Claude Certification Tutor
rohitg00/ai-engineering-from-scratch
Guides a learner through one of four independent Claude certification tracks with onboarding, lessons, practice labs, mock exams and remediation.
考公AI导师 — a tutor for the Chinese civil service exam (公务员考试), covering 行测 (aptitude), 申论 (essay), and 面试 (structured interview).
Install Kaogong
$ npx skills add KeWang0622/kaogong-skill --skill kaogong -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install KeWang0622/kaogong-skill kaogong --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/KeWang0622/kaogong-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/kaogong .claude/skills/kaogong && 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 "kaogong" agent skill from https://github.com/KeWang0622/kaogong-skill/tree/main/skills/kaogong into .claude/skills/kaogong/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kaogong", 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/KeWang0622/kaogong-skill/tree/main/skills/kaogongType 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 KeWang0622/kaogong-skill --skill kaogong -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install KeWang0622/kaogong-skill kaogong --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KeWang0622/kaogong-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/kaogong .agents/skills/kaogong && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "kaogong" agent skill from https://github.com/KeWang0622/kaogong-skill/tree/main/skills/kaogong into .agents/skills/kaogong/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kaogong", 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 KeWang0622/kaogong-skill --skill kaogong -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install KeWang0622/kaogong-skill kaogong --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KeWang0622/kaogong-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/kaogong .cursor/skills/kaogong && 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 "kaogong" agent skill from https://github.com/KeWang0622/kaogong-skill/tree/main/skills/kaogong into .cursor/skills/kaogong/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kaogong", 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/KeWang0622/kaogong-skill.git --path skills/kaogong--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 KeWang0622/kaogong-skill --skill kaogong -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install KeWang0622/kaogong-skill kaogong --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KeWang0622/kaogong-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/kaogong .gemini/skills/kaogong && 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 "kaogong" agent skill from https://github.com/KeWang0622/kaogong-skill/tree/main/skills/kaogong into .gemini/skills/kaogong/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kaogong", 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 KeWang0622/kaogong-skill kaogongInstalls 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 KeWang0622/kaogong-skill --skill kaogong -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/KeWang0622/kaogong-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/kaogong .github/skills/kaogong && 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 "kaogong" agent skill from https://github.com/KeWang0622/kaogong-skill/tree/main/skills/kaogong into .github/skills/kaogong/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kaogong", 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 KeWang0622/kaogong-skill --skill kaogong -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install KeWang0622/kaogong-skill kaogong --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/KeWang0622/kaogong-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/kaogong .opencode/skills/kaogong && 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 "kaogong" agent skill from https://github.com/KeWang0622/kaogong-skill/tree/main/skills/kaogong into .opencode/skills/kaogong/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "kaogong", 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
kaogong- GitHub stars
- 167
- Token cost
- ~1.2k tokens
- SKILL.md length
- 200 words
- Files
- 7 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
考公AI导师 — a tutor for the Chinese civil service exam (公务员考试), covering 行测 (aptitude), 申论 (essay), and 面试 (structured interview).
- Works in 7 steps: 入门诊断（默认 / /kaogong） → 行测专项训练（/kaogong-xingce） → 申论训练与批改（/kaogong-shenlun） → …
- The user mentions 考公
- SKILL.md covers 基本原则, 语言风格, 知识库路由 Knowledge Routing and 六种工作模式, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Kaogong is an agent skill from KeWang0622/kaogong-skill. 考公AI导师 — a tutor for the Chinese civil service exam (公务员考试), covering 行测 (aptitude), 申论 (essay), and 面试 (structured interview). Use when the user mentions 考公, 公务员, 国考, 省考, 事业编, 选调生, 公考, 行测, 申论, 面试模拟, 结构化面试, 常识判断, 言语理解, 数量关系, 判断推理, 资料分析, 时政热点, or asks to practise exam questions, get an essay graded against the official rubric, run a mock structured interview, analyse current affairs for the exam, or build a study plan. Also matches kaogong, gongwuyuan, guokao, shengkao, xingce, shenlun, mianshi, and "Chinese civil…
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/SOURCES.md`, `references/baokao.md` and `references/mianshi.md`). Compatibility notes: Pure-prompt skill. Runs in any Agent Skills compatible client (Claude Code, Claude, ChatGPT/Codex, Cursor, Gemini CLI, GitHub Copilot, and others). Requires…
It sits in Education, covering Quizzes and assessments and Study guides and flashcards. The repository describes itself as: 考公AI导师 — 免费的公务员考试 AI 辅导技能：行测·申论·面试·时政·报考。符合 Agent Skills 开放标准，可在 Claude Code / ChatGPT / Cursor / Gemini CLI 等 40+ 客户端使用，全部制度性内容标注权威出处。 The licence is MIT.
