Draft a grading rubric with point ranges that leave no gaps
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 prompt.
Use cases
Methods
Paste into a general LLM and draft a grading rubric with point ranges that leave no gaps.
LLMPrompt
Prompt
Copied 0
Persona: You are an experienced college [discipline, e.g., Biology / History / Nursing] instructor who designs clear, fair rubrics. Task: Draft a grading rubric for the attached [assignment type, e.g., lab report / research essay / case study]. If no assignment is attached, stop and tell me. Audience: Students will use the rubric to check their work before submitting, and I'll use it to grade. Write every level description in plain language a [student level, e.g., first-year / second-year] student can act on: describe what they can see in their own work, not vague qualities like "strong" or "adequate." Context: This is [course number and title] at [type of institution, e.g., a community college / a four-year university]. Use only the attached assignment, and base every criterion on what it actually asks students to do. If something in the assignment is unclear, ask me rather than guessing. Steps: 1. In one sentence, tell me what the assignment requires so I know you've read it. 2. Ask me up to [number, e.g., 3] questions about what I value most and where my students usually struggle. Ask one at a time and wait for my answer before asking the next. 3. Draft the rubric, using my answers to set the weighting. Format: - A table with [number, e.g., 4–5] criteria as rows and 3 levels as columns: Exceeds, Meets, Not Yet. - Point weights for each criterion, totaling [total points, e.g., 100]. - In every cell, show the point range for that level next to the description (e.g., "Meets: 14–17 pts"). - Point ranges for each criterion must cover every score from 0 to that criterion's maximum, with no gaps or overlaps. - Below the table, show the total point range for each level across the whole rubric, so students can see what an overall "Exceeds," "Meets," or "Not Yet" score looks like. - Each "Not Yet" cell should name one specific thing the student can do to improve. Boundaries: Don't add requirements that aren't in the assignment.
No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/draft-a-gap-free-grading-rubric - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "draft-a-gap-free-grading-rubric",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}