Agent Skills: Q-Educator

Develop course content for university teaching via interview-driven workflow. Use for course planning, lecture prep, assignment design, or student communication.

UncategorizedID: tyrealq/q-skills/q-educator

Install this agent skill to your local

pnpm dlx add-skill https://github.com/TyrealQ/q-skills/tree/HEAD/skills/q-educator

Skill Files

Browse the full folder contents for q-educator.

Download Skill

Loading file tree…

skills/q-educator/SKILL.md

Skill Metadata

Name
q-educator
Description
Develop course content for university teaching via interview-driven workflow. Use for course planning, lecture prep, assignment design, or student communication.

Q-Educator

Produce course materials for graduate-level, projects-first courses through an interview-driven process that prioritizes student judgment, transparent reasoning, and domain-specific analogies.

References

  • references/teaching_philosophy.md — six governing principles
  • references/interview_protocol.md — six-question interview sequence
  • references/lecture_template.md — lecture outline structure and design rules
  • references/demo_template.md — demo outline structure and design rules
  • references/email_guidelines.md — follow-up email style rules
  • references/assignment_template.md — scaffolded assignment prompt structure
  • references/feedback_template.md — per-group feedback structure and design rules
  • references/key_phrases.md — philosophy catchphrases for natural use in content
  • references/lecture_example.md — example lecture outline with domain-specific analogies
  • references/demo_example.md — example demo outline with pipeline walkthrough
  • references/email_example.md — example follow-up email in conversational style
  • references/assignment_example.md — example assignment prompt with full scaffold
  • references/feedback_example.md — example per-group feedback document

Core Principles

  • Projects-first: students learn by executing analytical workflows, not absorbing lectures
  • Judgment over polish: develop scholarly judgment, not polished AI output
  • Instructor as arbiter: exemplars and diagnostic feedback, not content transmission
  • Repeat-exposure transfer: same analytic logic across projects in different domains
  • Transparent reasoning: justify choices, acknowledge tradeoffs, document decisions
  • Domain-specific analogies: always from the course's subject area, never generic tech

Workflow

Step 1 (Interview): Conduct six-question interview per references/interview_protocol.md. Only begin content generation after the interview is complete.

Step 2 (Content Pipeline): Produce deliverables in this order, pausing for instructor review after each:

| Deliverable | Template | Example | |-------------|----------|---------| | Lecture Outline | references/lecture_template.md | references/lecture_example.md | | Demo Outline | references/demo_template.md | references/demo_example.md | | Follow-Up Email | references/email_guidelines.md | references/email_example.md |

Step 3 (Assessment, as needed):

| Deliverable | Template | Example | |-------------|----------|---------| | Assignment Prompt | references/assignment_template.md | references/assignment_example.md | | Per-Group Feedback | references/feedback_template.md | references/feedback_example.md |

Scope

Include: Lecture outlines, demo outlines, follow-up emails, assignment prompts, per-group feedback for graduate-level projects-first courses.

Checklist

  • [ ] Interview completed before drafting (references/interview_protocol.md)
  • [ ] Teaching philosophy principles reflected in content (references/teaching_philosophy.md)
  • [ ] Domain-specific analogies used throughout (never generic tech metaphors)
  • [ ] Each deliverable reviewed by instructor before proceeding to next
  • [ ] Key phrases appear naturally where appropriate (references/key_phrases.md)
  • [ ] Deliverable follows its template structure and design rules
Q-Educator Skill | Agent Skills