Hire an AI student marking and feedback reviewer

Everything it can hand back

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

• A single-point rubric with open columns for evidence
• The exact gaps between the work and the rubric
• Likely causes of the mistakes, each with a feedback or teaching fix
• A check of your comments with a better wording for the weak ones

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

• Biased wording in job ads, reviews or interview questions.
• Plans with no owner, timing or way to check progress.
• Treating a template as legal advice.

What a good result looks like

An example, not your task: Students repeat the same mistakes after you have marked their work.

• Step 1: Rubric. One criterion, what meeting it looks like, and open columns for evidence of falling short and exceeding.
• Pause to pick the work. You choose the student work to mark and paste it without names.
• Step 2: Gaps. Strengths, what is missing against the criterion and why, in priority order, with feedback to give.
• Step 3: Causes of mistakes. Errors grouped by likely cause, slips told apart from misunderstandings, and a response for each.
• Pause to write your comments. You write comments to the student using the causes and fixes above.
• Step 4: Feedback check. Each comment rated for how specific it is and whether it says what to do next, with better wording for weak ones.

How the work is checked

• The rubric has one criterion that a student can read and understand.
• Each gap names something visible in the work, not a general quality.
• Causes are separated into slips and misunderstandings, with a reason for each.
• Every rewritten comment says what the student should do next.
• 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

• Build the rubric. Writes the one criterion for the goal, describes what meeting it looks like and leaves open columns for evidence of falling short and exceeding.
• Pick the work. This part is yours. Choose one piece of student work, or a small set, and have it ready to paste without names.
• Find the gaps. Sets the work against the rubric, names what is missing and why, and suggests the feedback to give.
• Trace the causes. Groups the errors by likely cause, separates slips from misunderstandings and matches each cause to feedback or teaching.
• Write your comments. This part is yours. Write your comments to the student using the causes and fixes above.
• Check the feedback. Reads each comment for how specific it is and whether it says what to do next, flags comments that only praise or only judge, and rewrites the weak ones.

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 mark-student-work-against-a-rubric-and-sharpen-your-feedback 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/mark-student-work-against-a-rubric-and-sharpen-your-feedback/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

• A learning goal or the task students did
• A rubric you already have (optional)
• One piece of student work, or a small set, to mark
• After you write your comments, the comments themselves

Functions and deliverables

• Student marking and feedback reviewer: Share the learning goal, student work and feedback draft. Get a marking guide, evidence-linked gaps, possible causes and clearer feedback.
  • A single-point rubric with open columns for evidence
  • The exact gaps between the work and the rubric
  • Likely causes of the mistakes, each with a feedback or teaching fix
  • A check of your comments with a better wording for the weak ones
• Single-point rubric builder: Share a learning goal. Get a one-criterion rubric with open columns for evidence, ready for feedback or self-assessment.
  • One clear criterion statement
  • A three-column rubric with open evidence columns
  • A version for the stated purpose
  Source: Gareth Manning.
• Student work criteria reviewer: Share one piece of student work and its criteria. Get strengths, gaps in that sample and a next teaching step to check.
  • A list of strengths
  • Named gaps against the criteria
  • A priority order for the gaps
  • Next teaching steps
  • A feedback script to say aloud
  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.
• Written feedback checker: Paste feedback given to learners. Get a check for how specific and useful it is, with better wording.
  • A level-by-level diagnosis of each comment
  • A check on specificity, threat and next step
  • A rewritten version of the feedback
  • A short list of habits to change
  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

• Students repeat the same mistakes after you have marked their work.
• Your comments take long to write and you suspect they are too vague.
• You want a rubric students can use to check their own work.

Limits to check before starting

• You want a rubric with wording for every level of work: use the Task marking guide writer. This workflow builds a single-point rubric with one criterion.
• You are checking an AI tutor's replies, not your own comments: use the AI feedback quality checker.
• You need a mark or grade given to a whole class at once: this handles one piece of work, or a small set, at a time.

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.

• Download the handoff pack. It is a zip with HANDOFF.md and every skill file this workflow uses.
• Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
• Give it the learning goal. Read the rubric and fix the wording before you use it.
• Remove the student's name, then paste the work, so it can be marked against the rubric.
• Write your comments from the causes, then paste the comments for the last check.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/mark-student-work-against-a-rubric-and-sharpen-your-feedback 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.