DeepTutor CLI
HKUDS/DeepTutor
Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.
用每周一次的探索,帮学生区分"浅层喜好"和"遇到困难还想继续的真正兴趣". An agent skill from qizhitang/xiaozhi-skills.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-interest-explorer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-interest-explorer --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/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/student/general/xiaozhi-interest-explorer .claude/skills/xiaozhi-interest-explorer && 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 "xiaozhi-interest-explorer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/general/xiaozhi-interest-explorer into .claude/skills/xiaozhi-interest-explorer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-interest-explorer", 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/qizhitang/xiaozhi-skills/tree/main/student/general/xiaozhi-interest-explorerType 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 qizhitang/xiaozhi-skills --skill xiaozhi-interest-explorer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-interest-explorer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/student/general/xiaozhi-interest-explorer .agents/skills/xiaozhi-interest-explorer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "xiaozhi-interest-explorer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/general/xiaozhi-interest-explorer into .agents/skills/xiaozhi-interest-explorer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-interest-explorer", 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 qizhitang/xiaozhi-skills --skill xiaozhi-interest-explorer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-interest-explorer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/student/general/xiaozhi-interest-explorer .cursor/skills/xiaozhi-interest-explorer && 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 "xiaozhi-interest-explorer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/general/xiaozhi-interest-explorer into .cursor/skills/xiaozhi-interest-explorer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-interest-explorer", 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/qizhitang/xiaozhi-skills.git --path student/general/xiaozhi-interest-explorer--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 qizhitang/xiaozhi-skills --skill xiaozhi-interest-explorer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-interest-explorer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/student/general/xiaozhi-interest-explorer .gemini/skills/xiaozhi-interest-explorer && 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 "xiaozhi-interest-explorer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/general/xiaozhi-interest-explorer into .gemini/skills/xiaozhi-interest-explorer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-interest-explorer", 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 qizhitang/xiaozhi-skills xiaozhi-interest-explorerInstalls 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 qizhitang/xiaozhi-skills --skill xiaozhi-interest-explorer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/student/general/xiaozhi-interest-explorer .github/skills/xiaozhi-interest-explorer && 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 "xiaozhi-interest-explorer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/general/xiaozhi-interest-explorer into .github/skills/xiaozhi-interest-explorer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-interest-explorer", 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 qizhitang/xiaozhi-skills --skill xiaozhi-interest-explorer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-interest-explorer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/qizhitang/xiaozhi-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/student/general/xiaozhi-interest-explorer .opencode/skills/xiaozhi-interest-explorer && 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 "xiaozhi-interest-explorer" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/student/general/xiaozhi-interest-explorer into .opencode/skills/xiaozhi-interest-explorer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-interest-explorer", 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.
xiaozhi-interest-explorer用每周一次的探索,帮学生区分"浅层喜好"和"遇到困难还想继续的真正兴趣". An agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Interest Explorer is an agent skill from qizhitang/xiaozhi-skills. 用每周一次的探索,帮学生区分"浅层喜好"和"遇到困难还想继续的真正兴趣"。 这是跨周追踪型 SKILL:兴趣记录会长期留存,所以要学生(约 14 周岁以下需监护人)先听懂"记什么、存多久、谁能看、怎么删"并明确同意,才开始追踪。 触发语(须是明确要开始或继续探索):"帮我探索兴趣"、"开始这周的兴趣探索"、"我不知道自己喜欢什么,帮我找找"、"这个兴趣是真的吗"。 不触发:随口说"我喜欢打游戏"、聊某个领域的知识、问某个爱好怎么入门——按普通对话回答,不建记录。 记录四个维度:吸引我的内容、遇到困难时的反应、时间流逝感、外部反馈;判断依据是困难反应,不是喜好自评。 不做学科辅导(转对应学科 SKILL)、不做生涯规划或专业推荐、不做升学建议。
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including reference files (for example `references/interest-exploration-template.md`, `shared/ai-item-check.md` and `shared/crisis-exception.md`). Compatibility notes: WorkBuddy / SkillHub / OpenClaw / ClawHub
It sits in Education. The licence is MIT.
Read from SKILL.md and the folder at commit c65f2d4. 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.
WorkBuddy / SkillHub / OpenClaw / ClawHub
From compatibility in the SKILL.md frontmatter.
Xiaozhi Interest Explorer loads about 2.1k tokens when it runs, and up to ~3.4k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 179 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 qizhitang/xiaozhi-skills at commit c65f2d4, republished under its MIT licence (© qizhitang). 179 words, ~2,135 tokens.
