Oai Solution Reviewer
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…
将批量面经或零散面试题逐题去重并分发:Agent/LLM/AI工程题写入 zero2Agent 的 learn-agent-interview,传统后端八股写入相邻 zero2Leetcode 的夏季八股。大批量输入使用 gpt-5.6-luna API 逐篇并发抽题和语义召回,再审查、去重和写答案;不新建面经实录文章。
$ npx skills add ranxi2001/zero2Agent --skill classify-interview-questions -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ranxi2001/zero2Agent classify-interview-questions --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ranxi2001/zero2Agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/classify-interview-questions .claude/skills/classify-interview-questions && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "classify-interview-questions" agent skill from https://github.com/ranxi2001/zero2Agent/tree/main/.agents/skills/classify-interview-questions into .claude/skills/classify-interview-questions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "classify-interview-questions", 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.
$skill-installer install https://github.com/ranxi2001/zero2Agent/tree/main/.agents/skills/classify-interview-questionsType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ranxi2001/zero2Agent --skill classify-interview-questions -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ranxi2001/zero2Agent classify-interview-questions --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ranxi2001/zero2Agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/classify-interview-questions .agents/skills/classify-interview-questions && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "classify-interview-questions" agent skill from https://github.com/ranxi2001/zero2Agent/tree/main/.agents/skills/classify-interview-questions into .agents/skills/classify-interview-questions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "classify-interview-questions", 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 ranxi2001/zero2Agent --skill classify-interview-questions -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ranxi2001/zero2Agent classify-interview-questions --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ranxi2001/zero2Agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/classify-interview-questions .cursor/skills/classify-interview-questions && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "classify-interview-questions" agent skill from https://github.com/ranxi2001/zero2Agent/tree/main/.agents/skills/classify-interview-questions into .cursor/skills/classify-interview-questions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "classify-interview-questions", 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.
$ gemini skills install https://github.com/ranxi2001/zero2Agent.git --path .agents/skills/classify-interview-questions--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ranxi2001/zero2Agent --skill classify-interview-questions -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ranxi2001/zero2Agent classify-interview-questions --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ranxi2001/zero2Agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/classify-interview-questions .gemini/skills/classify-interview-questions && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "classify-interview-questions" agent skill from https://github.com/ranxi2001/zero2Agent/tree/main/.agents/skills/classify-interview-questions into .gemini/skills/classify-interview-questions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "classify-interview-questions", 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 ranxi2001/zero2Agent classify-interview-questionsInstalls 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 ranxi2001/zero2Agent --skill classify-interview-questions -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ranxi2001/zero2Agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/classify-interview-questions .github/skills/classify-interview-questions && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "classify-interview-questions" agent skill from https://github.com/ranxi2001/zero2Agent/tree/main/.agents/skills/classify-interview-questions into .github/skills/classify-interview-questions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "classify-interview-questions", 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 ranxi2001/zero2Agent --skill classify-interview-questions -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ranxi2001/zero2Agent classify-interview-questions --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ranxi2001/zero2Agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/classify-interview-questions .opencode/skills/classify-interview-questions && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "classify-interview-questions" agent skill from https://github.com/ranxi2001/zero2Agent/tree/main/.agents/skills/classify-interview-questions into .opencode/skills/classify-interview-questions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "classify-interview-questions", 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.
classify-interview-questions将批量面经或零散面试题逐题去重并分发:Agent/LLM/AI工程题写入 zero2Agent 的 learn-agent-interview,传统后端八股写入相邻 zero2Leetcode 的夏季八股。大批量输入使用 gpt-5.6-luna API 逐篇并发抽题和语义召回,再审查、去重和写答案;不新建面经实录文章。
Classify Interview Questions is an agent skill from ranxi2001/zero2Agent. 将批量面经或零散面试题逐题去重并分发:Agent/LLM/AI工程题写入 zero2Agent 的 learn-agent-interview,传统后端八股写入相邻 zero2Leetcode 的夏季八股。大批量输入使用 gpt-5.6-luna API 逐篇并发抽题和语义召回,再审查、去重和写答案;不新建面经实录文章。
Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 20 other files, including scripts (for example `question-frequency.json`, `question-index.json` and `question-index.md`).
