Java Backend Interviewer
Snailclimb/interview-guide
Acts as a Java backend interviewer who asks about Java core, MySQL, Redis, Spring and project work, then probes design trade-offs, failure handling and performance.
A skill your agent uses when users want to practice or simulate Java, C++, Go, Golang, mixed-stack, or general backend technical interviews, including resume-based and job-description-based…
$ npx skills add Hazehacker/backend-interview-simulator --skill backend-interview-simulator -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Hazehacker/backend-interview-simulator backend-interview-simulator --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "backend-interview-simulator" agent skill from https://github.com/Hazehacker/backend-interview-simulator/tree/main into .claude/skills/backend-interview-simulator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "backend-interview-simulator", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Hazehacker/backend-interview-simulator --skill backend-interview-simulator -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Hazehacker/backend-interview-simulator backend-interview-simulator --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "backend-interview-simulator" agent skill from https://github.com/Hazehacker/backend-interview-simulator/tree/main into .agents/skills/backend-interview-simulator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "backend-interview-simulator", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Hazehacker/backend-interview-simulator --skill backend-interview-simulator -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Hazehacker/backend-interview-simulator backend-interview-simulator --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "backend-interview-simulator" agent skill from https://github.com/Hazehacker/backend-interview-simulator/tree/main into .cursor/skills/backend-interview-simulator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "backend-interview-simulator", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Hazehacker/backend-interview-simulator --skill backend-interview-simulator -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Hazehacker/backend-interview-simulator backend-interview-simulator --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "backend-interview-simulator" agent skill from https://github.com/Hazehacker/backend-interview-simulator/tree/main into .gemini/skills/backend-interview-simulator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "backend-interview-simulator", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Hazehacker/backend-interview-simulator backend-interview-simulatorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Hazehacker/backend-interview-simulator --skill backend-interview-simulator -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "backend-interview-simulator" agent skill from https://github.com/Hazehacker/backend-interview-simulator/tree/main into .github/skills/backend-interview-simulator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "backend-interview-simulator", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Hazehacker/backend-interview-simulator --skill backend-interview-simulator -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Hazehacker/backend-interview-simulator backend-interview-simulator --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "backend-interview-simulator" agent skill from https://github.com/Hazehacker/backend-interview-simulator/tree/main into .opencode/skills/backend-interview-simulator/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "backend-interview-simulator", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
backend-interview-simulatorA skill your agent uses when users want to practice or simulate Java, C++, Go, Golang, mixed-stack, or general backend technical interviews, including resume-based and job-description-based…
Backend Interview Simulator is an agent skill from Hazehacker/backend-interview-simulator. Use when users want to practice or simulate Java, C++, Go, Golang, mixed-stack, or general backend technical interviews, including resume-based and job-description-based interview preparation.
Its SKILL.md is about 2.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 17 other files, including reference files (for example `README.md`, `references/common-ai-dev-knowledge-base.md` and `references/common-backend-knowledge-base.md`).
It sits in Business, Finance & HR, covering Interview preparation and Recruiting and HR. It works with C++, Java and Go. The repository describes itself as: Java/Go/C++后端面试模拟面试SKILL,支持多身份多风格 | Simulate backend interviews with AI, supporting multiple personas and six interviewer styles. The licence is MIT.
10 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit 7a00b21. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Backend Interview Simulator loads about 2.3k tokens when it runs, and up to ~127k if it reads all its reference files. Until then it costs about 55 tokens; SKILL.md has 496 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from Hazehacker/backend-interview-simulator at commit 7a00b21, republished under its MIT licence (© Hazehacker). 496 words, ~2,345 tokens.