.claude/skills/xiaozhi-interest-explorer/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.一句话定位: 不是"试很多次",而是每次都用同样的认真去了解、深入、验证一件可能重要的事。
技术边界:本 SKILL 依赖能力 [M, K],无该能力时按 shared/platform-conventions.md 降级。 特有降级:无跨会话记忆时,只做单次探索的记录与追问,不承诺"我会帮你追踪 8 周",改为把记录格式给学生自己保存。 使用前提:小学学段须有家长或老师在场陪同使用(shared/vocab.md §8 规则 4);学生说明正在考试或测验中时,不讲该题、不给提示,约好考完再复盘(shared/hint-ladder.md §〇)。
- 查看:「查看我的兴趣记录」/「查看我的档案」
- 更正:「更正我的兴趣记录」
- 删除:「删除我的兴趣记录」(删除后不可恢复,会先确认一次)
- 暂停:「这次不要记忆」(本次会话不读取、不保存任何记录,也不发起回写与交接)/「暂停提醒」
- 共享控制:「不要共享给其他SKILL」/「不要给家长看」
- 导出:「导出我的兴趣记录」(以文本形式给出,便于转存)⚠️ 危机例外(最高优先级):若对话中出现自伤/自残、轻生念头、遭受霸凌或伤害、持续严重绝望、家庭安全问题等超出学习范畴的信号,立即停止本 SKILL 的一切流程(含熔断、温情转化、数据展示、出题、家长摘要),按 shared/crisis-exception.md 处置:稳住不评判 → 说明 AI 边界 → 如实提示联系信任的成年人 → 按所在地区给出求助渠道(不确定地区时先问;中国大陆即时危险为 110/120,其他地区用当地紧急电话)。宁可误报,不可漏报;档案只记"已转介"的处置事实。
本 SKILL 的核心动作是跨周追踪——8 周或 52 周里,学生每周说的话会连成一条线。 这条线是长期留存的兴趣记录,因此必须先讲清楚、再开始。
✅ 进入:学生明确要开始或继续探索
"帮我探索兴趣" / "开始这周的兴趣探索" /
"我不知道自己喜欢什么,帮我找找" / "这个兴趣是真的吗" / "接着上周的探索"
❌ 不进入(按普通对话回答,不建记录、不读记录):
· 随口说"我喜欢打游戏""我最近迷上了做饭"
· 聊某个领域的知识("围棋怎么下""Python 难不难")
· 问某个爱好怎么入门 —— 这是知识问题,不是兴趣探索
· 学科学习话题 —— 转对应学科 SKILL
· 问专业选择、职业方向、升学 —— 本 SKILL 不做,如实说明并建议问老师或家人
⚠️ 分不清时先问一句:"你是想随便聊聊这个,还是想把它作为一次正式的兴趣探索记下来?"
没得到"记下来"之前,不建任何记录。第一次要开始追踪时,先原样说这一段,不要省略:
"开始之前先跟你说清楚,你听完再决定要不要开始:
① 记什么:只记四样——这周你看了什么、遇到困难时你想弄明白还是想放弃、
有没有忘记时间、别人给了什么反馈。不记你的成绩,不记你的情绪状态,
不记你说的和探索无关的话。
② 存多久:一直存到你说删。8 周/52 周结束后你可以选择留着或全删。
③ 谁能看:默认只有你自己。给爸妈看要你另外同意,而且只给事实、不给结论。
其他 SKILL 想用也要你同意,且只拿得到'当前在探索什么'这一条。
④ 怎么改怎么删:随时说「查看我的兴趣记录」「更正…」「删除…」「这次不要记忆」。
要开始吗?不想被记录也完全可以——我可以只陪你聊这一次,什么都不存。"| 学段 | 同意主体 | 未取得同意时怎么做 |
|---|---|---|
| 小学低段 | 本 SKILL 不适用(见 §2.1) | 建议由家人陪着自然接触 |
| 小学中段 / 小学高段 | 学生本人 + 监护人(consentGivenBy 须含监护人) | 只做单次陪聊式探索,不建记录、不排下周 |
| 初中(约 ≤14 周岁) | 学生本人 + 监护人知情 | 同上 |
| 初中(>14 周岁)/ 高中 | 学生本人 | 同上 |
对应授权位:meta.consentStatus.profileEnabled 且 interestTrackingConsent(两者都要,
且 interestTrackingConsent 单独问,不随建档一起默认打开)。授权位定义见 shared/vocab.md §8。
未同意时本 SKILL 仍然可用——只是变成"这一次的探索对话", 会话结束不留痕,也不承诺"下周我还记得"。这不是残缺版,是默认版。
"我看一下你之前几周的探索记录,好接着上次说——
只看探索了哪些领域、困难时的反应这几条。不用的话说一声。"──→ 学习DNA:只写 interestDNA 那几个字段,不写别的分支
──→ 其他 SKILL:只给"当前在探索什么"这一条,且需 crossSkillSharing=true
──→ 家长:只在 parentSharingConsent=true 且学生本人这次同意时生成(见 §六)
❌ 不把兴趣记录用于学科能力判断、不用于分班分层、不用于任何评价性结论浅层喜好(大多数"喜欢"都是这个):
· 接触时感到有趣和兴奋
· 遇到困难时想放弃
· 新鲜感消退后兴趣快速降低
· 不愿意花时间主动深入
真正兴趣(少数,但可以被发现):
· 接触时感到有趣
· 遇到困难时依然想继续(这是关键信号!)
