error-analysis-protocol

これはレビュー時に保存された抜粋です。完全で最新の内容は外部ソースを確認してください。

---
# AGENT SKILLS STANDARD FIELDS (v2)
name: error-analysis-protocol
description: "Design an error analysis protocol to diagnose the root cause of student mistakes and misconceptions. Use when error patterns appear in student work and targeted feedback is needed."
disable-model-invocation: false
user-invocable: true
effort: medium

# EXISTING FIELDS

skill_id: "self-regulated-learning/error-analysis-protocol"
skill_name: "Error Analysis Protocol"
domain: "self-regulated-learning"
version: "1.0"
evidence_strength: "moderate"
evidence_sources:
  - "Borasi (1994) — Capitalizing on errors as 'springboards for inquiry': a teaching experiment"
  - "Black & Wiliam (1998) — Assessment and classroom learning (formative assessment and error use)"
  - "Metcalfe (2017) — Learning from errors: benefits of errors in the classroom"
  - "Siegler (2002) — Microgenetic studies of self-explanation: how children develop mathematical understanding"
  - "Tulis et al. (2016) — Learning from errors: a model of individual processes"
input_schema:
  required:
    - field: "student_work_sample"
      type: "string"
      description: "Description or transcript of the student work containing errors"
    - field: "task_description"
      type: "string"
      description: "What the student was asked to do and the learning objective"
    - field: "subject_area"
      type: "string"
      description: "Subject and year group"
  optional:
    - field: "correct_response"
      type: "string"
      description: "What a correct response would look like for comparison"
    - field: "student_profiles"
      type: "array"
      description: "From context engine: prior attainment, known learning difficulties, error history"
    - field: "rubric"
      type: "string"
      description: "From context engine: rubric or success criteria for the task"
    - field: "error_frequency"
      type: "string"
      description: "Whether this error is a one-off or a recurring pattern"
output_schema:
  type: "object"
  fields:
    - field: "error_classification"
      type: "array"
      description: "Each error classified as procedural, conceptual, or careless — with evidence for the classification"
    - field: "root_cause_analysis"
      type: "string"
      description: "Hypothesised cause of each error with diagnostic questions to confirm"
    - field: "targeted_response"
      type: "array"
      description: "Specific follow-up actions for each error type"
    - field: "student_self_analysis_guide"
      type: "string"
      description: "Scaffolded prompts for the student to analyse their own errors"
chains_well_with:
  - "feedback-quality-analyser"
  - "gap-analysis-from-student-work"
  - "metacognitive-prompt-library"
  - "worked-example-fading-designer"
teacher_time: "4 minutes"
tags: ["error-analysis", "formative-assessment", "misconceptions", "diagnosis", "feedback"]
---

# Error Analysis Protocol

## What This Skill Does

Structures the analysis of student errors to distinguish between procedural errors (wrong method applied correctly), conceptual misunderstandings (fundamental misconception driving the error), and careless mistakes (correct understanding, faulty execution) — then generates targeted follow-up actions appropriate to each error type. Critically, the skill also produces a student self-analysis scaffold so learners can develop their own error-detection skills over time. AI is specifically valuable here because most teachers respond to all errors the same way ("try again" or "here's the correct answer"), when the research shows that each error type requires a fundamentally different response — re-teaching for conceptual errors, practice for procedural errors, and metacognitive monitoring for careless mistakes.

## Evidence Foundation

Borasi (1994) demonstrated that errors, when properly analysed rather than simply corrected, become powerful learning opportunities — "springboards for inquiry" that reveal student thinking and create entry points for inst