bytedance-backend

用于字节后端面试出题；以算法与编码能力为第一门槛，同时考察高并发场景下的系统设计能力。

Quality

70%

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/bytedance-backend/SKILL.md

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 provides concrete actionable interview guidance with a clear sequenced workflow. Its main weakness is progressive disclosure: the Additional Resources section points to bundle files that are not actually present, leaving the references as dead ends.

Suggestions

Create the referenced bundle files (algorithm-data-structures.md, distributed.md, system-design-scenarios.md) under references/ so the category-to-file mapping resolves to real content.

Add 1-2 concrete sample questions or question templates per category so the guidance is copy-paste ready rather than purely behavioral.

Optionally add an explicit verification/checklist step (e.g. confirm data-structure coverage and a complexity claim before moving on) to strengthen workflow validation.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient — a two-sentence Overview plus five tightly-worded numbered rules and a short resource map, with no padding or explanation of concepts Claude already knows; every token earns its place, matching anchor 5.	5 / 5
Actionability	Instructions give concrete, executable behavioral rules with specific examples ('计数、去重、延迟任务、TopK', '至少覆盖两类以上', '每次只追一个关键点'), but no ready-made question templates or sample prompts are provided, leaving minor gaps versus fully copy-paste-ready anchor 5.	4 / 5
Workflow Clarity	A clear five-step interview sequence (prioritize algorithm questions → balanced coverage → probing follow-up → engineering migration → pacing) is present, with the '追问' step acting as a soft comprehension checkpoint, but there are no explicit validation/feedback loops, so it sits at anchor 4 rather than 5.	4 / 5
Progressive Disclosure	SKILL.md is a lean overview with references clearly signaled and organized by category (ARRAY_LINKEDLIST/DP, DISTRIBUTED/SYSTEM_DESIGN, PROJECT), but the referenced files (algorithm-data-structures.md, distributed.md, system-design-scenarios.md) do not exist in any bundle directory, so navigation to the detail content is broken, capping the score at 3.	3 / 5
	Total	16 / 20 Passed

Description

61%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 names a specific niche and two concrete capability areas with natural trigger terms, but it omits any explicit 'when to use this skill' guidance, which caps completeness and slightly weakens trigger distinctiveness.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user is preparing for or conducting a ByteDance backend interview, or asks for 算法/系统设计 interview questions.'

Broaden trigger terms with natural synonyms like '面试题', '后端开发', '刷题', '八股' to improve keyword coverage.

Consider naming one or two more concrete actions (e.g. '出题、追问、复杂度评估') to lift specificity above the two-pillar summary.

Dimension	Reasoning	Score
Specificity	Names the domain (字节后端面试出题) plus two concrete capability pillars ('算法与编码能力' and '高并发场景下的系统设计能力'), but stops at a high-level two-pillar description rather than listing several specific actions, matching anchor 3.	3 / 5
Completeness	It clearly states what the skill does (generates ByteDance backend interview questions with algorithm-first and system-design screening) but provides no explicit 'Use when...' trigger guidance, so per the missing-trigger cap completeness stays at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('字节后端面试', '算法', '编码', '高并发', '系统设计') with good coverage; a few natural synonyms/variations (e.g. '面试题', '后端开发', '刷题') are missing, so it sits above anchor 3 but below comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The ByteDance-backend niche with algorithm-plus-system-design triggers is clearly distinct and low conflict risk, but the absence of an explicit 'use when' clause leaves minor overlap risk with generic backend/interview skills, placing it above anchor 3 and short of the fully-triggered anchor 5.	4 / 5
	Total	14 / 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/bytedance-backend/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.