# Rubric Generator

> >

- **Type:** Skill
- **Install:** `agentstack add skill-jjuice22-classroom-ready-ai-skills-rubric-generator`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [JJuice22](https://agentstack.voostack.com/s/jjuice22)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [JJuice22](https://github.com/JJuice22)
- **Source:** https://github.com/JJuice22/classroom-ready-ai-skills/tree/main/skills/rubric-generator

## Install

```sh
agentstack add skill-jjuice22-classroom-ready-ai-skills-rubric-generator
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Rubric Generator

## Purpose

Build rubrics that do two things simultaneously: give teachers a fair,
consistent scoring guide and give students a transparent roadmap for
producing quality work. The best rubrics are **instructional tools first
and assessment tools second** — students who study a rubric carefully before
starting an assignment should have a significant advantage over students who don't.

**Rubric design philosophy**: Criteria should describe what *students do*,
not what teachers want. Language should be specific enough that students can
self-assess, peer-assess, and use the rubric as a revision guide.

---

## What You Need From the User

Gather before generating. Ask for anything missing:

- **Assignment description** (required): What are students producing?
- **Grade level** and subject
- **Standards alignment**: Are there specific Common Core, NGSS, state, or
  local standards this should address?
- **Rubric format preference**:
  - **Analytic** (separate criteria scored independently — most diagnostic)
  - **Holistic** (one overall score with a descriptor — fastest to use)
  - **Single-point** (describes proficiency only; teacher notes above/below)
- **Point scale**: 4-point (1–4), percentage-based (100%), or a specific
  scale the user specifies
- **Audience**: Teacher-only scoring guide or student-facing rubric?
  (If student-facing, language must be directly accessible)

**Default**: Analytic rubric, 4-point scale, student-facing language,
no specific format requested.

---

## Rubric Types

### Analytic Rubric (Default)

Multiple criteria, each scored independently. Most useful for:
- Complex, multi-component assignments
- When diagnostic feedback matters (e.g., "strong argument but weak evidence")
- Assignments where students need to understand which component to revise

Format:

| Criteria | 4 — Exceeds | 3 — Meets | 2 — Approaching | 1 — Beginning |
|---|---|---|---|---|
| [Criterion 1] | [descriptor] | [descriptor] | [descriptor] | [descriptor] |
| [Criterion 2] | [descriptor] | [descriptor] | [descriptor] | [descriptor] |

### Holistic Rubric

One score based on overall quality. Most useful for:
- Quick, formative assessment
- First drafts or early performance tasks
- Situations where the whole is more important than the parts

Format:

| Score | Descriptor |
|---|---|
| 4 | [What an exceptional response looks like — multiple specific features] |
| 3 | [What a proficient response looks like] |
| 2 | [What a developing response looks like] |
| 1 | [What a beginning response looks like] |

### Single-Point Rubric

Describes only the proficient level. Most useful for:
- Student-centered assessment cultures where growth mindset matters
- When you want to avoid students "aiming for the 3"
- Quick, focused feedback

Format:

| Area for Growth | Proficient — Criteria | Strength/Evidence |
|---|---|---|
| [Notes below standard] | [Criterion 1 — proficient descriptor] | [Notes above standard] |
| [Notes below standard] | [Criterion 2 — proficient descriptor] | [Notes above standard] |

(Teacher writes in the left and right columns during scoring.)

---

## Criteria Selection Protocol

For every assignment, identify 3–6 criteria. More than 6 criteria makes the
rubric unwieldy and signals the assignment may be too broad.

**Criteria selection by assignment type:**

### Argumentative / Analytical Essay

| Criterion | What It Measures |
|---|---|
| Thesis / Claim | Clarity, specificity, arguability of central argument |
| Evidence | Quality, relevance, and quantity of textual/research support |
| Analysis / Commentary | Depth of connection between evidence and claim |
| Organization | Logical structure, transitions, paragraph coherence |
| Conventions | Grammar, spelling, punctuation, citation format |
| Voice / Style (optional) | Sophistication, precision, and appropriateness of word choice |

### Research Project / Presentation

| Criterion | What It Measures |
|---|---|
| Content Knowledge | Accuracy, depth, and relevance of information presented |
| Source Quality | Credibility, variety, and appropriate use of sources |
| Organization | Logical sequence, clear introduction and conclusion |
| Delivery / Presentation | Eye contact, pacing, volume, engagement with audience |
| Visual Aids | Clarity, accuracy, and support for spoken content |
| Time Management | Meets time requirements; neither rushed nor overlong |

### Lab Report / Science Investigation

| Criterion | What It Measures |
|---|---|
| Hypothesis | Testable, specific, connected to background knowledge |
| Procedure | Replicable, controlled, safe |
| Data Collection | Accurate, organized, labeled, units included |
| Analysis | Correct interpretation of data; patterns identified |
| Conclusion | Connected to hypothesis; explains results; considers error |
| Scientific Writing | Objective voice, precise vocabulary, correct conventions |

### Creative / Narrative Writing

| Criterion | What It Measures |
|---|---|
| Narrative Focus | Clear, sustained central idea or story |
| Development | Characters, setting, conflict developed with detail |
| Structure | Beginning, middle, end with intentional pacing |
| Craft and Style | Purposeful word choice, sentence variety, voice |
| Conventions | Grammar, spelling, punctuation serve the writing |

### Discussion / Seminar Participation

| Criterion | What It Measures |
|---|---|
| Content Knowledge | Uses textual evidence; demonstrates preparation |
| Quality of Contribution | Advances discussion; introduces new ideas |
| Active Listening | Responds to peers; builds on others' ideas |
| Respectful Discourse | Professional, inclusive communication |
| Frequency | Contributes meaningfully [X] or more times |

---

## Descriptor Language Standards

**What makes rubric descriptors work:**

✅ **Specific and observable**: "Includes at least 3 pieces of textual evidence,
each with a direct quote and a page number" not "uses good evidence"

✅ **Distinguishable across levels**: A student should be able to clearly see
which level describes their work and understand why

✅ **Student-authored-feeling**: Descriptors read as "what you did" not
"what the teacher expects"

✅ **Growth-oriented at lower levels**: Level 1 and 2 descriptors name what
*is* present, not just what is missing:
- ❌ "Lacks a clear thesis"
- ✅ "Thesis is present but states a topic rather than a specific, arguable claim"

✅ **Parallel structure across levels**: If Level 4 says "3 or more pieces of
evidence," Level 3 says "2 pieces of evidence," not something structurally different

---

## Point Values and Grade Conversion

After generating the rubric, offer a grade conversion table if the user wants one:

**4-point scale (4 criteria):**
```
Total possible: 16 points