It sits in Business, Finance & HR, covering Interview preparation. It works with OpenAI. The repository describes itself as: 面向大厂Agent研发岗位求职的agent教程网站,涵盖技术路线与面试八股文. The licence is MIT.
12 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 472ce78. 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.
Ships 9 files in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pythonpython3From the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
nowcoder.comFrom 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.
Classify Interview Questions loads about 2.6k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 531 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); the scripts in this folder are not scanned.
The full file from ranxi2001/zero2Agent at commit 472ce78, republished under its MIT licence (© ranxi2001). 531 words, ~2,553 tokens.
.claude/skills/classify-interview-questions/SKILL.md (or your agent's skills folder). This skill also uses 18 other files; get the full folder from GitHub.将新面试题按考察维度分类,拆分后加入已有题库。不新建独立面经实录文章。
zero2Agent/learn-agent-interview/。../zero2Leetcode/_includes/interview-seasons/2026/summer.md。question-index.json;question-index.md 是人工维护源。每次修改 Markdown 后必须重建 JSON 并运行 stale check。question-frequency.json 是 Agent 题单频次事实源。frequency 等于 evidence 中可归因的独立面经出现次数;题库汇总、“高频题”等不可追溯标签不计数。正文只在现有最小主题组内按频次降序排列,同频按稳定的 firstSeenOrder 排列。来源链接是题库可信度的一部分。以后新增题、增强已有题和调研答案都按以下标准维护,不只写不可核验的公司名或“高频题”。
有公开原文时,正文 > 来源: 使用可点击的 Markdown 链接,链接文字保留公司、岗位和轮次,例如:
> 来源:[阿里云 Agent Infra 一面](https://www.nowcoder.com/feed/main/detail/<id>)链接必须直达原始面经文章或用户指定的一手页面,不使用搜索结果页、信息流首页、聚合转载、短链或无关主页。多个独立来源分别给链接,不能把多个 URL 藏在一个笼统标签里。
同一来源要贯穿三处:正文来源行、question-index.md 的题目来源、question-frequency.json 的 evidence。人工索引保留 Markdown 链接;频次 JSON 中每个独立原文 URL 单独占一个 evidence,同一核心题里的同一 canonical URL 只计一次。
增强已有题时保留原有链接,再追加新来源或追问链接;不要把已经可点击的来源降级成纯文本。
URL 只是可追溯入口,不自动证明内容是一手面经。仍需按真实面试过程、公司/岗位/轮次和问题上下文判断是否可归因,转载、题库汇总和营销内容仍不计频次。
用户明确授权的本地题库或私有材料可以作为来源,但没有公开 URL 时必须写明“用户授权题库(无公开 URL)”,不得伪造链接,也不得把本机绝对路径、私有下载地址或凭证写进站点。若能定位到公开原文,先验证内容一致再补回原始链接。
无公开 URL、又没有用户明确授权或其他可归因证据的题目,不进入频次事实源。
THIRD_PARTY_NOTICES.md。独立改写答案,不复制外部文章的长段落、图表或受版权保护内容。| 编号 | 维度 | 目录 | 典型考察内容 |
|---|---|---|---|
| 01 | 架构选型 | 01-architecture-design/ | ReAct/Plan-Execute/ToT、Agent 组成、设计范式、规划器 |
| 02 | 工具管理 | 02-tool-management/ | 参数校验、工具路由、多工具调度、Mock 生成 |
| 03 | 容错与鲁棒性 | 03-fault-tolerance/ | 超时处理、误操作防范、幻觉治理、失败恢复 |
| 04 | 记忆与上下文 | 04-memory-context/ | 长对话、模糊需求、上下文污染、长短期记忆、to-do list |
