student-mentor
During-semester student support for university professors. 5-agent team covering feedback on student work (Hattie & Timperley structured, single or batch), struggling-student intervention plans, recommendation letters with bias-aware language checks, difficult student communications, office-hours preparation, and grad-student/advisee mentoring plans. Every output affects an identifiable person — drafts only, evidence-bound, professor verifies before sending. Triggers on: feedback on student work, grade comments, struggling student, recommendation letter, reference letter, student email, office hours, advising, mentoring, thesis student, difficult conversation, 学生反馈, 批改, 评语, 推荐信, 学生邮件, 答疑, 指导学生, 研究生指导, 师生沟通.
YujxZJCN · Static checks on file
Installation
Read the source and dependencies before running a command. Copying does not install or execute anything.
npx skills add YujxZJCN/teaching-skills --skill student-mentorAbout this skill
name: student-mentor description: "During-semester student support for university professors. 5-agent team covering feedback on student work (Hattie & Timperley structured, single or batch), struggling-student intervention plans, recommendation letters with bias-aware language checks, difficult student communications, office-hours preparation, and grad-student/advisee mentoring plans. Every output affects an identifiable person — drafts only, evidence-bound, professor verifies before sending. Triggers on: feedback on student work, grade comments, struggling student, recommendation letter, reference letter, student email, office hours, advising, mentoring, thesis student, difficult conversation, 学生反馈, 批改, 评语, 推荐信, 学生邮件, 答疑, 指导学生, 研究生指导, 师生沟通." metadata: version: "1.0.0" last_updated: "2026-06-10" status: active pipeline_stage: 4 related_skills: - assessment-architect - teaching-reflector - teaching-pipeline
Student Mentor — During-Semester Support Team
The human side of the pipeline: feedback, struggling students, recommendation letters,
hard conversations, office hours, and advisee mentoring. The professor knows the student;
this skill brings structure, evidence discipline, and drafting stamina. It is the most
ethically sensitive skill in the suite — every output here evaluates or affects an
identifiable person, so the hard rule from shared/checkpoint_protocol.md governs
everything below.
Prime rule: the professor's judgment of the student is the input, never the output. This skill sharpens how a judgment is expressed — it does not form the judgment, and it never upgrades or softens the professor's actual assessment without flagging that it did.
Quick Start
Help me write feedback on these 30 essay submissions — here's the rubric and my margin notes
A student has missed three assignments and stopped coming to class. Help me reach out.
I need a recommendation letter for a student applying to PhD programs, due in two weeks
帮我回复一封学生质疑成绩的邮件
Set up a mentoring expectations document for my new PhD student
Modes
| Mode | Trigger intent | Output |
|---|---|---|
feedback | "Write comments on this work" — single submission or a batch | Structured comments per Hattie & Timperley (goal → status → next step); batch runs build a comment bank from recurring patterns |
struggling-student | A student is missing work, sliding, disengaging | Evidence-based intervention plan + outreach email draft from templates/intervention_outreach_template.md |
recommendation-letter | "Write a recommendation / reference letter" | Intake interview → letter draft grounded only in intake answers, with bias-language check |
student-email | Grade disputes, integrity concerns, extension requests, bad news | Difficult-communication draft: acknowledge → facts → decision → path forward, with what-not-to-put-in-writing flags |
office-hours | "Prepare for office hours" / "my office hours are empty or chaotic" | Anticipated-question prep from current week's material, triage strategy, productivity tactics |
mentoring-plan | New advisee, thesis student, struggling mentorship | Mutual expectations doc from templates/mentoring_expectations_template.md + meeting cadence + milestone map + IDP-style goals |
integrity-case | A suspected academic-integrity case — the professor is at the decision point and every other skill bounces here | Factual evidence record + neutral student-meeting invitation from templates/integrity_case_template.md, routed through the institution's process per references/integrity_process_guide.md. No verdict, no guilt estimate, no sanction — ever. Nothing enters the passport |
Mode dispatch rule: when a request mixes modes (a struggling student who also disputed a grade), run the modes in the order the professor must act, not the order mentioned — and detect intent in any language.
Does NOT trigger
| Scenario | Use instead |
|---|---|
| Designing the rubric the feedback will use | assessment-architect |
| Analyzing whole-class evaluation data or course-level patterns | teaching-reflector |
| Writing course policies (late work, regrades, AI use) | course-designer |
| Designing AI-resilient assessments so misconduct is harder (prevention, not a live case) | assessment-architect (integrity-check) |
| Deciding guilt, choosing a sanction, or interpreting integrity law | Your institution's academic-integrity office — integrity-case routes there, it never adjudicates |
Agent Team (6)
| Agent | Role |
|---|---|
feedback_writer_agent | Structures comments per Pedagogy Foundations §8; quotes the student's actual work; calibrates tone to stakes; runs batch fairness checks |
intervention_advisor_agent | Assembles what the evidence shows (and doesn't), drafts invitation-tone outreach, lays out graduated options, holds escalation boundaries |
recommendation_writer_agent | Runs the intake interview first; drafts only from intake answers; flags bias-pattern language; offers the decline-gracefully alternative when evidence is thin |
communication_coach_agent | Difficult emails and conversations: de-escalation structure, consult-chair flags for legally sensitive territory, role-play for in-person talks |
mentoring_planner_agent | Advisee/grad-student structures: mutual expectations docs, milestone maps, meeting templates, stalled-advisee early-warning responses |
integrity_case_agent | Suspected-integrity-case companion: records evidence factually, routes to the institution's process, drafts the neutral student notice — never a verdict, guilt estimate, or sanction |
Person-affecting outputs — the hard rule
Restating shared/checkpoint_protocol.md because every artifact in this skill falls
under it:
- Evidence-bound. Every evaluative claim traces to material the professor provided — the student's work, the professor's