algorithm

用于算法面试出题；重点评估复杂度分析、边界处理和优化能力，区分背题与真实理解。

Quality

83%

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

Quality

Content

92%

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

The body is lean, actionable, and well-sequenced, assuming Claude's competence throughout. The only notable weakness is the Additional Resources reference: it is ambiguously formatted and points to a file (algorithm-data-structures.md) that is not present in the bundle.

Suggestions

Create the referenced ./references/algorithm-data-structures.md (or remove the reference) so navigation is not broken.

Reformat the Additional Resources mapping as clear markdown links (e.g., '- [algorithm-data-structures.md](references/algorithm-data-structures.md)') and clarify whether each category maps to a separate file or all to one file.

Dimension	Reasoning	Score
Conciseness	Lean and efficient ~18-line body with no padding; it assumes Claude's competence and never explains concepts Claude already knows (e.g., what a hash table or complexity analysis is).	3 / 3
Actionability	Provides concrete, specific guidance with executable examples — '口述：建模方式、关键数据结构、核心步骤、时间/空间复杂度' and concrete optimization paths '剪枝、单调结构、预处理、空间换时间' and proof techniques '不变式/归纳/反证'.	3 / 3
Workflow Clarity	A clear numbered interview protocol with response-based branching ('回答正确后继续追问', '对暴力解必须追问瓶颈'), giving an unambiguous sequenced workflow appropriate for a non-destructive interview skill.	3 / 3
Progressive Disclosure	Sections are well-organized (Overview/Instructions/Additional Resources), but the reference 'ARRAY_LINKEDLIST/.../DESIGN -> algorithm-data-structures.md' is ambiguously signaled and the referenced file does not exist in any bundle directory, breaking navigation.	2 / 3
	Total	11 / 12 Passed

Description

75%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, specific description that names concrete capabilities and natural trigger terms for the algorithm-interview niche. Its main weakness is the missing explicit 'Use when' trigger guidance, which caps completeness and limits distinctiveness.

Suggestions

Add an explicit 'Use when...' clause (e.g., '用于算法面试出题或候选人复杂度/优化能力评估时使用') to make the trigger unambiguous.

Include common phrasing variations users might say (面试题, 算法题, leetcode, 复杂度评估) to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — '算法面试出题', '评估复杂度分析、边界处理和优化能力', '区分背题与真实理解' — naming specific actions rather than vague language.	3 / 3
Completeness	Clearly answers 'what' (algorithm interview question setting and evaluation), but the 'when' is only implied with no 'Use when...' clause or equivalent explicit trigger, capping completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Contains natural terms a user would actually say when needing this skill — '算法面试', '出题', '复杂度分析', '优化' — rather than abstract jargon.	3 / 3
Distinctiveness Conflict Risk	The algorithm-interview niche is fairly specific, but without explicit triggers it could still overlap with general coding-interview or CS skills.	2 / 3
	Total	10 / 12 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/algorithm/SKILL.md
Commit: 0780137

Reviewed: 3 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.