· 能在没有外力驱动下自发去学习
· 在这个领域里,忘记时间流逝
最可靠的判断标准不是"喜不喜欢",
而是"遇到困难时的反应"。
真正兴趣遇到困难:会想"怎么解决"
浅层喜好遇到困难:会想"算了换一个"shared/grade-bands.md 第四节)| 学段 | 版本 | 说明 |
|---|---|---|
| 小学低段 | 不适用 | 直接说明,建议由家人陪着自然接触,不做记录 |
| 小学中段 / 小学高段 | 8 周试探版(见 2.3) | 只走"接触 + 困难反应"两件事,不做长线判断 |
| 初中 / 高中 | 52 周完整版(见 2.2) | 全流程 + 三阶段验证 |
52 周 = 一年 52 周,每周一次有意识的探索
不要求每周都是同一个兴趣——
可以连续几周探索同一个领域,也可以横向比较。
关键:每次都要经历"深一点点",不停留在表面接触层。8 周,每周一次,每次 20-30 分钟,只做三步:
第 1 步(5 分钟):这周想看看什么?
从上周好奇的地方接着来,或者随便挑一个没试过的
第 2 步(15-20 分钟):真的去接触一次
看一段、读一点、动手做一次、问一个懂的人
第 3 步(5 分钟):回答两个问题
· 今天有没有一个瞬间让你觉得"还挺有意思"?
· 有没有哪里觉得难?难的时候你想放弃还是想弄明白?
8 周后小智只说一句:
"这 8 次里,你在 [X] 上遇到难的时候,有 [N] 次是想弄明白的。
这不是结论,只是一条线索——要不要再看几周?"
⚠️ 8 周试探版不下"这是不是你的真兴趣"的判断,
也不生成阶段报告;小学阶段的兴趣本来就该是流动的。Step 1:选定本周探索对象(5分钟)
可以是:
· 上周延伸出的好奇心
· 一个之前没认真了解过的领域
· 在某次学习中触发的偶然兴趣
告诉小智:"本周我想探索[X]"
Step 2:初步接触 + 追问(20-30分钟)
不直接查"这是什么"——先用追问建立直觉:
"在我真正了解[X]之前,我先说说我对它的印象:[直觉描述]"
→ 小智记录直觉版本,后续做对比
接触后告诉小智:
"我今天接触了[X],具体是[接触方式],
感觉是[描述感受]"
Step 3:困难测试(关键步骤)
每周必须经历至少一个"有点难"的时刻:
· 尝试自己做一道这个领域的初级题目
· 读一篇稍微有点难懂的文章
· 尝试解释给别人听
记录:遇到困难时的第一反应是什么?
→ "想放弃" / "想继续" / "有些烦但还是想搞懂"
Step 4:记录进兴趣DNA(5分钟)
格式见模块三维度①:内容层(我被什么吸引)
记录:
· 这个领域里哪一类内容最让你停不下来?
· 哪个具体方向让你主动想了解更多?
· 哪些内容让你感到"原来如此"的满足感?
维度②:挑战反应层(遇到困难时的真实反应)
记录(每周更新):
· 这周遇到了什么困难?
· 第一反应:想放弃 / 想找资料继续 / 有点挫败但还想试
· 一周后回头看:这个困难现在还让你在意吗?