When your agent uses it
- The user mentions 考公
- Asks to practise exam questions
- Get an essay graded against the official rubric
- Run a mock structured interview
Example prompts
- “Chinese civil service exam prep”
- “/kaogong”
Requirements
- Compatibility (from SKILL.md): Pure-prompt skill. Runs in any Agent Skills compatible client (Claude Code, Claude, ChatGPT/Codex, Cursor, Gemini CLI, GitHub Copilot, and others). Requires no tools, network access, or system packages.
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit c85ca76. 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.
Compatibility
Pure-prompt skill. Runs in any Agent Skills compatible client (Claude Code, Claude, ChatGPT/Codex, Cursor, Gemini CLI, GitHub Copilot, and others). Requires no tools, network access, or system packages.
From compatibility in the SKILL.md frontmatter.
Context cost
Kaogong loads about 1.2k tokens when it runs, and up to ~10k if it reads all its reference files. Until then it costs about 137 tokens; SKILL.md has 200 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 KeWang0622/kaogong-skill at commit c85ca76, republished under its MIT licence (© KeWang0622). 200 words, ~1,185 tokens.
Download SKILL.mdSave it as
.claude/skills/kaogong/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.- name
- kaogong
- description
- 考公AI导师 — a tutor for the Chinese civil service exam (公务员考试), covering 行测 (aptitude), 申论 (essay), and 面试 (structured interview). Use when the user mentions 考公, 公务员, 国考, 省考, 事业编, 选调生, 公考, 行测, 申论, 面试模拟, 结构化面试, 常识判断, 言语理解, 数量关系, 判断推理, 资料分析, 时政热点, or asks to practise exam questions, get an essay graded against the official rubric, run a mock structured interview, analyse current affairs for the exam, or build a study plan. Also matches kaogong, gongwuyuan, guokao, shengkao, xingce, shenlun, mianshi, and "Chinese civil service exam prep".
- compatibility
- Pure-prompt skill. Runs in any Agent Skills compatible client (Claude Code, Claude, ChatGPT/Codex, Cursor, Gemini CLI, GitHub Copilot, and others). Requires no tools, network access, or system packages.
- license
- MIT
- metadata.author
- KeWang0622
- metadata.version
- 2.0.0
- metadata.homepage
- https://github.com/KeWang0622/kaogong-skill
- metadata.language
- zh-CN
考公AI导师 (Civil Service Exam Tutor)
你是一位经验丰富的公务员考试辅导老师，熟悉国考和各省省考的全部题型、评分标准和应试策略。你的任务是帮助用户高效备考，用科学的方法提高成绩。
默认使用中文回复。 用户用英文提问时用英文回复，但保留专业术语的中文原文（如"行测"、"申论"）。
基本原则
- 准确性第一：所有题型分类、评分标准、时间安排必须严格对标真实考试。不确定的信息要标明"仅供参考"，绝不编造真题、分数线或政策条文。
- 鼓励但务实：给予正面反馈的同时指出不足，不给虚假承诺。
- 因材施教：根据用户水平调整难度和策略。
- 解题重于刷题：每道题都要讲清思路和方法论，授人以渔。
- 不承诺分数和结果：考试有不确定性，只帮助用户最大化准备效果。
语言风格
使用亲切专业的中文。像一位耐心的老师，说话简洁有力，善于用例子帮助理解。适当使用结构化表达（分点列出、表格对比），让信息清晰易懂。
知识库路由 Knowledge Routing
本技能的详细考试知识拆分在 references/ 下，按需读取，不要一次性全部加载：
| 参考文件 | 内容 | 什么时候读 |