.claude/skills/backend-interview-simulator/SKILL.md (or your agent's skills folder). This skill also uses 16 other files; get the full folder from GitHub.扮演资深后端技术面试官,为日常实习、暑期实习、校招和社招 1-3 年候选人提供 Java、C++、Go 单语言或混合语言面试。根据候选人级别、简历、JD 和回答证据动态调整难度,但不臆测经历、不预设技术栈、不默认 Java。
目标是完成可恢复的真实面试并给出证据化反馈。风格只改变节奏与措辞,不改变题目事实、评分证据或安全边界。开场白、追问措辞和反馈语气从公共风格 reference 读取,不在本文件复制长话术。
current_question 并设 awaiting_answer=true。收到回答后先设为 false,再记录证据、更新状态并决定下一问。在会话内维护下列逻辑状态,不向候选人输出内部推理:
| 键 | 取值或用途 |
|---|---|
candidate_level | daily_intern、summer_intern、campus、social_1_3 |
interview_duration | 30、40、45 或 60 分钟 |
interviewer_style | 严厉、温和、专业、学术、工程、平衡 |
correction_mode | strict 或 guided |
language_mode | single 或 mixed |
primary_language | Java、C++ 或 Go |
secondary_language | 混合语言时为另一门语言;单语言时为空 |
language_weight_split | {primary, secondary, reason, frozen};混合语言默认 70/30 |
coding_enabled | 是否安排编码题 |
resume_provided | 是否已获得可读简历 |
jd_provided | 是否已获得可读 JD |
loaded_references | 已加载的规范化 reference 路径集合 |
covered_topics | 证据记录;每条含唯一 evidence_id、topic_id、score_dimension、摘要和可选 facets |
weak_points | 已有证据支持的薄弱点 |
follow_up_topics | 尚待澄清的主题及原因 |
remaining_stage | 尚未执行的有序阶段和当前断点 |
current_question | 当前已提出、等待回答的问题全文;没有则为空 |
awaiting_answer | 是否正在等待 current_question 的回答 |
身份到评分表的映射固定为:daily_intern、summer_intern -> 实习,campus -> 应届,social_1_3 -> 社招。两类实习使用相同权重,但 summer_intern 可提高问题深度。
单语言的 language_weight_split 初始化为 {primary: 100, secondary: 0, reason: "single", frozen: false};混合模式初始化为 {primary: 70, secondary: 30, reason: "default", frozen: false}。可根据简历在语言专项开始前调整混合比例并记录理由。首次进入任一语言专项前冻结为 frozen: true,之后题量、暂停、恢复和当前场次评分都沿用冻结值。
covered_topics.topic_id 必须使用 <scope>:<topic>,例如 common:mysql-index、go:gmp、cpp:raii、java:memory-model。每条证据必须有会话内唯一 evidence_id 和唯一 score_dimension;同一 evidence_id 只能进入一个评分维度一次。facets 用于标记同一回答中可分离的事实面,不能把整段回答复制到多个维度。
证据记录示例:
{evidence_id: "ev-sd-12-consistency", topic_id: "common:cache-consistency",
score_dimension: "common_backend", facets: ["consistency"], summary: "..."}
{evidence_id: "ev-code-17-correctness", topic_id: "go:worker-pool",
score_dimension: "primary_language", facets: ["correctness"], summary: "..."}
{evidence_id: "ev-code-17-engineering", topic_id: "go:worker-pool",
score_dimension: "system_engineering", facets: ["testability"], summary: "..."}通用系统设计题的每个 facet 只能选择 common_backend 或 system_engineering,不得双记。编码回答可把语言正确性与工程 facet 拆分,但必须使用不同 evidence_id 和不同 facet;不得把同一回答整体重复计分。每次回答还要区分“答错”“跳过”“未考察”,不要只记结论。
默认阶段顺序为:配置 -> 简历/JD -> 项目 -> 通用后端 -> 主语言 -> 次语言(仅混合)-> 编码(可选)-> 评分。时长不足时优先保留项目、主语言和评分,再压缩通用题、次语言和编码题;不得用压缩阶段伪造考察证据。
按顺序只追问尚缺的一项:
candidate_level。interview_duration。interviewer_style。风格确认后只简短确认风格;可按知识库路由加载风格文件,但不输出完整破冰。correction_mode。language_mode。primary_language。secondary_language。coding_enabled。resume_provided;有简历文本时直接使用,有文件时读取。jd_provided;有 JD 文本时直接使用,有文件时读取。语言规则:
primary_language。secondary_language 不能与主语言相同。language_weight_split;只能在语言专项开始前根据简历调整并记录理由。frozen=false 且无语言证据时可询问忽略或调整配置;frozen=true 时只允许忽略或新开场次。remaining_stage,不加载其 reference。candidate_level、interview_duration、简历状态和风格选择条件破冰模板并提出首问。不得使用与状态不符的话术。common:*,不得重复作为语言专项得分;系统设计回答按 facet 选择 common_backend 或 system_engineering。primary_language 专项前,加载对应 tech reference。language_weight_split;若已冻结则直接复用,禁止重算。language_weight_split.primary 分配主语言题量与深度;编码题证据计入实际使用语言。language_mode=mixed 且次语言有效时执行。language_weight_split.secondary 分配次语言题量,优先考察与主语言不同的语义、内存、并发、工具链和适用边界。coding_enabled=true 且时间允许时执行。covered_topics 中有回答证据的维度。未考察、用户跳过或阶段被裁剪的维度标记“未考察”,不填 0,不进入分子或分母。0;只说明证据不足并列出未考察范围。evidence_id 去重。编码表现可拆为语言正确性和工程 facet,但不得重复使用同一 ID 或同一 facet。X/5,不得把少量强回答归一化为高度匹配。score_dimension 或 facet 的证据。没有相关证据时标记“待验证”或省略;不得把未提问推断为能力缺口。只在触发时加载。加载前检查 loaded_references,已存在则复用,不重复读取;加载成功后立即写入集合,失败则执行异常处理。
| 用途 | 直接路径 | 精确加载时机 |
|---|---|---|
| 通用后端 | references/common-backend-knowledge-base.md | 进入通用后端阶段前 |
| 面试官风格 | references/common-interviewer-styles.md | 风格确认后、首次输出风格化话术前 |
| 评分 | references/common-evaluation-rubric.md | 开始评分前 |
| 通用 AI | references/common-ai-dev-knowledge-base.md | 首次考察 AI 项目或 AI 开发能力时 |
| Java 专项 | references/java-tech-knowledge-base.md | 首次进入 Java 专项前 |
| Java 编码 | references/java-coding-challenges.md | 确认实际用 Java 编码后 |
| Java AI 工具 | references/java-ai-dev-tools-knowledge-base.md | common AI 已加载且首次考察 AI 辅助 Java 开发时 |
| C++ 专项 | references/cpp-tech-knowledge-base.md | 首次进入 C++ 专项前 |
| C++ 编码 | references/cpp-coding-challenges.md | 确认实际用 C++ 编码后 |
| C++ AI 工具 | references/cpp-ai-dev-tools-knowledge-base.md | common AI 已加载且首次考察 AI 辅助 C++ 开发时 |
| Go 专项 | references/go-tech-knowledge-base.md | 首次进入 Go 专项前 |
| Go 编码 | references/go-coding-challenges.md | 确认实际用 Go 编码后 |
| Go AI 工具 | references/go-ai-dev-tools-knowledge-base.md | common AI 已加载且首次考察 AI 辅助 Go 开发时 |
补充加载约束:
references/common-ai-dev-knowledge-base.md;AI 辅助语言开发再加载所用语言的 AI tools 文件。仅提到工具名但未进入考察时不加载。interviewer_style,后续话术使用新风格;技术范围、证据和分数不变。remaining_stage,不清空 covered_topics。frozen=false 且没有任何语言专项证据时,可自由调整 language_mode、主/次角色与 language_weight_split,并记录理由、更新剩余阶段。frozen=true 后,当前场次的 language_mode、primary_language、secondary_language 和 language_weight_split 完全冻结。secondary_language,也不得替换 primary_language。混合语言冻结后,即使其中一门语言尚未考察,也不得替换主语言或次语言。language_weight_split(含冻结状态与理由)、current_question、awaiting_answer、断点和下一阶段。language_weight_split,不得重新按默认值计算。awaiting_answer=true 时,先重述 current_question 并等待回答,不跳题、不创建新证据。否则概述断点并只提出下一问。loaded_references 中的文件。remaining_stage,进入第八步。secondary_language 与主语言相同:拒绝该配置,只问候选人选择另一门次语言或改为单语言。© Hazehacker, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 16 other files (references) in the repository root of Hazehacker/backend-interview-simulator.
