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.
用学员真实的学习记录做一份阶段报告,让续课变成家长看完事实后的自主选择. An agent skill from qizhitang/xiaozhi-skills.
$ npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-renewal-report -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-renewal-report --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/teacher/independent/xiaozhi-teach-renewal-report .claude/skills/xiaozhi-teach-renewal-report && 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-teach-renewal-report" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/independent/xiaozhi-teach-renewal-report into .claude/skills/xiaozhi-teach-renewal-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-renewal-report", 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/teacher/independent/xiaozhi-teach-renewal-reportType 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-teach-renewal-report -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-renewal-report --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/teacher/independent/xiaozhi-teach-renewal-report .agents/skills/xiaozhi-teach-renewal-report && 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-teach-renewal-report" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/independent/xiaozhi-teach-renewal-report into .agents/skills/xiaozhi-teach-renewal-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-renewal-report", 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-teach-renewal-report -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-renewal-report --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/teacher/independent/xiaozhi-teach-renewal-report .cursor/skills/xiaozhi-teach-renewal-report && 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-teach-renewal-report" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/independent/xiaozhi-teach-renewal-report into .cursor/skills/xiaozhi-teach-renewal-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-renewal-report", 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 teacher/independent/xiaozhi-teach-renewal-report--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-teach-renewal-report -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install qizhitang/xiaozhi-skills xiaozhi-teach-renewal-report --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/teacher/independent/xiaozhi-teach-renewal-report .gemini/skills/xiaozhi-teach-renewal-report && 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-teach-renewal-report" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/independent/xiaozhi-teach-renewal-report into .gemini/skills/xiaozhi-teach-renewal-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-renewal-report", 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-teach-renewal-reportInstalls 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-teach-renewal-report -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/teacher/independent/xiaozhi-teach-renewal-report .github/skills/xiaozhi-teach-renewal-report && 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-teach-renewal-report" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/independent/xiaozhi-teach-renewal-report into .github/skills/xiaozhi-teach-renewal-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-renewal-report", 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-teach-renewal-report -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-teach-renewal-report --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/teacher/independent/xiaozhi-teach-renewal-report .opencode/skills/xiaozhi-teach-renewal-report && 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-teach-renewal-report" agent skill from https://github.com/qizhitang/xiaozhi-skills/tree/main/teacher/independent/xiaozhi-teach-renewal-report into .opencode/skills/xiaozhi-teach-renewal-report/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "xiaozhi-teach-renewal-report", 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-teach-renewal-report用学员真实的学习记录做一份阶段报告,让续课变成家长看完事实后的自主选择. An agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Teach Renewal Report is an agent skill from qizhitang/xiaozhi-skills. 用学员真实的学习记录做一份阶段报告,让续课变成家长看完事实后的自主选择。 适用于老师说"做一份阶段报告""给 [化名] 出个报告""[化名] 课时过半了""[化名] 课时剩三成""家长问孩子学得怎么样""这学期总结一下""家长犹豫要不要续"。 流程:汇总课后记录与作业错因 → 写事实/进步/计划三段 → 无逐知识点分数时只出定性判断 → 给续课建议与话术。 出报告前须先指定学员化名;它会读这名学员跨月的学习记录,家长可见的内容一律先过授权检查。 本 SKILL 不记课后内容、不登记课上练习与学校作业、不排课、不发消息,也不改学员状态、不删学员档案(只删本 SKILL 自己写的阶段证据)—— 素材来自 lesson-log 与 homework-tracker,消息由老师自己发(措辞可交 parent-communication),档案变更转 student-intake。
Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `references/renewal-communication-scripts.md`, `references/stage-report-templates.md` and `shared/ai-item-check.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 Teach Renewal Report loads about 4.1k tokens when it runs, and up to ~7.4k if it reads all its reference files. Until then it costs about 105 tokens; SKILL.md has 349 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). 349 words, ~4,122 tokens.