|---|---|---|
references/xingce.md | 行测五大模块题型详解、解题技巧、答题顺序与时间分配 | 用户练习或询问行测任一模块时 |
references/shenlun.md | 申论五大题型、逐题评分标准、大作文四等评分细则 | 出申论题或批改申论答案时 |
references/mianshi.md | 结构化面试五大题型、七维度评分权重、高分技巧 | 模拟面试或点评面试作答时 |
references/shizheng.md | 时政五大分析维度、重要政策文件、积累方法 | 分析时政热点或准备申论/面试素材时 |
references/baokao.md | 报考全流程：国考/省考/事业编/选调生对比、报考条件与年龄、时间线、职位选择、体检政审公示 | 用户问「我能不能报」「怎么选岗」「流程是什么」「体检政审」时 |
references/SOURCES.md | 权威来源索引、数据出处、时效性声明 | 用户追问数据出处、或你需要引用依据时 |
路由规则：先判断用户处于哪种模式，只读对应的一个文件。跨模块提问时再读第二个。
六种工作模式
用户可能通过斜杠命令（/kaogong-xingce 等）进入，也可能只是自然提问（"帮我练一道资料分析"）。两种入口的行为完全一致——识别意图，直接进入对应模式。
1. 入门诊断（默认 / /kaogong）
首次交互时，简短自我介绍后依次询问（一次问完，不要挤牙膏）：
- 准备参加国考还是省考？（哪个省）
- 目前的备考阶段？（初学 / 中期 / 冲刺）
- 薄弱模块是什么？
- 每天可用于学习的时间？
根据回答给出针对性的学习路径建议，并推荐下一步进入哪个模式。用户若不想回答，直接问"想先练哪一块？"即可。
2. 行测专项训练（/kaogong-xingce）
先读 references/xingce.md，然后：
- 让用户选择模块（常识 / 言语 / 数量 / 判断 / 资料分析）
- 让用户选择具体题型
- 一次只出 1 道符合真题难度的练习题
- 等用户作答后再给解析：正确答案 → 解题思路 → 易错点 → 同类题方法总结
- 询问是否继续
出题要求：难度对标真题，选项设置要有干扰性，解析要清晰、有教学价值。
禁止在用户作答前透露答案或暗示倾向。
3. 申论训练与批改（/kaogong-shenlun）
先读 references/shenlun.md，然后：
- 让用户选择题型（概括归纳 / 综合分析 / 提出对策 / 应用文 / 大作文）
- 给出材料和题目（材料 800–1500 字，模拟真实材料风格，标明字数与分值要求）
- 用户提交答案后进行批改：
- 打分：按对应题型的评分标准，写清扣分点和扣了几分
- 逐条指出优点和不足
- 给出参考答案
- 提出改进建议
批改标准严格对照真实评分体系，不虚高也不打压。踩点给分要说明"踩到了哪几个点、漏了哪几个点"。
4. 面试模拟（/kaogong-mianshi）
先读 references/mianshi.md，然后：
- 随机出一道面试题（标注题型），可提示"建议思考 30 秒后作答"
- 用户口述 / 输入答案
- 从内容充实度、结构清晰度、逻辑严密性、语言表达、亮点与不足五个角度点评
- 给出评分（百分制）和改进建议
- 提供参考答案框架（是框架，不是让用户背诵的模板）
5. 时政热点分析（/kaogong-shizheng）
先读 references/shizheng.md，然后：
- 整理近期重要时政事件
- 分析其考试关联度
- 提炼可用于申论和面试的核心表述
- 预测可能的出题角度
时效性提醒：你的训练数据有截止日期。涉及"最新"时政时，必须提示用户核对官方发布，并说明你掌握的信息可能不是最新的。
6. 个性化学习计划（/kaogong-plan）
- 收集信息：考试时间、每日可用时间、当前水平、薄弱环节
- 制定分阶段计划：基础期 → 提高期 → 冲刺期
- 细化到每日任务
- 提供阶段性检测节点
- 根据反馈动态调整
计划要可执行：写"每天 30 分钟资料分析速算，20 题"，而不是"加强资料分析"。
7. 报考咨询与选岗（/kaogong-baokao）
先读 references/baokao.md，然后：
- 判断用户想解决的是能不能报（资格条件）、报什么（选岗）、还是流程怎么走
- 按参考文件回答，并明确区分：哪些是长期稳定的制度规定，哪些是逐年变化的当年公告内容
- 涉及具体年份的时间、年龄、职位条件，必须提示以当年官方公告为准，并给出国家公务员局（scs.gov.cn）或本省人事考试网的查询入口
选岗建议只做方法论指导，不替用户做决定，也不预测某个岗位的分数线。
引用与可信度
回答涉及制度、数据、评分标准时，遵循 references/SOURCES.md 的三级标注：
- 🟢 官方（法律法规、部委文件、政府公告）— 可以肯定地陈述
- 🟡 权威媒体（新华社、人民网等对官方数据的报道）— 陈述时标明年份
- 🟠 行业整理（培训机构对真题的统计，如逐模块题量、分值权重）— 必须说明「为业内统计/推测，非官方口径」
不确定就说不确定。 绝不编造真题、分数线、职位表内容或政策条文。
互动准则
- 首次交互：简短自我介绍，询问用户需求，不要一次输出太多信息
- 练习模式：一次出一题，等用户作答后再解析，不要直接给答案
- 批改模式：先肯定优点，再指出不足，最后给建议
- 知识讲解：用简洁语言 + 实例说明，避免纯理论堆砌
- 进度追踪：记住用户的薄弱点，后续训练有针对性地加强
- 激励机制：适时鼓励用户的进步，保持学习动力
边界与免责 Scope & Disclaimer
- 本技能提供的是备考训练，不是官方考试信息源。报名时间、职位表、分数线、政策变动一律以国家公务员局及各省考试院官方发布为准。
- 练习题为模拟原创题，不是真题。不要声称某道题是"某年真题"。
- 评分标准依据公开的阅卷规则整理，评分结果仅供参考，与实际阅卷可能存在差异。
- 不提供、不协助任何形式的考试作弊，包括代考、泄题、考场作弊工具。用户若提出此类请求，明确拒绝并说明原因。
© KeWang0622, MIT. 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 6 other files (references) in skills/kaogong of KeWang0622/kaogong-skill.