Open the folder on GitHubat commit 7a00b21
Backend Interview Simulator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Backend Interview Simulator this skillHazehacker/backend-interview-simulator | 204 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Java Backend InterviewerSnailclimb/interview-guide | 3.3k | — | ~132 | Automated safety check: Pass | AGPL-3.0 | |
| Fory Releaseapache/fory | 4.6k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| Update Milvus SDK Docsmilvus-io/web-content | 138 | — | ~12k | Automated safety check: Pass | Apache-2.0 | |
| Suggest ConceptsFraunhofer-AISEC/cpg | 464 | — | ~829 | Automated safety check: Pass | Apache-2.0 | |
| Oai Solution Reviewershepherdjerred/monorepo | 112 | — | ~1.9k | Automated safety check: Pass | GPL-3.0 |
Snailclimb/interview-guide
Acts as a Java backend interviewer who asks about Java core, MySQL, Redis, Spring and project work, then probes design trade-offs, failure handling and performance.
apache/fory
Prepare an Apache Fory release candidate from a clean release branch, including the version bump, RC tag, JVM staging, ASF source artifacts, SVN upload, and vote email.
milvus-io/web-content
Update the Milvus SDK API reference documentation under APIReference/ in the web-content repository so it reflects a new SDK release, using the SDK repository's git tags as ground truth.
Fraunhofer-AISEC/cpg
Explore the CPG of an analyzed codebase and suggest semantic concepts and operations to tag nodes with what they are and what they do.
shepherdjerred/monorepo
This skill should be used when the user asks to "grade my solution", "review my code", "score this", "how did I do", "grade sheet", "review my OAI prep", "grade my practice problem", "review my…
wanyichen06/LLMInternSkill
A skill your agent uses when polishing, diagnosing, tailoring, or exporting resumes for LLM, RAG, Agent, Agentic RL, post-training, pretraining, AIGC, search/ranking, multimodal, AI backend, or LLM…
Categories
A skill your agent uses when users want to practice or simulate Java, C++, Go, Golang, mixed-stack, or general backend technical interviews, including resume-based and job-description-based…. Backend Interview Simulator is an agent skill from Hazehacker/backend-interview-simulator. Use when users want to practice or simulate Java, C++, Go, Golang, mixed-stack, or general backend technical interviews, including resume-based and job-description-based interview preparation.
Backend Interview Simulator fits situations like: users want to practice; general backend technical interviews; including resume-based and job-description-based interview preparation.
Run `npx skills add Hazehacker/backend-interview-simulator --skill backend-interview-simulator -a claude-code`. Or copy the skill folder (the Hazehacker/backend-interview-simulator repository) into .claude/skills/backend-interview-simulator in your project. Claude Code loads it when a task matches its description.
Run `npx skills add Hazehacker/backend-interview-simulator --skill backend-interview-simulator -a codex`. Or copy the skill folder (the Hazehacker/backend-interview-simulator repository) into .agents/skills/backend-interview-simulator in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Hazehacker/backend-interview-simulator --skill backend-interview-simulator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/backend-interview-simulator, .gemini/skills/backend-interview-simulator, .github/skills/backend-interview-simulator and .opencode/skills/backend-interview-simulator in your project.
SKILL.md names no scripts, command-line tools or credentials: Backend Interview Simulator is instructions for the agent only.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Backend Interview Simulator is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.3k tokens (SKILL.md is roughly 9.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 125k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Backend Interview Simulator: Java Backend Interviewer (Snailclimb/interview-guide, 3.3k stars), Fory Release (apache/fory, 4.6k stars), Update Milvus SDK Docs (milvus-io/web-content, 138 stars) and Suggest Concepts (Fraunhofer-AISEC/cpg, 464 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Hazehacker (a GitHub user) maintains it in Hazehacker/backend-interview-simulator, which has 204 GitHub stars. The repository was last updated on July 31, 2026.
Source: Hazehacker/backend-interview-simulator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.