more colloquial terms would lift completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when preparing for or generating questions for Alibaba backend interviews.'

Surface more natural user phrasing and synonyms (e.g. 'Java 后端面试题', '系统设计面试', '八股文') alongside the domain-internal terms.

Tighten the capability list into discrete concrete actions (e.g. '生成项目深挖追问、设计系统设计题、考察中间件原理') to approach comprehensive specificity.

DimensionReasoningScore

Specificity

Names the domain (阿里后端面试出题) plus several concrete capability axes (业务深度、项目落地、中间件选型、取舍与闭环), giving broad coverage with minor gaps; not quite the exhaustive multi-action list of anchor 5.

4 / 5

Completeness

The 'what' is clear (阿里后端面试出题) but there is no 'Use when...' trigger clause and 'when' is only weakly implied, so per the guideline a missing trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant domain terms (面试出题、后端、中间件选型) are present but somewhat internal/jargon-like and missing common natural variations a user would spontaneously say; not comprehensive.

3 / 5

Distinctiveness Conflict Risk

Targets a clear, narrow niche (阿里巴巴后端面试出题) with distinct triggers and minimal risk of firing for unrelated skills.

5 / 5

Total

15

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Snailclimb/interview-guide
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.