java-backend-tencent

用于腾讯后端面试出题；重点考察计算机基础、计网与操作系统原理，并结合业务场景验证技术选型能力。

Quality

74%

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/java-backend-tencent/SKILL.md

Quality

Content

82%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 content is lean, highly actionable, and clearly sequenced for an interviewer-persona skill. Its one significant defect is that all seven referenced resource files are missing, breaking the progressive-disclosure navigation the skill relies on.

Suggestions

Create the referenced files under references/ (network-os.md, java.md, mysql.md, redis.md, mq.md, spring.md, system-design-scenarios.md) or remove the dangling references.

If keeping the references, convert the arrow map into proper markdown links (e.g. [network-os.md](references/network-os.md)) so the paths and existence are verifiable.

Add a brief note on what each referenced file contains so Claude knows which to consult per question category.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: no over-explanation of what TCP/IP or threading models are, no padding. Every line (persona, 5 numbered directives, resource map) earns its place.	5 / 5
Actionability	Provides concrete, specific guidance: named topics (TCP/IP, HTTP/HTTPS, 线程模型, 内存模型) and concrete selection questions ('为何用 MQ 而不是同步调用，何时不用缓存'). As an instruction-only skill, the actionable directives cover common cases without needing code.	5 / 5
Workflow Clarity	A clear 5-step sequenced interview flow (fundamentals → system design → selection → per-round follow-ups → pace/consistency). This is a conversational skill, so the destructive/batch validation cap does not apply; it stops short of 5 only because there are no explicit checkpoints/feedback loops.	4 / 5
Progressive Disclosure	The Additional Resources section is well organized as a one-level category→file map (NET_OS->network-os.md, JAVA->java.md, etc.), but none of the referenced files (network-os.md, java.md, mysql.md, redis.md, mq.md, spring.md, system-design-scenarios.md) exist in references/. The navigation is structurally signaled but functionally broken.	2 / 5
	Total	16 / 20 Passed

Description

66%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 is specific and domain-distinct, naming concrete actions for Tencent backend interview question generation. Its main weakness is the absence of an explicit 'Use when...' trigger clause, which caps completeness.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user needs to generate or practice Tencent backend interview questions, 八股, or system-design questions.'

Include common synonyms such as '面试题', 'mock interview', and '八股' to broaden natural trigger coverage.

Mention the key tech stacks (Java, MySQL, Redis, MQ, Spring) in the description to sharpen distinctiveness from generic interview skills.

Dimension	Reasoning	Score
Specificity	Names the domain (腾讯后端面试) and several concrete actions: 出题, 考察计算机基础/计网/操作系统原理, and 结合业务场景验证技术选型能力. Coverage is strong but not exhaustive, fitting the 'several specific actions; minor gaps' anchor rather than the comprehensive 5.	4 / 5
Completeness	Clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance; 'when' is only weakly implied. Per the rubric guideline, a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user might say ('腾讯后端面试', '计网', '操作系统', '技术选型'), but misses common synonyms/variants like '面试题', 'mock interview', or '八股'. Good coverage with a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	The '腾讯后端面试出题' niche is fairly distinct with specific triggers, with only minor overlap risk against generic interview-question skills. Not a 5 because 'interview question generation' as a category could overlap with broader interview skills.	4 / 5
	Total	15 / 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/java-backend-tencent/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.