LLM Intern Skill
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…
Plays an interviewer for AI agent developer roles, probing agent loops, tool integration, MCP, RAG, context engineering and multi-agent design through practical scenarios.
SKILL.md written in Chinese; this summary is our English description.
Install AI Agent Developer Interview Questions
$ npx skills add Snailclimb/interview-guide --skill ai-agent-dev -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Snailclimb/interview-guide ai-agent-dev --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/Snailclimb/interview-guide.git skills-src && mkdir -p .claude/skills && cp -r skills-src/app/src/main/resources/skills/ai-agent-dev .claude/skills/ai-agent-dev && 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 "ai-agent-dev" agent skill from https://github.com/Snailclimb/interview-guide/tree/master/app/src/main/resources/skills/ai-agent-dev into .claude/skills/ai-agent-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-agent-dev", 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/Snailclimb/interview-guide/tree/master/app/src/main/resources/skills/ai-agent-devType 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 Snailclimb/interview-guide --skill ai-agent-dev -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Snailclimb/interview-guide ai-agent-dev --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Snailclimb/interview-guide.git skills-src && mkdir -p .agents/skills && cp -r skills-src/app/src/main/resources/skills/ai-agent-dev .agents/skills/ai-agent-dev && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ai-agent-dev" agent skill from https://github.com/Snailclimb/interview-guide/tree/master/app/src/main/resources/skills/ai-agent-dev into .agents/skills/ai-agent-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-agent-dev", 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 Snailclimb/interview-guide --skill ai-agent-dev -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Snailclimb/interview-guide ai-agent-dev --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Snailclimb/interview-guide.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/app/src/main/resources/skills/ai-agent-dev .cursor/skills/ai-agent-dev && 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 "ai-agent-dev" agent skill from https://github.com/Snailclimb/interview-guide/tree/master/app/src/main/resources/skills/ai-agent-dev into .cursor/skills/ai-agent-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-agent-dev", 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/Snailclimb/interview-guide.git --path app/src/main/resources/skills/ai-agent-dev--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 Snailclimb/interview-guide --skill ai-agent-dev -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Snailclimb/interview-guide ai-agent-dev --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Snailclimb/interview-guide.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/app/src/main/resources/skills/ai-agent-dev .gemini/skills/ai-agent-dev && 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 "ai-agent-dev" agent skill from https://github.com/Snailclimb/interview-guide/tree/master/app/src/main/resources/skills/ai-agent-dev into .gemini/skills/ai-agent-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-agent-dev", 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 Snailclimb/interview-guide ai-agent-devInstalls 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 Snailclimb/interview-guide --skill ai-agent-dev -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Snailclimb/interview-guide.git skills-src && mkdir -p .github/skills && cp -r skills-src/app/src/main/resources/skills/ai-agent-dev .github/skills/ai-agent-dev && 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 "ai-agent-dev" agent skill from https://github.com/Snailclimb/interview-guide/tree/master/app/src/main/resources/skills/ai-agent-dev into .github/skills/ai-agent-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-agent-dev", 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 Snailclimb/interview-guide --skill ai-agent-dev -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Snailclimb/interview-guide ai-agent-dev --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Snailclimb/interview-guide.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/app/src/main/resources/skills/ai-agent-dev .opencode/skills/ai-agent-dev && 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 "ai-agent-dev" agent skill from https://github.com/Snailclimb/interview-guide/tree/master/app/src/main/resources/skills/ai-agent-dev into .opencode/skills/ai-agent-dev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ai-agent-dev", 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.
Facts
- Skill name
ai-agent-dev- GitHub stars
- 3.3k
- Token cost
- ~183 tokens
- SKILL.md length
- 52 words
- Files
- 3
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Plays an interviewer for AI agent developer roles, probing agent loops, tool integration, MCP, RAG, context engineering and multi-agent design through practical scenarios.
- Works in 6 steps: 先确认候选人的技术栈（LangChain / Spring AI /… → 提问遵循梯度：使用经验 -> 原理机制 -> 边界与故障 -> 优化与权衡。 → 每个主问题必须包含至少一个权衡点（如召回率 vs 延迟、上下文长度 vs… → …
- Preparing interview questions for an AI agent developer role
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Practicing for an agent engineering interview
What it does
The skill sets the agent up as an interviewer, with instructions written in Chinese, who tests whether a candidate can build agent systems and not only describe concepts. Topics are agent loop design, tool integration, context management, the quality of RAG retrieval and multi-agent collaboration. It begins by asking about the candidate's stack, such as LangChain, Spring AI or a custom framework, and their real project experience, and bases follow-up questions on those projects.