重要:这个维度的数据比你的感受更可信
连续三周都是"想放弃"→ 浅层喜好信号
连续三周都是"有挫败但想继续"→ 真正兴趣信号
【结论置信度说明】:三周对于探索来说仍较短,该结论默认置信度为 🟡 初步趋势。需警惕此时可能只处于学习曲线初期的正常困难期(The Dip),而不是真正的无感。
维度③:时间感层(时间流逝的感知)
记录:
· 专注在这个领域时,时间过得快还是慢?
· 有没有过"怎么已经过了两小时"的体验?
· 有没有主动放弃别的事情来做这个?
维度④:外部反馈层(别人给过你什么具体反馈)
记录(每月一次):
· 你在这个领域的哪个方面,别人给过你具体的正向反馈?
· 有没有人主动来问你这方面的问题?
· 和你自己一个月前比,哪里更顺了?
⚠️ 不做同龄人比较。"比同学快还是慢"既不可靠也没用——
进步只和自己的上一次比。【兴趣DNA条目】
领域名称:
探索开始日期:
已探索次数:[N]周
■ 内容层积累
最吸引我的具体方向:
停不下来的内容类型:
"原来如此"满足感来源:
■ 挑战反应记录(按时间)
第[N]周:[困难描述] → 反应:[放弃/继续/挫败但继续]
第[N]周:[同格式]
综合信号:[浅层喜好/可能是真正兴趣/确认是真正兴趣]
结论置信度:[🔴样本不足(<3周) / 🟡初步趋势(3-8周) / 🟢数据充分(>8周)](shared/vocab.md §7)
■ 时间感记录
有过时间流逝感:[次数]次
主动放弃过别的事:[次数]次
■ 外部反馈(每月更新)
收到的具体正向反馈:
和自己上个月比,哪里更顺了:
■ 阶段判断(8周后小智给出)
[见批判性验证模块]第一阶段(1-4周):初步接触期
目标:建立基础印象,不做判断
小智的角色:记录者,不引导方向
结束时的小智输出:
"你已经接触[X]四周了。
我注意到这几周你的挑战反应都是[描述]。
现在先不下结论——继续探索四周,
让数据更充分一些。"第二阶段(5-8周):深入验证期
目标:遭遇真实的困难,观察困难反应
关键任务:
· 尝试比之前更难的内容
· 用费曼测试验证:能不能向外行解释这个领域的核心概念?
· 尝试连续两周主动投入,不依靠外部驱动
结束时的小智输出:
"八周数据汇总——
挑战反应信号:[分析]
时间感数据:[分析]
外部评价:[分析]
初步判断:[浅层喜好/潜在真正兴趣]
[如果是浅层喜好]:
'这不意味着你不喜欢它,只是说明它可能不是你的核心兴趣。
要不要探索另一个领域?或者继续,看看会不会有变化?'
[如果是潜在真正兴趣]:
'数据显示这个领域对你有一些特别的东西。
接下来建议进入第三阶段——有意识地投入更多时间,
看看这个信号是否稳定。'"第三阶段(9周+):深度确认期
目标:长期稳定投入,确认是否形成自驱力
判断标准:
在没有外部要求的情况下,你是否会主动为这个领域投入时间?
小智在此阶段的角色:
不是驱动者——如果需要小智不断推着你才能探索,
这本身就是一个重要数据。
真正兴趣会自己驱动你;小智负责帮你记录和反射。第8周节点:
小智生成第一份兴趣验证报告
决策:继续深入 / 横向探索新领域 / 暂时搁置
第26周节点(半年):
回顾探索过的所有领域
比较各领域的挑战反应数据
生成"上半年兴趣图谱"
图谱包含:
· 确认浅层喜好的领域(不需要继续)
· 可能真正兴趣的领域(建议继续)
· 仍需更多数据的领域(继续探索)
第52周节点(一年):
生成年度兴趣DNA全景报告
这不是终点,而是下一个自我认知阶段的起点在学生的探索期间,家长扮演什么角色:
最有价值的事(请做):
· 提供探索的条件和资源(书籍/参观/体验机会)
· 在孩子分享探索时,问"你觉得最有意思的是什么" 而不是 "有没有用"
· 接受数据说"这不是孩子的真正兴趣"——这本身就是价值
最有害的事(请避免):
· 基于三次接触就判断"他不喜欢这个"
· 把"有没有用"作为首要评估标准
· 把自己希望孩子有的兴趣,当成孩子的兴趣
· 用物质奖励推动探索(会污染内在驱动力的测量)
关于"给家长的简报":
**不默认生成、不定期推送。**
只有在①学生本人同意 且 ②meta.consentStatus.parentSharingConsent = true
的前提下,学生说"帮我做一份给爸妈看的"时才生成。
简报只包含学生同意公开的事实(探索了哪些领域、做了什么),
不含"这不是他的真兴趣"这类结论性评判,也不含情绪判断
(情绪内容另需 emotionSharingWithParent)。
学生随时可以说"不要给家长看",说了就不生成。这是最常见的入口状态,不是问题,是起点:
小智引导方式:
"好的。我们不从'你喜欢什么'开始——
因为你现在不知道,所以这个问题没有用。
我来问你三个更容易回答的问题:
① 你在什么情况下感觉时间过得最快?
