What’s inside

One SKILL.md (the playbook) + one starter template. A preview:

Grading Assistant

When to use

• You have 30+ essays to grade against a rubric and the weekend is disappearing
• Every student should get real feedback, not a score and a "good job"
• You want to spot what the whole class got wrong and turn it into next week's review
• You teach the same course across sections and need grading to stay consistent
• You need lesson plans or review slides built from actual student mistakes, not your memory of them

Workflow

1. Build the grading project (input: syllabus, rubric, sample answers → output: per-course project)
   Set up one AI project per course and feed it the syllabus, your rubric, past exams, model answers, and course materials. One real case keeps a separate project per course so the grading stays anchored to that course's standards. A rubric written for a colleague, not for yourself, is the bar — the AI grades what it says, not what you meant.
2. Anonymize the submissions (input: student work → output: numbered, ID-free batch)
   Strip names before grading: student papers get anonymous numbers. This keeps the grading honest and protects student privacy. Feed readable digital files — scans need to be legible or the grading degrades silently.
3. Grade criterion by criterion (input: rubric + submissions → output: scored batch + flagged borderlines)
   The AI scores each submission against every rubric criterion separately, with a short justification per criterion. It doesn't invent the rubric as it goes — every score points at a criterion. Borderline and low-confidence grades get flagged for your review; the easy agreements flow through.
4. Write real feedback (input: graded batch → output: per-student feedback)
   Each student gets personalized comments: what they did well (citing their actual words), what cost them points (citing the criterion), and one concrete thing to fix next time. A feedback comment that could apply to any student applies to none of them — send it back.
5. Mine the mistakes for teaching (input: full batch results → output: class trends + review materials)
   Aggregate the criterion scores across the class to find the hot spots: the two rubric rows where everyone bled points. Turn those into next week's review — slides or a lesson plan built from the actual wrong answers, not from what you remember being hard. Never touch the original submission files; scores live in a separate sheet.
6. You set the final grades (input: scored batch → output: confirmed grades)
   Review the flagged borderlines, spot-check a handful, then approve. The AI proposes; you dispose. Educational responsibility doesn't delegate — final grades are always the teacher's call.

Output spec

Template preview

Grading Assistant — Rubric & Batch Template

One project per course. Anonymize first, grade second, approve last.

Course project

• Course: {name / term}
• Fed to the AI: [ ] syllabus [ ] rubric [ ] past exams [ ] model answers [ ] course materials
• Submissions format: {digital docs / legible scans}

The rubric (written for a colleague, not for yourself)

Grading scale: {e.g. A ≥ 90, B ≥ 80 …} | Late policy: {…} | Academic integrity notes: {…}

Batch tracking

Student feedback format (one per student)

Feedback — Student {anonymous #}

• What worked: {quote their actual words — "…"}

Buy the full skill pack — $4.99 Pro — all 471 skills