Questions climb a ladder from experience to mechanism, then to limits and failures, then to optimization and trade-offs. Every main question needs at least one trade-off, such as recall against latency or context length against information density. When answers stay abstract the interviewer presses for specifics: protocol choice, token budgets, retry policy and observability metrics. At least once the candidate is asked for measurable numbers, and scenario questions are required, for example how to debug a hallucination loop in a live agent. A companion file groups the question bank by category.
When your agent uses it
- Preparing interview questions for an AI agent developer role
- Practicing for an agent engineering interview
- Probing a candidate's real project experience with RAG and MCP
Example prompts
- “Interview me for an AI agent developer position, starting from my Spring AI project.”
- “Give me scenario questions on context engineering and multi-agent design.”
- “Ask me how I would debug a hallucination loop in a production agent.”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- 先确认候选人的技术栈（LangChain / Spring AI / 自研框架）和实际项目经验，围绕真实项目追问。
- 提问遵循梯度：使用经验 -> 原理机制 -> 边界与故障 -> 优化与权衡。
- 每个主问题必须包含至少一个权衡点（如召回率 vs 延迟、上下文长度 vs 信息密度）。
- 回答停留在概念层时，必须追问具体实现：协议选型、Token 预算分配、错误重试策略、可观测性指标。
- 至少一次要求候选人给出可量化指标（如 TTFT、P99 延迟、检索召回率、Token 利用率）。
- 不要只问名词解释，必须有场景化问题（如"线上 Agent 出现幻觉循环，你怎么排查"）。
What it can do on your machine
Read from SKILL.md and the folder at commit 969e2af. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
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.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
AI Agent Developer Interview Questions loads about 183 tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 52 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.
Safety
Auto-check passed
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.
SKILL.md
The full file from Snailclimb/interview-guide at commit 969e2af, republished under its AGPL-3.0 licence (© Snailclimb). 52 words, ~183 tokens.
Download SKILL.mdSave it as
.claude/skills/ai-agent-dev/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- ai-agent-dev
- description
- 用于 AI Agent 开发岗位面试出题；覆盖 Agent 架构、LLM 调用、工具集成、MCP 协议、RAG、上下文工程与多 Agent 协作，强调工程落地与故障处理能力。
Overview
你是一位 AI Agent 开发岗位面试官，关注候选人对 Agent 系统的工程实现能力，而不是只会描述概念。重点考察：Agent Loop 设计、工具集成方式、上下文管理策略、RAG 检索质量治理和多 Agent 协作模式。
Instructions
- 先确认候选人的技术栈（LangChain / Spring AI / 自研框架）和实际项目经验，围绕真实项目追问。
- 提问遵循梯度：使用经验 -> 原理机制 -> 边界与故障 -> 优化与权衡。
- 每个主问题必须包含至少一个权衡点（如召回率 vs 延迟、上下文长度 vs 信息密度）。
- 回答停留在概念层时，必须追问具体实现：协议选型、Token 预算分配、错误重试策略、可观测性指标。
- 至少一次要求候选人给出可量化指标（如 TTFT、P99 延迟、检索召回率、Token 利用率）。
- 不要只问名词解释，必须有场景化问题（如"线上 Agent 出现幻觉循环，你怎么排查"）。
Additional Resources
出题前优先参考这些资料，并按分类落题：
- AGENT_BASIS / LLM_CALLING / MCP_PROTOCOL / RAG / CONTEXT_ENGINEERING / MULTI_AGENT / PROJECT -> ai-agent-dev.md
© Snailclimb, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files in app/src/main/resources/skills/ai-agent-dev of Snailclimb/interview-guide.
- SKILL.md
- ai-agent-dev.md
- skill.meta.yml
Open the folder on GitHubat commit 969e2af
Compare with similar skills
AI Agent Developer 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 |
|---|---|---|---|---|---|---|
| AI Agent Developer Interview Questions this skillSnailclimb/interview-guide | 3.3k | — | ~183 | Automated safety check: Pass | AGPL-3.0 | |
| LLM Intern Skillwanyichen06/LLMInternSkill | 324 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Backend Interview SimulatorHazehacker/backend-interview-simulator | 206 | — | ~2.3k | Automated safety check: Pass | MIT | |
| Resume Evidence WorkflowElowwwen/resume-evidence-workflow | 163 | — | ~2.4k | Automated safety check: Pass | MIT | |
| Evaluateandrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2- | 501 | — | ~1.9k | Automated safety check: Pass | MIT | |
| Offer Toolkit Skillyanliudesign/offer-toolkit-skill | 520 | — | ~1.2k | Automated safety check: Pass | MIT |
Similar skills
Backend Interview Simulator
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…
Resume Evidence Workflow
Elowwwen/resume-evidence-workflow
Build a reusable career-evidence bank, match it to a job description (JD), select the best installed resume skill, and deliver an application-ready resume.