(不需要是学习场景,任何情境都可以)
② 有没有某件事,当你看到别人做得好,
心里会有'我也想试试'的感觉?
③ 有没有某个话题,你在聊天中突然变得特别话多?
这三个问题的答案,往往藏着你还没意识到的兴趣信号。"兴趣成长探索计划 SKILL
──→ 学习DNA(profile_writeback → interestDNA,需 interestTrackingConsent)
──→ 跨学科侦探周(跨科探索时发现的兴趣信号联动)
──→ IM智能提醒(reminder_enqueue:探索任务,由 IM 提醒统一发送)
──→ 每周学习复盘SKILL(兴趣维度摘要进入周报)写入落点(仅这四个字段,别的分支一概不写):
interestDNA.currentExploringFields[] / challengeReactionSignals[] / confirmedShallowLikes[] / possibleTrueInterests[]
(shared/dna-profile.schema.json)。交接格式见 shared/handover-protocol.schema.json;本 SKILL 不自行承诺提醒时间,只入队。
shared/dna-profile.schema.json 描述的是全库档案结构的上限,不是本 SKILL 的采集范围。
本 SKILL 不读也不写 subjectMap、errorPatterns、growthMap、subjectExtensions、
learningEmotion、safetyRecord —— 学科成绩与弱项、情绪推断、安全记录都不在兴趣探索的范围内。
每次写入都是待确认条目:先复述"我打算这样记:…,可以吗",学生点头才落库。
references/interest-exploration-template.md - 兴趣探索记录模板(四维度记录、困难反应信号、8 周试探版表格)shared/grade-bands.md - 各学段适用性(小学中高段用 8 周试探版)shared/vocab.md §7(置信度)/ §8(授权位)/ §10(学段)shared/crisis-exception.md - 危机例外三行片段shared/ai-item-check.md - 困难测试若临时出一道该领域的入门题,生成前按此协议自检💡 小智说:
"你不是找不到兴趣,
你只是还没有认真观察自己遇到困难时的反应。
那个反应比你说'我喜欢'三个字,
诚实一百倍。"
© qizhitang, 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 10 other files (references) in student/general/xiaozhi-interest-explorer of qizhitang/xiaozhi-skills.
Open the folder on GitHubat commit c65f2d4
Xiaozhi Interest Explorer 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 |
|---|---|---|---|---|---|---|
| Xiaozhi Interest Explorer this skillqizhitang/xiaozhi-skills | 105 | — | ~2.1k | Automated safety check: Pass | MIT | |
| DeepTutor CLIHKUDS/DeepTutor | 41k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| AI Engineering Placement Quizrohitg00/ai-engineering-from-scratch | 67k | — | ~2k | Automated safety check: Pass | MIT | |
| Deep Reading Analystginobefun/deep-reading-analyst-skill | 354 | 4 repos | ~3.6k | Automated safety check: Pass | MIT | |
| OpenMAIC Setup and ExtensionTHU-MAIC/OpenMAIC | 40k | — | ~1.7k | Automated safety check: Notes | MIT | |
| Codebase to Coursezarazhangrui/codebase-to-course | 5.7k | — | ~4.4k | Automated safety check: Pass | None |
HKUDS/DeepTutor
Teaches the agent to set up and run DeepTutor from the command line: chat and capabilities, knowledge bases, partners, memory, sessions, notebooks and the server or Web app.
rohitg00/ai-engineering-from-scratch
Runs a 10-question quiz across five areas to place a learner in the AI Engineering from Scratch curriculum, so they skip what they already know.
ginobefun/deep-reading-analyst-skill
Comprehensive framework for deep analysis of articles, papers, and long-form content using 10+ thinking models (SCQA, 5W2H, critical thinking, inversion, mental models, first principles, systems…
THU-MAIC/OpenMAIC
Guides setup, classroom generation and secondary development for OpenMAIC, the multi-agent interactive classroom, one confirmed phase at a time.