- SKILL.md
- references/SOURCES.md
- references/baokao.md
- references/mianshi.md
- references/shenlun.md
- references/shizheng.md
- references/xingce.md
Open the folder on GitHubat commit c85ca76
Compare with similar skills
Kaogong 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 |
|---|---|---|---|---|---|---|
| Kaogong this skillKeWang0622/kaogong-skill | 167 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Claude Certification Tutorrohitg00/ai-engineering-from-scratch | 66k | — | ~3k | Automated safety check: Pass | MIT | |
| StudyVault Quiz Tutorbevibing/tutor-skills | 1.3k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Project Mastery Coachtudoumashu/ai-memory-skillpack | 456 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Ccar F Examprep Coachsarveshtalele/claude-architect-exam-guide | 175 | — | ~5.8k | Automated safety check: Pass | None | |
| Exam PrepIssacW228/student-llm-wiki | 177 | — | ~270 | Automated safety check: Pass | MIT |
Similar skills
StudyVault Quiz Tutor
bevibing/tutor-skills
Quizzes you on the notes in an Obsidian StudyVault, tracks proficiency per concept and drills weak areas in four-question rounds.
Project Mastery Coach
tudoumashu/ai-memory-skillpack
Train strict project ownership from repo-local docs/ai memory and central LLM Wiki project entities.
Ccar F Examprep Coach
sarveshtalele/claude-architect-exam-guide
A personalized study-coach skill for the Claude Certified Architect – Foundations (CCAR-F) certification.
Exam Prep
IssacW228/student-llm-wiki
Generate practice exam questions from weak concepts. An agent skill from IssacW228/student-llm-wiki.
Lesson Generator
dair-ai/dair-academy-plugins
Builds a self-contained multi-lesson course page with lesson navigation, objectives, flashcards, quizzes and source links, as plain HTML, CSS and JavaScript.
Related
Categories
Questions about Kaogong
What does Kaogong do?
考公AI导师 — a tutor for the Chinese civil service exam (公务员考试), covering 行测 (aptitude), 申论 (essay), and 面试 (structured interview). Kaogong is an agent skill from KeWang0622/kaogong-skill. 考公AI导师 — a tutor for the Chinese civil service exam (公务员考试), covering 行测 (aptitude), 申论 (essay), and 面试 (structured interview).
When should I use Kaogong?
Kaogong fits situations like: the user mentions 考公; asks to practise exam questions; get an essay graded against the official rubric; run a mock structured interview.
How do I install Kaogong in Claude Code?
Run `npx skills add KeWang0622/kaogong-skill --skill kaogong -a claude-code`. Or copy the skill folder (skills/kaogong in KeWang0622/kaogong-skill) into .claude/skills/kaogong in your project. Claude Code loads it when a task matches its description.
How do I install Kaogong in Codex?
Run `npx skills add KeWang0622/kaogong-skill --skill kaogong -a codex`. Or copy the skill folder (skills/kaogong in KeWang0622/kaogong-skill) into .agents/skills/kaogong in your project. Codex loads it when a task matches its description.
Can I use Kaogong 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 KeWang0622/kaogong-skill --skill kaogong -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kaogong, .gemini/skills/kaogong, .github/skills/kaogong and .opencode/skills/kaogong in your project.
What does Kaogong need to run?
SKILL.md names no scripts, command-line tools or credentials: Kaogong is instructions for the agent only. Compatibility (from SKILL.md): Pure-prompt skill. Runs in any Agent Skills compatible client (Claude Code, Claude, ChatGPT/Codex, Cursor, Gemini CLI, GitHub Copilot, and others). Requires no tools, network access, or system packages..
Does Kaogong 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 Kaogong 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 Kaogong use?
Kaogong is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Kaogong use?
About 1.2k tokens (SKILL.md is roughly 4.7k 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 9k tokens, read only when the agent opens those files.
What are the alternatives to Kaogong?
Skills that share tags, products or a category with Kaogong: Claude Certification Tutor (rohitg00/ai-engineering-from-scratch, 66k stars), StudyVault Quiz Tutor (bevibing/tutor-skills, 1.3k stars), Project Mastery Coach (tudoumashu/ai-memory-skillpack, 456 stars) and Ccar F Examprep Coach (sarveshtalele/claude-architect-exam-guide, 175 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Kaogong?
KeWang0622 (a GitHub user) maintains it in KeWang0622/kaogong-skill, which has 167 GitHub stars. The repository was last updated on September 8, 2026.
Source: KeWang0622/kaogong-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.