Evaluate
andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-
Evaluate how well a job posting matches your background. An agent skill from andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-.
Offer Toolkit Skill
yanliudesign/offer-toolkit-skill
求职工具包。把「找岗位 → 签 offer」拆成六个独立子 skill：⓪ Job Hunt 批量发现岗位，① Job Description 解码具体 JD，② Resume 定向简历，③ BQ 准备行为面试，④ Offer Compare 对比多份 offer，⑤ Salary Negotiation 谈 package。任何求职相关请求（找工作、该不该投、改简历、准备面试、选…
Solana Agent Kit
internet-court/internet-court-skill
Walks through building AI agents that run Solana operations such as token deploys, NFT minting, swaps and staking with SendAI's toolkit, in chat or fully autonomous mode.
More from Snailclimb/interview-guide
All 9 skills in this repoAlibaba Backend Interviewer
Snailclimb/interview-guide
Generates backend interview questions in the style of an Alibaba interviewer, probing real projects, trade-offs and middleware choices in depth.
ByteDance Backend Interviewer
Snailclimb/interview-guide
Plays a ByteDance backend interviewer who sets algorithm questions first, probes correctness and complexity, then asks how the solution holds up under high concurrency.
Frontend Interview Question Setter
Snailclimb/interview-guide
Sets frontend engineering interview questions on JavaScript, React or Vue, browser internals and performance, with scenario-based follow-ups drawn from the candidate's resume.
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.
Tencent Java Backend Interview
Snailclimb/interview-guide
Sets the agent up as a Tencent-style backend interviewer who probes networking and operating-system fundamentals, then ties technology choices to business scenarios.
Python Backend Interview Questions
Snailclimb/interview-guide
Acts as a Python backend interviewer, setting practical questions on Python basics, databases, Django and Flask, caching and deployment, with follow-ups on real production work.
Related
Works with
Questions about AI Agent Developer Interview Questions
What does AI Agent Developer Interview Questions do?
Plays an interviewer for AI agent developer roles, probing agent loops, tool integration, MCP, RAG, context engineering and multi-agent design through practical scenarios. The skill sets the agent up as an interviewer, with instructions written in Chinese, who tests whether a candidate can build agent systems and not only describe concepts. Topics are agent loop design, tool integration, context management, the quality of RAG retrieval and multi-agent collaboration.
When should I use AI Agent Developer Interview Questions?
AI Agent Developer Interview Questions fits situations like: preparing interview questions for an AI agent developer role; practicing for an agent engineering interview; probing a candidate's real project experience with RAG and MCP.
How do I install AI Agent Developer Interview Questions in Claude Code?
Run `npx skills add Snailclimb/interview-guide --skill ai-agent-dev -a claude-code`. Or copy the skill folder (app/src/main/resources/skills/ai-agent-dev in Snailclimb/interview-guide) into .claude/skills/ai-agent-dev in your project. Claude Code loads it when a task matches its description.
How do I install AI Agent Developer Interview Questions in Codex?
Run `npx skills add Snailclimb/interview-guide --skill ai-agent-dev -a codex`. Or copy the skill folder (app/src/main/resources/skills/ai-agent-dev in Snailclimb/interview-guide) into .agents/skills/ai-agent-dev in your project. Codex loads it when a task matches its description.
Can I use AI Agent Developer Interview Questions in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Snailclimb/interview-guide --skill ai-agent-dev -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-agent-dev, .gemini/skills/ai-agent-dev, .github/skills/ai-agent-dev and .opencode/skills/ai-agent-dev in your project.
What does AI Agent Developer Interview Questions need to run?
SKILL.md names no scripts, command-line tools or credentials: AI Agent Developer Interview Questions is instructions for the agent only.
Does AI Agent Developer Interview Questions access the network?
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.
Is AI Agent Developer Interview Questions safe to install?
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.
What licence does AI Agent Developer Interview Questions use?
AI Agent Developer Interview Questions is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does AI Agent Developer Interview Questions use?
About 183 tokens (SKILL.md is roughly 732 characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to AI Agent Developer Interview Questions?
Skills that share tags, products or a category with AI Agent Developer Interview Questions: LLM Intern Skill (wanyichen06/LLMInternSkill, 324 stars), Backend Interview Simulator (Hazehacker/backend-interview-simulator, 206 stars), Resume Evidence Workflow (Elowwwen/resume-evidence-workflow, 163 stars) and Evaluate (andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-, 501 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains AI Agent Developer Interview Questions?
Snailclimb (a GitHub user) maintains it in Snailclimb/interview-guide, which has 3,315 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 16, 2026.
Source: Snailclimb/interview-guide on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.