CtrlK
BlogDocsLog inGet started
Tessl Logo

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。

55

Quality

61%

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/java-backend-tencent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is commendably concise and gives specific, actionable interview guidance with a clear topic sequence. Its main weaknesses are directive-level rather than example-rich actionability, implicit rather than explicit workflow checkpoints, and reference files that are named but not actually bundled.

Suggestions

Ship the referenced files (network-os.md, java.md, mysql.md, redis.md, mq.md, spring.md, system-design-scenarios.md) under references/ — or remove the "Additional Resources" links — so progressive disclosure is not broken.

Add one or two concrete worked interview exchanges (an example 底层追问 chain and a 选型追问 chain) to lift actionability from directive to copy-paste-ready.

Make the workflow's per-round cadence an explicit checklist with a gating checkpoint (e.g. "每轮结束前确认:是否已有一个底层追问和一个工程追问;否则补问再推进").

DimensionReasoningScore

Conciseness

The ~18-line body is lean and direct; it assumes Claude's competence (never explains what TCP/IP, MQ, or HTTP/HTTPS are) and every line earns its place with no padding.

3 / 3

Actionability

Guidance is specific and actionable — named topics (TCP/IP、HTTP/HTTPS、线程模型) and concrete example probes ("为何用 MQ 而不是同步调用,何时不用缓存") — but it stays mostly directive ("先问…再过渡", "持续深挖为什么") with only two worked examples rather than comprehensive copy-paste-ready material.

2 / 3

Workflow Clarity

A clear phase sequence is given ("先问网络与操作系统基础,再过渡到业务系统设计与中间件选型") plus a per-round cadence rule, but progression relies on interviewer judgment with no explicit gating checkpoints or feedback loops.

2 / 3

Progressive Disclosure

Structure is good — a concise overview plus a categorized, one-level-deep "Additional Resources" map (NET_OS→network-os.md, JAVA→java.md, etc.) — but the referenced files do not exist in any bundle directory, so the navigation points to missing files.

2 / 3

Total

9

/

12

Passed

Description

57%

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 targets a clear, distinctive niche and states what it does, but it lacks an explicit "Use when…" trigger and only partially covers the natural keywords a user would say. Specificity is decent but stays at a conceptual rather than concrete-action level.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to prepare for or generate questions for a Tencent backend interview (后端面试题、八股、模拟面试)."

Broaden trigger-term coverage with natural variations users actually say: 面试题、八股文、面经、模拟面试、后端面经.

Make the concrete actions more granular rather than abstract verbs — e.g. "生成八股题、追问底层原理、结合业务场景出选型题" instead of "考察/验证".

DimensionReasoningScore

Specificity

Names the niche and several actions — "面试出题", "考察计算机基础、计网与操作系统原理", "验证技术选型能力" — but they sit at a conceptual level (考察/验证) rather than the granular concrete verbs of the anchor-3 examples.

2 / 3

Completeness

The "what" is explicit ("用于腾讯后端面试出题;重点考察…"), but there is no "Use when…" clause or equivalent explicit trigger guidance; the "when" is only implied by "用于…", capping completeness at 2 per the rubric guidelines.

2 / 3

Trigger Term Quality

Core natural terms are present ("腾讯后端面试", "出题") but common variations a user would actually say — 面试题、八股、面经、模拟面试 — are missing, so coverage is partial.

2 / 3

Distinctiveness Conflict Risk

"腾讯后端面试" combined with 计网/OS/技术选型 is a clear, narrow niche with distinct triggers, very unlikely to fire for an unrelated skill.

3 / 3

Total

9

/

12

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.