| 05 | 评估与全局观 | 05-eval-and-vision/ | 量化评估、落地挑战、AI 工具价值/边界、行业认知 |
| 06 | 多智能体协作 | 06-multi-agent-collab/ | 角色分工、通信机制、冲突仲裁、记忆共享 |
| 07 | 工程化踩坑 | 07-engineering-pitfalls/ | 死循环、状态丢失、成本控制、AI Coding 实践、工具使用 |
| 08 | Prompt 工程 | 08-prompt-engineering/ | 模板构建、Skills 机制、好/差 Prompt 区别、框架创新 |
| 09 | RAG 与检索 | 09-rag-retrieval/ | chunk 设计、查询改写、召回精排、Embedding/ReRank 微调 |
| 10 | 训练与模型 | 10-training-and-data/ | 数据清洗、LoRA、PPO/DPO/GRPO、位置编码、归一化、量化部署、多模态 |
| 11 | AI 代码测试 | 11-ai-code-testing/ | 覆盖率插桩、前置分析、代码过滤 |
| 12 | 业务 AI 工程 | 12-business-ai-engineering/ | 业务需求拆解、方案选型、效果评估、智能客服与业务落地 |
| 13 | 简历项目拷打 | 13-project-deep-dive/ | 项目部署、框架选型、意图识别、工具设计、知识库构建、性能优化 |
| 14 | 公司偏好(派生页) | 14-company-preferences/ | 从各维度来源统计公司考察偏好,不直接写入新题 |
| 15 | Agent 概念 | 15-agent-concepts/ | Harness/Context Engineering、Vibe Coding、MCP、Skills 等概念辨析 |
| 16 | Agent Infra | 16-agent-infra/ | Runtime、Checkpoint、幂等、Sandbox、Kubernetes、调度与可观测 |
| 17 | AI Infra | 17-ai-infra/ | 分布式训练、LLM Serving、GPU 调度、模型发布与 AIOps |
以本轮抓取的 manifest.json 为唯一输入清单,按 articles[] 顺序生成稳定序号。每篇必须使用 localSourcePath 指向的原文;不能只遍历当前输出目录,因为复用文章可能位于历史目录。
先读取两个仓库现有题目索引/标题。Agent 侧以本 Skill 的 question-index.md 为快速索引;后端侧读取 summer include 的编号标题。
批量任务统一运行维护脚本:
python .claude/skills/classify-interview-questions/scripts/batch_extract_and_recall.py \
--manifest ".claude/skills/scrape-nowcoder/nowcoder-output-<range>/manifest.json" \
--out ".codex-tmp/llm-interview-audit-<range>" \
--model "gpt-5.6-luna" \
--outer-workers 3 --workers 8 \
--rerank-batch-size 1 --candidate-k 12 --top-k 5固定约束:
gpt-5.6-luna。除非用户明确指定,不使用更慢的模型跑整批原文。extract_and_recall.py --llm,不能把 all-in-one.md 当成一篇输入;否则会丢失文章归因和 canonical URL 边界。--workers 负责问题级重排。默认 3 x 8;遇到限流时先降低外层并发,不降低抽取完整性。high/review/low 只是召回带,不直接决定新增。batch-summary.json,不保存配置密钥。gate_rejected,自动重试 failed。需要重新检查门禁拒绝项时显式加 --retry-gate-rejected。pre_gate_rejected,不调用抽题 API。gate_rejected 同样不会进入抽题阶段。duplicate-evidence.jsonl、enhancement.jsonl、novel.jsonl、review.jsonl、out-of-scope.jsonl。中断时已完成文章的队列结果仍可恢复。对于单篇诊断仍可直接运行:
python .claude/skills/classify-interview-questions/scripts/extract_and_recall.py \
--input article.md --llm --llm-model gpt-5.6-luna --workers 8 \
--rerank-batch-size 1 --candidate-k 12 --top-k 5 \
--format json --out audit.json读取 batch-summary.json 并验证:
articleCount == completedCount == manifest.articles.length。failed == 0 且所有成功结果的 llmErrorCount == 0。no_questions 表示 Luna 完成判断但没有抽出完整题干,是可审计的空结果;真正失败项必须重跑,不能用确定性抽取静默替代。model 和逐篇 llm.model 均为本轮指定的 Luna 模型。gate_rejected 保留在账本中,并与空正文、失效页、教程、推广、付费聚合和重复账号稿核对。extract_and_recall.py --allow-non-interview --llm 重跑;禁止整批绕过门禁。sourceClassification、完整问题、Top-K、llmRelation、llmConfidence 和原因。不得只留最终题目清单。候选判断只消费逐篇 JSON、四类队列和必要的现有目标题块,不再重新把整篇原文交给 Agent 阅读。默认自动归并规则:
same 置信度不低于 0.85:从新题候选中丢弃,进入 duplicate-evidence,用于补来源和 frequency。same,但 overlap 不低于 0.80:进入 enhancement,补追问、反例或答案缺口。same/overlap,且 different 不低于 0.85:进入 novel 新题候选队列。review,禁止自动新增。out_of_scope;缺少指代对象或题干截断的问题进入 review。它们不能因为与技术题库不同而进入 novel。可随时用结果账本重新生成队列:
python .claude/skills/classify-interview-questions/scripts/build_recall_queues.py \
--summary ".codex-tmp/llm-interview-audit-<range>/batch-summary.json" \
--out ".codex-tmp/llm-interview-audit-<range>/queues"最终逐题输出:
新增:核心考点或工程约束确实不同。增强:同一核心题,只追加来源、追问、反例或现有答案缺失部分。排除:非目标域、个人化且无法通用、题干不完整、重复/推广/无可靠来源。LLM 的 same/overlap/different 和置信度是证据,不是最终裁决。高相似仍可能是约束不同的新题;低相似也可能是已有题的换词。每项 ledger 必须记录原始文章序号、canonical URL、LLM 问题文本、Top-K 和最终理由。
对需要当前事实、协议、框架或模型细节的新增题,查当前一手资料,返回支持具体结论的官方直达链接,并明确事实与推断。调研阶段不直接编辑题库。
把最终确认的新题和增强映射按目标文件分组。一个文件同一时间只允许一个写作者;写作者只读取目标全文、相邻问题和结构化候选,不重新扫描原始面经。共享的 question-index.md、question-frequency.json、入口计数和排序由主流程最后单点维护。
传统后端题按连续编号写入 zero2leetcode summer include;算法题只更新算法题单,不占传统八股编号。
主流程负责:
question-index.md 的连续编号、维度数、总数、来源追问和日期。question-frequency.json:同题新增面经时追加唯一 evidence,新题新增完整记录,然后执行组内频次排序。05_interview/index.md 的入口计数。llmErrors、抽取题数、新增数、增强数、公开原文链接数、授权但无公开 URL 的来源数,以及各类排除数。收到面试题后,逐题判断属于哪个维度:
输出分类结果表格供用户确认(如果题量大可直接执行)。
先读取 question-index.md(位于本 skill 目录下),快速判断新题是否与已有题目重复或高度相似;再读取 question-frequency.json,确认已有题的历史面经证据。仅在需要定位主题组和插入位置时读取目标 md 文件。
对每篇目标文章:
每道题用标准格式:
## Q:{面试题(通用化后的表述)}
> 来源:[{公司 / 岗位 / 轮次}]({原始面经 URL})
**新手答**:"{浅层回答}"
**高手答**:
{深度回答,分层递进,带具体方案}
**差距在哪**:{分析差距,点出面试官考什么}如果来源是用户授权但没有公开 URL 的本地材料,使用:
> 来源:用户授权的「{题库名称}」(无公开 URL)答案中的外部事实链接放在对应结论附近。面试来源链接证明“这道题被问过”,官方资料链接证明“答案里的事实依据”,两者不能互相替代。
善用 Mermaid 流程图:当答案涉及多阶段流程、对比关系或架构拆分时,优先用 ```mermaid 流程图替代纯文本 ASCII 图。项目前端已支持 Mermaid 渲染,流程图比文字列表更直观。适合使用的场景:
不需要每道题都加图,只在图比文字更清晰时使用。
插入完成后,对所有修改过的文件运行:
python3 .claude/skills/chinese-quotes-fix/fix_quotes.py "learn-agent-interview/{目标目录}/index.md"分发完成后,更新 question-index.md:
同步维护 question-frequency.json:
frequency == evidence.lengthfirstSeenOrder 记录题目在当前维度的初次入库顺序,只在新题首次建档时分配,后续重排不得修改最后执行稳定排序并校验三个索引:
python .claude/skills/classify-interview-questions/scripts/sync_question_frequency.py
python .claude/skills/classify-interview-questions/scripts/sort_questions_by_frequency.py
python .claude/skills/classify-interview-questions/scripts/sync_question_frequency.py --check