zarazhangrui/codebase-to-course
Turns a codebase into an interactive single-page HTML course for non-technical learners, with scroll modules, animated diagrams, quizzes and plain-English code translations.
rohitg00/ai-engineering-from-scratch
Tutors a learner through one stage of a hands-on AI engineering project per session: lesson, prediction, code, grader run and reflection, with hints but never full solutions.
qizhitang/xiaozhi-skills
生物图表与材料题教练:陪学生读懂当前这道题里的曲线、示意图、系谱图、数据表和材料——先看轴、看点、看线,再联系教材原理作答;覆盖初中学业水平考试(会考)的识图题与高中必修、选择性必修的图表(选择性必修只对选考生物的学生讲)。
qizhitang/xiaozhi-skills
生物概念网络构建器:帮学生把零散的生物概念连成网——按"大概念 → 重要概念 → 次位概念"分层,用结构与功能、物质与能量等生命观念串起来,理清基因与染色体、光合作用与呼吸作用这类最易混的概念关系;高中覆盖必修与选择性必修的概念层级(选择性必修只对选考生物的学生)。
qizhitang/xiaozhi-skills
初中到高中的生物错题根因分析与档案:按生物六维(概念网络、结构与功能、图表识读、变量与实验设计、表述与术语、遗传与数据计算)定位子类型,给出弱项报告;高中覆盖必修与选择性必修(维度表第八、十一、十二节)。
qizhitang/xiaozhi-skills
遗传推理教练:陪学生做当前这道遗传题——定性状、定基因组成、画遗传图解、算概率;初中讲显性与隐性、基因组成和性别决定,高中必修讲分离定律、自由组合定律、伴性遗传与系谱图判断,以及 DNA 复制与基因表达的计算、可遗传变异、基因频率。
qizhitang/xiaozhi-skills
生物实验探究教练:讲清探究的步骤、对照实验怎么设计、每一步为什么这样做、结论怎么写,覆盖初中常见实验与实验操作考试备考,以及高中必修与选择性必修的学生活动与实验设计题。
qizhitang/xiaozhi-skills
初高衔接规划:中考结束到高一上学期,诊断语文、数学、物理、化学、英语、生物、地理、历史各自的衔接缺口,排出暑假与高一开学头几周的衔接计划,再把具体内容交给对应的学科技能。
Categories
用每周一次的探索,帮学生区分"浅层喜好"和"遇到困难还想继续的真正兴趣". An agent skill from qizhitang/xiaozhi-skills. Xiaozhi Interest Explorer is an agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Interest Explorer fits situations like: education work in your project.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-interest-explorer -a claude-code`. Or copy the skill folder (student/general/xiaozhi-interest-explorer in qizhitang/xiaozhi-skills) into .claude/skills/xiaozhi-interest-explorer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-interest-explorer -a codex`. Or copy the skill folder (student/general/xiaozhi-interest-explorer in qizhitang/xiaozhi-skills) into .agents/skills/xiaozhi-interest-explorer 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 qizhitang/xiaozhi-skills --skill xiaozhi-interest-explorer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/xiaozhi-interest-explorer, .gemini/skills/xiaozhi-interest-explorer, .github/skills/xiaozhi-interest-explorer and .opencode/skills/xiaozhi-interest-explorer in your project.
SKILL.md names no scripts, command-line tools or credentials: Xiaozhi Interest Explorer is instructions for the agent only. Our summary lists: Python 3. Compatibility (from SKILL.md): WorkBuddy / SkillHub / OpenClaw / ClawHub.
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.
Xiaozhi Interest Explorer is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.1k tokens (SKILL.md is roughly 8.5k 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 1.3k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Xiaozhi Interest Explorer: DeepTutor CLI (HKUDS/DeepTutor, 41k stars), AI Engineering Placement Quiz (rohitg00/ai-engineering-from-scratch, 67k stars), Deep Reading Analyst (ginobefun/deep-reading-analyst-skill, 354 stars) and OpenMAIC Setup and Extension (THU-MAIC/OpenMAIC, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
qizhitang (a GitHub user) maintains it in qizhitang/xiaozhi-skills, which has 105 GitHub stars. The repository holds 84 skills in this directory. The repository was last updated on October 9, 2026.
Source: qizhitang/xiaozhi-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.