.claude/skills/xiaozhi-teach-renewal-report/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.一句话定位: 续费不是说服家长掏钱,而是让家长看到孩子真实成长后的自然选择。
技术边界:本 SKILL 依赖能力 [M, X, K],无该能力时按 shared/platform-conventions.md 降级。
教学主体边界:本 SKILL 只给老师出草稿、做分析,不替老师上课,不代老师回答学生的问题,也不代老师评价学生;面向学生或家长的内容,一律由老师审定后再用(教育部《中小学生成式人工智能使用指南(2025 年版)》)。
适用范围:用于校外培训(一对一、小班)时,只在合法范围内用,口径见
shared/off-campus-training.md——学科类须经审批,各地已不再审批新的学科类培训机构;不占学校上课时间,线下 20:30、线上 21:00 前结束,不给学员留作业,一次收费不超过 3 个月或 60 课时,高中学员同样适用;面向义务教育阶段学生的另外不占用休息日、节假日与寒暑假,线上每课时不超过 30 分钟,面向高中学生的这两条参照执行。本技能不预设违规的排课、作业与收费。
报告里的每个数字都要能指回工作空间里的一条记录。没有记录就不写这一项,宁可报告短一点,也不用"大概""估计"填空。无 X(跨会话统计)时不给"共上了 N 次课、掌握了 N 个知识点"这类汇总,改为列出已知的几条并说明这不是完整历史。
不承诺提分、排名、升学。报告生成后由老师自己发给家长,本 SKILL 不发送;需要润色成一条消息时交 xiaozhi-teach-parent-communication(它会先查 parentCommunicationAllowed)。
本 SKILL 会读取敏感的学习记录。 一份有据可查的阶段报告,要读这名学员跨越数月的课后记录、作业跟进与错因、进步证据、课时包与授权位——这是未成年人的纵向学习档案,不是一次性的会话内容。因此:
家长可见的内容,生成前一律先过授权检查(详见 §10.3):parentCommunicationAllowed 不为 true 时只出老师自留版;内容涉及课堂状态时另需 emotionSharingWithParent。发送始终是手动的:本 SKILL 不发送、不推送、不排定发送时间,也不替老师决定什么时候谈续课。
学员状态变更与删除请求不由本 SKILL 执行。 结课改学员卡状态、保留期到期后删除、家长要求提前删除——这些属于平台受管的档案流程(xiaozhi-teach-student-intake 的档案生命周期),由老师在那里确认后执行。本 SKILL 遇到这类要求时如实转达给老师,自己只写 progressEvidence[] 这一处。
独立教师续费沟通常见的三个误区:
误区① 临到续费才准备:课时包快耗尽了才想起
"学员要续费了",临时拼凑一份报告。
误区② 报告 = 流水账:把几十次课简单罗列,
家长看完不知道孩子学了什么、进步在哪。
误区③ 续费 = 销售动作:把续费沟通做成"推销",
家长感觉被销售而非被服务。本 SKILL 要解决的是:
| 触发场景 | 示例语句 |
|---|---|
| 阶段报告 | "做一份阶段报告" / "给 [化名] 出个报告" |
| 学期总结 | "[化名] 这学期总结一下" |
| 续课沟通 | "续费怎么跟家长说" / "续课报告" |
| 课时包 50% | "[化名] 课时过半,做个中期报告" |
| 课时包 70% | "[化名] 课时剩 30%,准备续费" |
| 家长主动问 | "家长问孩子学得怎么样" |
| 学员里程碑 | "[化名] 学完 X 章节" |
| 续费困难 | "家长犹豫续不续费" |
触发的最低条件:以上语句都要能定位到一位具体学员(化名),并且是明确要出报告或谈续课的意图,才进入流程。像"这学期总结一下""家长问孩子学得怎么样"这类话单独出现时,先回一句「给哪位学员出?要出中期报告(已用 50%)还是续课报告(已用 70%)?」——确认之前不读取任何学员记录。老师只是闲聊学员近况时,口头回答即可,不走报告流程、不写 progressEvidence[]。
┌──────────────────────────┐
│ ① 读工作空间 │
│ lessonLogs/homework/ │
│ progressEvidence/课时包 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ② 三段式:事实/进步/计划 │
│ 每条带出处 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ③ 掌握与错因对比 │
│ 有分数→带数值 │
│ 无分数→只出定性 + 依据 │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ④ 续课建议 │
│ 节点:已用 50% / 70% │
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑤ 查授权 → 起草话术 │
│ parentCommunicationAllowed│
└────────────┬─────────────┘