python .claude/skills/classify-interview-questions/scripts/sort_questions_by_frequency.py --check
python .claude/skills/classify-interview-questions/scripts/build_question_index_json.py
python .claude/skills/classify-interview-questions/scripts/build_question_index_json.py --check输出分发结果表格:
| 题目 | 分发到 |
|---|---|
| Q1: ... | 05-eval-and-vision (新增) |
| Q2: ... | 10-training-and-data (增强已有) |
question-index.md、question-frequency.json、总数入口、频次排序和最终统计始终由主 Agent 单点维护。© ranxi2001, 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 18 other files (scripts) in .agents/skills/classify-interview-questions of ranxi2001/zero2Agent.
Open the folder on GitHubat commit 472ce78
Classify Interview Questions 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 |
|---|---|---|---|---|---|---|
| Classify Interview Questions this skillranxi2001/zero2Agent | 677 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Oai Solution Reviewershepherdjerred/monorepo | 112 | — | ~1.9k | Automated safety check: Pass | GPL-3.0 | |
| Algo Senseikaranb192/algo-sensei | 284 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Backend and Agent Project Selectorlishuangqiang/backend-agent-resume-scout | 347 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Interview Skillsjennifer88huang/interview-skills | 362 | — | ~3.1k | Automated safety check: Notes | None | |
| Backend Interview SimulatorHazehacker/backend-interview-simulator | 204 | — | ~2.3k | Automated safety check: Pass | MIT |
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…
karanb192/algo-sensei
Your personal DSA & LeetCode mentor. An agent skill from karanb192/algo-sensei.
lishuangqiang/backend-agent-resume-scout
Finds backend or AI agent projects on GitHub that are worth putting on a resume, checks them against local source and writes a Markdown resume package.
jennifer88huang/interview-skills
大厂 AI 模拟面试官。覆盖阿里、腾讯、字节跳动、百度、美团、京东、华为、滴滴、拼多多、Google、Meta、Amazon、Microsoft 等国内外头部互联网/科技公司。用户输入目标公司名、岗位名和 JD 内容,上传简历后,Agent 扮演大厂面试官,结合 JD 要求与简历情况,输出 10 道高质量面试题(含难度、参考答案提示、追问方向),并支持生成「好答案 vs 差答案」对比示例、HR…
Hazehacker/backend-interview-simulator
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…
coinluu/resume-jd-optimizer-cn
基于目标岗位 JD、中文简历和用户确认的真实经历,完成中国大陆求职场景下的 JD 解析、证据映射、缺口诊断、素材追问、定制简历重写、ATS/HR/面试官审查及投递沟通材料生成。用于应届、社招、转行及互联网、AI、产品、运营、销售、技术、数据、设计等岗位;当用户要求针对 JD 优化中文简历、提高匹配度、生成 Boss 直聘或猎头话术、检查面试自洽性时使用。
ranxi2001/zero2Agent
A skill your agent uses when user requests diagrams, flowcharts, architecture charts, or visualizations.
