CtrlK
BlogDocsLog inGet started
Tessl Logo

system-design

用于系统设计面试出题;聚焦容量估算、可用性与一致性权衡、可观测性和故障恢复。

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/system-design/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 well-structured, but its guidance stays at the directive-checklist level without concrete sample output, and its referenced resource files are missing entirely. Actionability, workflow clarity, and progressive disclosure are all capped at mid-level.

Suggestions

Add at least one fully-worked sample question (with the expected tradeoff and follow-up) so the guidance becomes copy-paste-ready and actionable.

Introduce an explicit validation/verification checkpoint (e.g., 'verify each question contains a tradeoff and a capacity-estimation ask before presenting') to add the feedback loop workflow clarity rewards.

Create the referenced files under references/ (high-availability.md, distributed.md, redis.md, design-pattern.md) or remove the dangling references so progressive disclosure points to real, navigable material.

DimensionReasoningScore

Conciseness

The body is lean and token-efficient — a one-line persona, four tight numbered rules, and a brief resource list — with no concept padding and no over-explanation of what Claude already knows, matching the 'lean and efficient; every token earns its place' anchor.

3 / 3

Actionability

Guidance is concrete (specific constraint types 'QPS、SLA、一致性级别、成本', a tradeoff example '一致性 vs 延迟', four required explanation areas, and an explicit prohibition), but it provides no sample question or output template, which is a key missing detail for a question-generation skill.

2 / 3

Workflow Clarity

Four numbered steps give a clear sequence, but there are no validation checkpoints or feedback loops, which the top anchor requires; and because this is a multi-step process, the simple-skill exception does not apply.

2 / 3

Progressive Disclosure

The body is well-sectioned (Overview/Instructions/Additional Resources) with one-level, category-signaled references, but the referenced files (high-availability.md, distributed.md, redis.md, design-pattern.md) do not exist in any bundle directory, so navigation is broken and the disclosure is non-functional.

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 is specific and distinctive, naming a clear niche and concrete focus areas, but it lacks an explicit 'Use when...' trigger and broader natural-keyword variations, leaving the what/when coverage incomplete. It is solid but capped at mid-level on completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' / '当用户需要…时使用' clause so the 'when' trigger is stated, not implied, raising completeness.

Broaden trigger terms with common variations (e.g., 'system design interview', '系统设计面试题', 'mock interview / 模拟面试') to improve trigger-term coverage.

Enumerate concrete actions beyond '出题' (e.g., '出题、追问、评估回答的权衡深度') to lift specificity from a single action to multiple discrete actions.

DimensionReasoningScore

Specificity

States one concrete action ('用于系统设计面试出题') and concrete focus topics (容量估算、可用性与一致性权衡、可观测性和故障恢复), but does not list multiple discrete actions, so it falls short of the 'multiple specific concrete actions' anchor.

2 / 3

Completeness

Clearly answers 'what' ('用于系统设计面试出题') but provides no explicit 'when to use' trigger clause; per the guideline a missing 'Use when...' equivalent caps completeness at 2.

2 / 3

Trigger Term Quality

Includes the natural trigger '系统设计面试' plus relevant specialized terms, but lacks common variations such as English 'system design', standalone '面试题', or 'mock/练习', matching the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

'系统设计面试出题' combined with the specific focus areas carves out a clear, narrow niche with distinct triggers that is unlikely to conflict with other skills.

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.