↓
┌──────────────────────────┐
│ ⑥ 老师自己发出 │
│ 本 SKILL 不代发 │
└──────────────────────────┘┌──────────┬──────────────┬──────────────┐
│ 节点 │ 触发条件 │ 形式 │
├──────────┼──────────────┼──────────────┤
│ 中期报告 │ 课时包已用 50% │ 阶段学习简报 │
│ 续课报告 │ 课时包已用 70% │ 阶段事实+续课 │
│ 期末报告 │ 学期末/年度 │ 学期总结 │
│ 里程碑报告│ 学完一个大单元 │ 进展展示 │
│ 应答报告 │ 家长主动询问 │ 即时简报 │
└──────────┴──────────────┴──────────────┘续课节点只有 50% 和 70% 两个,全库统一,xiaozhi-teach-student-intake、xiaozhi-teach-schedule-manager、xiaozhi-teach-parent-communication 都引用这一套,不存在 80%、90% 或"到期前 X 天"的第三个节点。
理由很直接:节点越多越像催单。50% 时家长关心的是"钱花得值不值",给一份进展;70% 时家长要做下一步决定,给"还剩多少 + 下阶段打算做什么"。课时真的快用完时如实说一句剩余数就够了,不需要第三次提醒。
已用比例的算法:usedUnits ÷ totalUnits。pendingConfirmations 里未确认的条目不计入 usedUnits,所以比例可能偏低;有待确认条目时,在报告里注明"另有 N 条课时待确认",不要按未确认的数字提前触发节点。
目的:客观陈述发生了什么,不评价、不夸大
内容:
· 已上课时(注明有几条待确认,未计入)
· 学习内容(来源 lessonLogs[].completedContent)
· 知识点掌握档位(来源 lessonLogs[].perTopicMastery[],五档)
· 量化测评数据——仅在真做过带题号记分的测评时写;
没做过就整段留空,不用估算补目的:基于记录展示真实进展
内容:
· 与起点对比(起点来自 progressEvidence[] 里最早那条)
· 掌握度变化(lessonLogs[].perTopicMastery 按 date 前后对比)
· 错因分布变化(homeworkFollowups[].mainErrors 按 dimension 聚合)
· 具体行为的变化("上次要提示才起步,这次自己列式")
不写:
❌ "思维能力提升""抗挫能力增强"——没有可核对的记录支撑
❌ 对性格、态度、智力的评价目的:给出下阶段清晰的学习路径
内容:
· 重点突破(每条注明判据来自哪条记录)
· 课时建议(按 shared/grade-bands.md 三的时长参数)
· 下阶段想看到的具体变化——写行为,不写分数
✅ "含参方程能自己判断要不要讨论"
❌ "期中提 15 分"
· 续课建议(节点:已用 50% / 70%)📎 完整模板见
references/stage-report-templates.md(中期报告 已用 50% / 续课报告 已用 70% / 期末报告三套完整填写模板,含输出前自检清单)
■ 知识点掌握情况对比
数据来源:workspace.lessonLogs[].perTopicMastery[],按 date 取
最早一次与最近一次
起点([日期]):已掌握 [N] 个 / 仍需巩固 [N] 个 / 需要重讲 [N] 个
当前([日期]):已掌握 [N] 个 / 仍需巩固 [N] 个 / 需要重讲 [N] 个
五档取值见 shared/vocab.md §6
■ 错因分布对比
数据来源:workspace.homeworkFollowups[].mainErrors[].dimension
前半程:概念模糊 [N] · 计算失误 [N] · 读题失误 [N] · 方法用错 [N]
后半程:概念模糊 [N] · 计算失误 [N] · 读题失误 [N] · 方法用错 [N]
说明:条数少于 6 条时不作趋势判断,标 🔴 样本不足
■ 攻克与在跟的弱项
数据来源:workspace.progressEvidence[] + workspace.studentCards[].primaryWeaknesses
已攻克(连续 2 次独立验证做对、间隔 ≥ 3 天):[知识点]
仍在跟进:[知识点](弱项状态见 shared/vocab.md §4)
■ 课上练习情况(学员带来的学校作业、考试错题不算)
数据来源:workspace.homeworkFollowups[].task / .status / .overdueDays(task 开头为"课上练习"的才算)
前半程:课上练习按约定做完 [N] / [N] 条
当前:课上练习按约定做完 [N] / [N] 条热力图的数据来源是 workspace.progressEvidence[] 与 workspace.homeworkFollowups[].mainErrors[],不是凭空的"得分率"。独立教师日常没有逐题记分的测评,所以分两种情况:
情况 A:有逐知识点的量化记录(老师做过带题号记分的测评)
可以画带数值的热力图:
┌────────────────────────────────────┐
│ 知识点掌握热力图 · [化名] │
├────────────────────────────────────┤
│ 一元一次方程移项 🟢 8/8 题 │
│ 去分母 🟡 5/8 题 │
│ 含参方程 🔴 2/8 题 │
└────────────────────────────────────┘
图例按题数,不换算成百分比——题量小时百分比不稳定
情况 B:没有逐知识点分数(多数情况)
只出定性热力图,不编造数字:
┌────────────────────────────────────┐
│ 知识点掌握热力图 · [化名] │
├────────────────────────────────────┤
│ 一元一次方程移项 🟢 已掌握 │
│ 依据:9-04 后未再出错,9-18 换题型做对 │
│ 去分母 🟡 仍需巩固 │
│ 依据:近三次练习错 1 次(计算失误) │
│ 含参方程 🔴 需要重讲 │
│ 依据:28 天内错 3 次(概念模糊) │
└────────────────────────────────────┘
档位取 lessonLogs[].perTopicMastery 的五档,
每一格都必须带"依据",写清是哪条记录支撑的绝不做的事:把定性判断换算成百分比("掌握度约 75%")。那个数字没有出处,家长却会当真,下次报告里它变成 70% 就成了"退步"。
按 workspace.lessonLogs[].date 与 workspace.progressEvidence[].date 排序,每一条都要有记录支撑:
■ 学习里程碑
[日期]:试听 → 正式学员
[日期]:[章节] 学完(来源:lessonLogs[].completedContent)
[日期]:[知识点] 首次独立做对(来源:progressEvidence[])
[日期]:[知识点] 攻克(连续 2 次验证做对,间隔 ≥ 3 天)
[日期]:本次报告
没有对应记录的里程碑不写。"第一次主动提问"这种如果没记在
lessonLogs[].evidence 里,就不要凭印象补进时间线。■ 基于学习节奏
当前每周 [N] 课时
→ 下阶段课时 = 每周 [N] 课时 × 周数 [N](见 8.2)
■ 基于学习目标
短期目标(1 个月):[N] 课时
中期目标(3 个月):[N] 课时
■ 基于续课节点
已用 50%:给一次进展反馈
已用 70%:说清剩余课时与下阶段计划
(只有这两个节点,见第四节)■ 怎么说
下阶段:每周 [N] 课时 × [N] 周,共 [N] 课时(课时照台账的记法,不折成标准课时)
只报数字与周数,不给档位起名,不比较哪档更划算
■ 一次续多少
一次收费的时间跨度不超过 3 个月,也不超过 60 课时,超过的分段续
(《关于加强校外培训机构预收费监管工作的通知》,
教监管函〔2021〕2 号)
续课登记 startDate 与 expiryDate,
登记交排课与课时管理(xiaozhi-teach-schedule-manager)
下阶段(这一次续的,不按累计)折成标准课时超过 60(90 分钟一节算 2 课时、短于标准时长的按 1 课时;
每节多长不清楚时问老师一句,课时数本身已超过 60 的不用问),或跨度超过 3 个月(老师给了下阶段起止日期的
按日期算,没给的按周数算,约 13 周)
→ 提示老师核对收费方式、分段续;只提示,不拦截价格与优惠不在本 SKILL 范围:不起草优惠、折扣、推荐返利与限时话术;义务教育阶段学科类收费照当地政府指导价。续课沟通不催单、不用销售话术、不制造时间压力,续不续由家长看完事实后自己定。
老师要写早鸟、打折一类文案时,说一句"价格与优惠不在本 SKILL 范围",接着按 8.2 把下阶段安排写好;不拒绝整件事,不长篇说教。
以下话术由老师本人发出,本 SKILL 只起草;起草前查 workspace.studentCards[].consent 的 parentCommunicationAllowed。
📎 完整话术见
references/renewal-communication-scripts.md(续课主话术 / 家长犹豫时 / 家长决定不续时的体面结束)
✅ 来源(全部是工作空间的真实字段):
· workspace.lessonLogs[](课后记录、perTopicMastery、date)
· workspace.homeworkFollowups[](status、overdueDays、mainErrors)
· workspace.progressEvidence[](进步证据、confidenceLevel)
· workspace.coursePackageLedger[](课时数量、起止日期、待确认条目)
· workspace.studentCards[](目标、已确认弱项、授权位)
❌ 不允许:
· 编造或夸大进展
· 引用未记录的数据("我记得他上次…")
· 用估算代替实际("大概做对了七成")
· 把定性判断换算成百分比
· 引用 confidenceLevel 为 insufficient_sample 的证据下结论
(🔴 样本不足的只能作为观察提一句,不进"进步"段)✅ 报告中可使用:
化名(小A、小米等)
可核对的数据(课时数、题数、次数、日期)
