Hire an AI quiz results and reteaching tracker

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• The most-missed questions with the share of the class who missed each
• Each reteached topic from last time marked moved up, flat or worse
• The likely cause behind each error, and the reteach that fits it
• A small-group list by student number, and recall starters for one and three weeks later

How it does the job well

• Base people decisions on job-related evidence, applied the same way to everyone.
• Write in plain, respectful language the person affected could read.
• Keep personal data to what the task needs, and handle it privately.
• Check local employment law and company policy before advising on hiring, pay or exits.

Mistakes it avoids

• Reteaching to the whole class what a few students missed.
• Taking one quiz as proof of a trend. Wait for the second before you call a topic stuck.
• Putting student names in any file.
• Sending the same fix a third time when two have not worked.
• Biased wording in job ads, reviews or interview questions.
• Plans with no owner, timing or way to check progress.

What a good result looks like

An example, not your task: You mark a quiz and want to know what to reteach, not only who struggled.

• The quiz in one line. Class size, the average, and the most-missed questions with the share of the class who missed each.
• Against last time. Each topic you reteached before, marked moved up, flat or worse, with the old and new shares.
• Why they missed it. The likely cause for each topic, marked as seen in the answers or as a guess.
• What to reteach. Each topic with the reteach chosen, the reason for the choice and the time it needs.
• Small group. Student numbers who need hints rather than a whole-class lesson, with the topic.
• Stuck topics. Any topic reteached twice with no gain, and the missing step underneath it.

How the work is checked

• Every share is worked out from the table, and the class size is stated.
• Each reteach matches the size and the cause of the problem, and says why.
• No topic got a third reteach of the same kind.
• Students appear by number only.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Read the results. Works out the share of the class who missed each question and ranks them. It says when the class is too small for the shares to be steady.
• Compare with last time. Sets each topic you reteached against its last result and marks it moved up, flat or worse.
• Find the cause. Looks at the wrong answers for the most-missed questions and names the likely cause of each error.
• Choose the reteach. More than half missed a new idea gets a short lesson. A procedure gets worked examples. Mixed-up ideas get a contrast task. A common mistake gets examples with that mistake in. A few students get hints in a small group.
• Stop a failing fix. If a topic was reteached twice with no gain, it looks for a missing step underneath, not a third try.
• Plan the recall and save. Writes short starters for one and three weeks later and saves the numbers for the next quiz.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id class-quiz-reteach-keeper only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/class-quiz-reteach-keeper/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Quiz results, one row per student, with student numbers and no names
• The quiz questions and the idea each one tests, the first time
• Sample wrong answers for the most-missed questions (optional, best)
• Your year group and how long you have before the next lesson (optional)

Helpful context (optional)

• A photo or paste of a few real wrong answers for the most-missed questions
• The scheme of work for the next two weeks

Tools and access

• Claude Code: It can keep the reteach log and read the results file each time.
• Google Sheets or your quiz tool: Export results as a table with one row per student and one column per question.

Functions and deliverables

• Quiz results and reteaching tracker: Review marked quiz results, plan focused reteaching and compare later answers, changing course when the same fix has not helped twice.
  • The most-missed questions with the share of the class who missed each
  • Each reteached topic from last time marked moved up, flat or worse
  • The likely cause behind each error, and the reteach that fits it
  • A small-group list by student number, and recall starters for one and three weeks later
• Quiz and dashboard data reader: Paste your quiz results or LMS numbers and get a plain reading of what they show, plus what to do in class next. A quiz data reader for teachers.
  • Plain-language reading of the data
  • What the data cannot say
  • Teaching actions for next class
  • Follow-up checks
  Source: Gareth Manning.
• Student mistake analyser: Share a student answer and the task. Get the error, a possible cause to check and targeted practice.
  • Errors sorted into types
  • The likely cause behind each
  • Questions to confirm the cause
  • A response plan for each error type
  • A self-analysis guide for students
  Source: Gareth Manning.
• Direct teaching lesson builder: Share the skill, class level and lesson time. Get teacher modelling, guided practice, independent tasks and checks before learners move on.
  • A three-stage I do, We do, You do lesson
  • Teacher talk and thinking-aloud prompts
  • Guided practice tasks
  • Independent practice tasks
  • Quick checks for understanding
  Source: Gareth Manning.
• Worked-example practice ladder builder: Turn any multi-step procedure into worked examples that fade into independent practice. Get a worked example sequence your students can follow.
  • Fully worked examples
  • Partly completed examples
  • Independent practice tasks
  • Self-explanation prompts
  • Guidance on pacing the fade
  Source: Gareth Manning.
• Concept comparison task designer: Find the one feature your students miss when they mix up two ideas. Get a confusing concept contrast task with examples and class questions.
  • The key feature to notice
  • A task with contrasting examples
  • Worked examples
  • Questions to ask in class
  Source: Gareth Manning.
• Flawed example writer: Name a topic, student level and common mistake. Get flawed examples, prompts to find and fix errors, and a correct version.
  • Examples with one planted error each
  • Prompts asking students to find, explain and fix it
  • Teacher answer key
  • Notes on how to run the activity
  Source: Gareth Manning.
• Step-by-step hint writer: Turn problem types and common errors into hints, rules for showing them, and final answers.
  • A hint sequence from light nudge to strong help
  • Each hint tied to one sticking point
  • A plan for what happens after the last hint
  • Notes on when to show each hint
  • A version matched to your students' level
  Source: Gareth Manning.
• Retrieval quiz writer: Give a topic, year group and question count. Get recall, cue and choice questions with answers and review timing.
  • Recall questions at three difficulty levels
  • A label for each question type
  • Answer notes
  • When to use the quiz after teaching
  Source: Gareth Manning.
• Lesson understanding check planner: Give it lesson stages. Get a quick check for each and a guide for what to do with answers.
  • Checks for each lesson stage
  • A hinge question
  • A cold-call sequence
  • An exit ticket
  • A decision tree for what to do with answers
  Source: Gareth Manning.
• Skill progression map builder: Name a skill and student level. Get a suggested learning path, diagnostic tasks and next steps to review.
  • Ordered stages from prerequisite to mastery
  • Links showing what depends on what
  • Checks for each stage
  • Notes on common stuck points
  Source: Gareth Manning.
• me.md builder: Answer a few questions, or let your AI use what it remembers. Get one private file that tells any AI who you are.
  • One me.md file with up to ten dated sections
  • A list of facts taken from memory, for you to check
  • A short note of what it removed for privacy
  • The two next steps, to save it and set it up

Tasks you can use it for

• You mark a quiz and want to know what to reteach, not only who struggled.
• A topic keeps coming back wrong and you want to try something different.
• You want a short recall starter for the topics students just missed.

Limits to check before starting

• You only want a fresh set of recall questions: use the Retrieval quiz writer skill on its own, with no results table.
• You have a very small class or a quiz of fewer than five questions: read the answers yourself, as the shares will swing too much.
• You want marks changed, reports written or families contacted: do that yourself, as this agent never does it.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to read this quiz.
• Take names out of your results. Use student numbers.
• Add a few real wrong answers for the most-missed questions if you can. The causes are then seen, not guessed.
• Choose what to teach from its list. Run it again after the next quiz and it compares with this one.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/class-quiz-reteach-keeper for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.