criterion-referenced-rubric-generator

Este extracto es una copia guardada durante la revisión. La fuente externa contiene la versión completa y actual.

---
# AGENT SKILLS STANDARD FIELDS (v2)
name: criterion-referenced-rubric-generator
description: "Generate a criterion-referenced rubric with descriptive performance levels for a task or objective. Use for marking guides and general curriculum contexts. For Manning programmes where Competent = success, use coherent-rubric-logic-builder instead."
disable-model-invocation: false
user-invocable: true
effort: medium

# EXISTING FIELDS

skill_id: "curriculum-assessment/criterion-referenced-rubric-generator"
skill_name: "Criterion-Referenced Rubric Generator"
domain: "curriculum-assessment"
version: "1.0"
evidence_strength: "strong"
evidence_sources:
  - "Brookhart (2013) — How to Create and Use Rubrics for Formative Assessment and Grading"
  - "Andrade (2000, 2013) — Using rubrics to promote thinking and learning"
  - "Jonsson & Svingby (2007) — The use of scoring rubrics: reliability, validity and educational consequences"
  - "Sadler (1989) — Formative assessment and the design of instructional systems"
  - "Panadero & Jonsson (2013) — The use of scoring rubrics for formative assessment purposes revisited"
input_schema:
  required:
    - field: "learning_objective"
      type: "string"
      description: "The learning objective the rubric assesses"
    - field: "task_description"
      type: "string"
      description: "The specific task students will complete"
    - field: "student_level"
      type: "string"
      description: "Age/year group"
  optional:
    - field: "criteria_count"
      type: "integer"
      description: "Number of criteria (default: 4)"
    - field: "performance_levels"
      type: "integer"
      description: "Number of performance levels (default: 4)"
    - field: "subject_area"
      type: "string"
      description: "The curriculum subject"
    - field: "existing_criteria"
      type: "string"
      description: "Any criteria the teacher wants included — the rubric will build around these"
output_schema:
  type: "object"
  fields:
    - field: "rubric"
      type: "object"
      description: "Complete rubric with criteria, performance level descriptors, and scoring guidance"
    - field: "design_rationale"
      type: "string"
      description: "Why these criteria were chosen and how descriptors were differentiated"
    - field: "student_friendly_version"
      type: "string"
      description: "A simplified version students can use for self and peer assessment"
    - field: "calibration_notes"
      type: "string"
      description: "Notes to help multiple markers apply the rubric consistently"
chains_well_with:
  - "competency-unpacker"
  - "backwards-design-unit-planner"
  - "gap-analysis-from-student-work"
  - "feedback-quality-analyser"
  - "kud-knowledge-type-mapper"
teacher_time: "3 minutes"
tags: ["rubric", "assessment", "criteria", "descriptive-language", "formative-assessment"]
---

# Criterion-Referenced Rubric Generator

## What This Skill Does

Produces a criterion-referenced rubric from a learning objective and task description, with descriptive (not evaluative) language at each performance level. Each criterion describes what the student's work LOOKS LIKE at each level — not how "good" it is. The output includes the full rubric, a design rationale, a student-friendly version for self/peer assessment, and calibration notes for consistency across markers. AI is specifically valuable here because effective rubric design requires precise, descriptive language that distinguishes between performance levels without using evaluative labels ("excellent," "good," "poor") or vague quantity indicators ("some," "many," "thorough") — and each descriptor must be qualitatively distinct from the adjacent levels, not just a scaled version of the same description.

## Evidence Foundation

Brookhart (2013) established that effective rubrics use descriptive rather than evaluative language — they describe what is PRESENT in the work, not how good it is. "Uses specific textual evidence to support each analyti