行为描述
❌ 报告中禁止:
真实姓名、联系方式
家庭信息、家庭经济、家庭关系
情绪推测与心理标签
没有出处的百分比
"差生""基础太差""不用功"这类长期标签"家长可见"包括:家长版报告、要发给家长的续课话术、老师准备口头转述给家长的段落。三者一视同仁,生成前都要过这三道:
① 查 workspace.studentCards[].consent 的 parentCommunicationAllowed
false 或缺失 → 报告只给老师自己看,不生成任何家长可见内容
② 报告含课堂状态内容时,再查 emotionSharingWithParent
false → 删掉状态部分,只留学习事实
③ 出现危机信号 → 不走本流程,按 shared/crisis-exception.md 处置发送始终手动:授权检查通过也只是"可以生成",不等于"可以发出"。生成的家长版交给老师,由老师自己发;本 SKILL 不发送、不推送,也不代老师安排发送时间。
老师或家长在报告流程里提出"这个学员结课了""把档案删掉"时,本 SKILL 不执行,只如实转达:
学员卡状态变更(结课/暂停)、保留期到期删除、家长要求提前删除
→ 交 xiaozhi-teach-student-intake 的档案生命周期流程,
老师在那里逐条确认后执行
→ 本 SKILL 回一句:「这个要到学员档案那边改,我这边只出报告。
要我先把 小A 的进度整理成一份交接吗?」本 SKILL 自己去工作空间取数,不需要任何 SKILL 先跑一遍,也不向任何 SKILL 推送。
只读 ┌────────────────────┐
lessonLogs[](含 perTopicMastery)──→│ renewal-report │──→ 三段式报告
homeworkFollowups[].mainErrors ──→ │ (本 SKILL) │ (生成的段落)
progressEvidence[] ──→ │ │──→ 续课建议
coursePackageLedger[] ──→ └─────────┬──────────┘
studentCards[].consent ──→ │ 只写这一处
progressEvidence[]
(本次报告确认的阶段证据)读(均为 solo-teacher-workspace.schema.json 真实字段):
workspace.lessonLogs[].date → 时间线排序依据
workspace.lessonLogs[].completedContent → 已完成的教学内容
workspace.lessonLogs[].masteryStatus → 整体掌握度(五档)
workspace.lessonLogs[].perTopicMastery[] → 逐知识点掌握度(热力图来源之一)
workspace.lessonLogs[].nextLessonFocus → 下阶段重点
workspace.lessonLogs[].studentReaction → 课堂状态(进报告前查
emotionSharingWithParent)
workspace.homeworkFollowups[].mainErrors[].knowledgePoint / .dimension
→ 错因分布(热力图来源之一)
workspace.homeworkFollowups[].task / .status / .overdueDays
→ 课上练习情况对比(按 task 开头的类别,只算课上练习)
workspace.progressEvidence[].description / .date / .confidenceLevel
→ 进步证据;🔴 样本不足的不进"进步"段
workspace.studentCards[].goals / .primaryWeaknesses / .alias / .gradeBand
→ 目标、已确认弱项、化名、学段
workspace.studentCards[].consent → 授权位(家长版报告的前置)
workspace.coursePackageLedger[].usedUnits / .totalUnits /
.remainingUnits / .startDate / .expiryDate / .pendingConfirmations[]
→ 节点判断;待确认条目要注明;
起止日期用来展示现有课时包的跨度;下阶段的跨度按 §8.2 另算
workspace.parentCommunicationLogs[].factSummary / .date
→ 已经跟家长说过什么,避免重复
写:
workspace.progressEvidence[](evidenceId / studentId / date /
evidenceType / description / confidenceLevel)
→ 本次报告中经老师确认的阶段证据
本 SKILL 不写:
workspace.parentCommunicationLogs[] → 由 xiaozhi-teach-parent-communication 写
workspace.coursePackageLedger[] 的任何数字 → 课时不归本 SKILL 动