ranxi2001/zero2Agent
Check and fix Chinese quote pairing in Markdown files generated by ClaudeCode or other agents, while preserving Markdown syntax and protected blocks.
ranxi2001/zero2Agent
在 zero2Agent 项目中创建新的学习文章。当用户说"写一篇新文章"、"创建文章"、"新建文章"、"在某模块下添加一篇关于X的文章"、"帮我起草一篇讲XX的内容"、"整理面经"时触发。适用于所有模块下新建内容,包括面试维度拆解文章和面经实录。即使用户没有明确说"文章",只要涉及给 zero2Agent 项目增加教学内容,也应当触发此技能。
ranxi2001/zero2Agent
在 zero2Agent 项目中创建新的学习模块。当用户说"新建模块"、"添加模块"、"创建一个新的学习章节"、"我想增加一个关于X的模块"时触发。负责创建模块目录结构、index.md,并同步更新主页 index.html 和 layouts/default.html 的导航。即使用户只是说"我想增加一个讲XX的章节",也应当触发此技能。
ranxi2001/zero2Agent
基于 CDP 原生 WebSocket 抓取牛客网面经文章。当用户说"抓牛客"、"爬牛客面经"、"nowcoder 抓取"、"抓取面经列表"时触发。通过 Chrome 调试端口直接连接已登录的浏览器会话,支持首页、话题、搜索分页和详情全文抓取,输出 Markdown。
ranxi2001/zero2Agent
审查 zero2Agent 项目中的文章内容质量。当用户说"审查文章"、"review内容"、"检查这篇文章写得怎么样"、"看看这篇符不符合项目风格"、"帮我看看内容质量"时触发。负责对照项目风格标准进行结构化评审,输出具体的改进建议。即使用户只是说"帮我看看写得怎么样",只要涉及 zero2Agent 的 Markdown 文章,也应当触发此技能。
Works with
Categories
将批量面经或零散面试题逐题去重并分发:Agent/LLM/AI工程题写入 zero2Agent 的 learn-agent-interview,传统后端八股写入相邻 zero2Leetcode 的夏季八股。大批量输入使用 gpt-5.6-luna API 逐篇并发抽题和语义召回,再审查、去重和写答案;不新建面经实录文章。. Classify Interview Questions is an agent skill from ranxi2001/zero2Agent.
Classify Interview Questions fits situations like: tasks that involve Interview preparation.
Run `npx skills add ranxi2001/zero2Agent --skill classify-interview-questions -a claude-code`. Or copy the skill folder (.agents/skills/classify-interview-questions in ranxi2001/zero2Agent) into .claude/skills/classify-interview-questions in your project. Claude Code loads it when a task matches its description.
Run `npx skills add ranxi2001/zero2Agent --skill classify-interview-questions -a codex`. Or copy the skill folder (.agents/skills/classify-interview-questions in ranxi2001/zero2Agent) into .agents/skills/classify-interview-questions 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 ranxi2001/zero2Agent --skill classify-interview-questions -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/classify-interview-questions, .gemini/skills/classify-interview-questions, .github/skills/classify-interview-questions and .opencode/skills/classify-interview-questions in your project.
Going by SKILL.md and its folder, Classify Interview Questions needs Python for the scripts in its folder and the command-line tools its instructions call (python and python3). Our summary lists: Python 3.
SKILL.md names 1 domain. In commands or code: nowcoder.com; the agent is likely to contact it when it follows the instructions. 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Classify Interview Questions is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Classify Interview Questions: Oai Solution Reviewer (shepherdjerred/monorepo, 112 stars), Algo Sensei (karanb192/algo-sensei, 284 stars), Backend and Agent Project Selector (lishuangqiang/backend-agent-resume-scout, 347 stars) and Interview Skills (jennifer88huang/interview-skills, 362 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
ranxi2001 (a GitHub user) maintains it in ranxi2001/zero2Agent, which has 677 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 7, 2026.
Source: ranxi2001/zero2Agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.