16    = 100% A+
14–15 = 90–99% A
12–13 = 80–89% B
10–11 = 70–79% C
8–9   = 60–69% D
Below 8 = Below 60% F
```

Adjust the table based on the number of criteria and the user's grading scale.

**Weighting**: If the user wants certain criteria weighted more heavily
(e.g., thesis worth 2x, conventions worth 0.5x), build a weighted version
with clear multipliers.

---

## Student-Facing Additions

When the rubric is student-facing, add:

### Pre-Assignment Self-Check
```
BEFORE YOU SUBMIT — CHECK YOUR WORK:
□ [Criterion 1]: Does my work do [specific description of proficient level]?
□ [Criterion 2]: Does my work do [specific description of proficient level]?
□ [Criterion 3]: Does my work do [specific description of proficient level]?
□ [Criterion 4]: Does my work do [specific description of proficient level]?
```

### Peer Review Prompt
2–3 sentence prompts for structured peer feedback using the rubric:
> "Using the rubric, give your partner feedback on their [criterion]. Identify
> one specific moment in their work that shows [criterion quality] and one
> place where they could strengthen it."

---

## Standards Alignment

If the user provides standards codes or asks for alignment, map each criterion
to its standard:

| Criterion | Standard | Standard Language (abbreviated) |
|---|---|---|
| Thesis / Claim | CCSS.ELA-LITERACY.W.9-10.1a | "Introduce precise claims..." |
| Evidence | CCSS.ELA-LITERACY.W.9-10.1b | "Develop claims with evidence..." |
| [etc.] | [etc.] | [etc.] |

Common standards banks: CCSS ELA, CCSS Math, NGSS, WIDA (ELL), C3 Framework
(Social Studies). Ask user to specify if standards alignment is needed.

---

## Quality Check Before Finalizing

- [ ] 3–6 criteria (not more)
- [ ] Descriptors are specific and observable at every level
- [ ] A student could self-assess with this rubric without teacher explanation
- [ ] Level descriptors are clearly distinguishable from each other
- [ ] Lower-level descriptors name what IS present, not only what is missing
- [ ] Criteria are parallel in structure
- [ ] Language is accessible for the target grade level
- [ ] Point values and grade conversion are clear
- [ ] Pre-assignment self-check is included (if student-facing)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [JJuice22](https://github.com/JJuice22)
- **Source:** [JJuice22/classroom-ready-ai-skills](https://github.com/JJuice22/classroom-ready-ai-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-jjuice22-classroom-ready-ai-skills-rubric-generator
- Seller: https://agentstack.voostack.com/s/jjuice22
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.