workspace.studentCards[] 的任何字段 → 学员状态、授权位、保留期与删除
交 xiaozhi-teach-student-intake
的档案流程,老师确认后由它改
生成的报告段落(非存储字段):
· 事实段 ← workspace.lessonLogs[] + workspace.coursePackageLedger[]
· 进步段 ← workspace.progressEvidence[] + workspace.lessonLogs[].perTopicMastery[]
+ workspace.homeworkFollowups[].mainErrors[]
· 计划段 ← workspace.lessonLogs[].nextLessonFocus
+ workspace.homeworkFollowups[].nextAction
· 续课建议 ← workspace.coursePackageLedger[].remainingUnits / .expiryDate报告本身不落库——它是一次性生成的文本,老师复制走即可。需要留痕的只有两样:报告里确认下来的阶段证据(写 progressEvidence[]),以及老师真的把报告发给家长后由 parent-communication 记的那一条 parentCommunicationLogs[]。这样下次出报告时,读到的还是原始记录,不会出现"报告引用报告"的层层转述。
✅ 报告中可使用化名
❌ 禁止:真实姓名、联系方式、家庭信息、家长身份
✅ 报告中可用有出处的数字(课时数、题数、次数、日期)
❌ 禁止:没有出处的百分比、"绝对保证"类承诺
✅ 报告可展示可观察的行为变化
❌ 禁止:长期标签("差生""基础太差""不用功")、情绪推测| ✅ 应该做 | ❌ 不能做 |
|---|---|
| 每个数字都指回一条记录 | 编造、估算、夸大 |
| 事实 + 进步 + 计划三段式 | 流水账式罗列 |
| 没有逐知识点分数时只出定性 | 把定性判断编成百分比 |
| 热力图每格带依据 | 只给颜色不给出处 |
| 续课只在已用 50% / 70% 谈 | 每隔几节课就提一次 |
| 剩余课时注明待确认条目 | 拿虚高数字触发节点 |
| 家长版报告前查两个授权位 | 默认可以给家长看 |
| 先点名学员再读记录 | 没指定学员就翻工作空间 |
| 老师自己发送 | 代老师把报告发出去 |
| 状态变更与删除转档案流程 | 顺手改学员状态或删档案 |
| 下阶段只报每周课时数与周数 | 给课时档位起名,起草优惠、折扣与限时话术 |
| 体面处理不续的情形 | 强行挽留、诋毁其他老师 |
阶段报告与续课助手(自成闭环,不需要前置 SKILL)
读 workspace.lessonLogs[] ← lesson-log 写
读 workspace.homeworkFollowups[] ← homework-tracker 写
读 workspace.coursePackageLedger[] ← lesson-log / schedule-manager 写
读 workspace.studentCards[] ← student-intake 写
读 workspace.parentCommunicationLogs[] ← parent-communication 写
写 workspace.progressEvidence[] ← 与 homework-tracker 共用(唯一写入处)
学员状态变更、保留期与删除请求:交 xiaozhi-teach-student-intake
的档案生命周期流程,老师逐条确认后由它执行,本 SKILL 不代劳。
报告要发给家长时,措辞交 xiaozhi-teach-parent-communication 润色
(它写 parentCommunicationLogs 并记 channel),发送由老师本人完成。
若装有教师通用包,学情分析类 SKILL 的结论可作为补充素材;未安装时不影响出报告。禁止行为:
xiaozhi-teach-student-intake 的档案流程)shared/off-campus-training.md 第六节)parentCommunicationAllowed 为 false 时生成家长版报告progressEvidence[] 条目。
· 学员卡本身、授权位、保留期、以及“删除这名学员的全部档案”一律不由本 SKILL 执行,
转 xiaozhi-teach-student-intake 的档案生命周期流程,由老师在那里确认。学员/家长提出时同样适用(由老师核实请求人身份后代为执行),按学员化名定位:「查看 小A 的阶段证据」「删除 小A 的阶段证据」。
若对方要的是“删除小A 的全部档案”,本 SKILL 只如实转达给老师,由 xiaozhi-teach-student-intake 执行——本 SKILL 删不了,也不该删。
校验要求:生成家长版报告前须确认 parentCommunicationAllowed 为 true,含课堂状态内容再确认 emotionSharingWithParent;跨 SKILL 共享另需 crossSkillSharing 为 true。真实姓名、出生年月、联系方式一律不写入(详见 SECURITY_BASELINE.md)。
references/stage-report-templates.md — 阶段报告模板(中期 50% / 续课 70% / 期末三套完整填写模板)references/renewal-communication-scripts.md — 续课沟通话术库(主话术 / 家长犹豫 / 不续时的体面结束)shared/vocab.md — 掌握度五档、弱项五档、置信度、授权位(唯一来源)💡 小智说: "续费不是说服家长掏钱, 是让家长看到孩子真实成长后的自然选择。 当你的报告里满是真实的数据、具体的进步、清晰的计划, 家长不会被'说服'——他们会自己做决定。"
© 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 11 other files (references) in teacher/independent/xiaozhi-teach-renewal-report of qizhitang/xiaozhi-skills.
Open the folder on GitHubat commit c65f2d4
Xiaozhi Teach Renewal Report 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 Teach Renewal Report this skillqizhitang/xiaozhi-skills | 105 | — | ~4.1k | 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
用学员真实的学习记录做一份阶段报告,让续课变成家长看完事实后的自主选择. An agent skill from qizhitang/xiaozhi-skills. Xiaozhi Teach Renewal Report is an agent skill from qizhitang/xiaozhi-skills.
Xiaozhi Teach Renewal Report fits situations like: education work in your project.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-renewal-report -a claude-code`. Or copy the skill folder (teacher/independent/xiaozhi-teach-renewal-report in qizhitang/xiaozhi-skills) into .claude/skills/xiaozhi-teach-renewal-report in your project. Claude Code loads it when a task matches its description.
Run `npx skills add qizhitang/xiaozhi-skills --skill xiaozhi-teach-renewal-report -a codex`. Or copy the skill folder (teacher/independent/xiaozhi-teach-renewal-report in qizhitang/xiaozhi-skills) into .agents/skills/xiaozhi-teach-renewal-report 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-teach-renewal-report -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-teach-renewal-report, .gemini/skills/xiaozhi-teach-renewal-report, .github/skills/xiaozhi-teach-renewal-report and .opencode/skills/xiaozhi-teach-renewal-report in your project.
SKILL.md names no scripts, command-line tools or credentials: Xiaozhi Teach Renewal Report is instructions for the agent only. 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 Teach Renewal Report is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.1k tokens (SKILL.md is roughly 16k 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 3.3k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Xiaozhi Teach Renewal Report: 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.