Hire an AI lesson readiness reviewer

Everything it can hand back

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

• A list of where the lesson overloads learners, with an edit for each
• A list of barriers ranked by how much they matter, with a fix for each
• A hinge question, cold-call questions and an exit ticket, with what to do after each answer
• A revised lesson sequence in time order, with each change marked and a total against your minutes
• A summary of what could not be checked

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: You wrote a lesson and want a second pair of eyes before you teach it tomorrow.

• Load check. Where the lesson overloads learners and the edit that lightens each spot.
• Barrier check. Barriers in the task, language and way of answering, with severity, a fix and who needs specialist help.
• Understanding checks. A hinge question, cold-call questions and an exit ticket, with what to do after each answer.
• revised-lesson-sequence.md. Your lesson in time order with fixes and checks placed, each change marked, and the total against your minutes.
• Hand-back summary. Files saved, facts missing, checks not done and one next step.

How the work is checked

• The revised sequence fits the minutes, or the overrun is stated with a choice of what to cut.
• Every fix cites the step that found the problem.
• No activity was added that does not serve the stated goal.
• Every class need named in the barrier check came from the notes given, or is marked as an assumption.
• 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

• Overloaded lesson checker. Finds too many new ideas at once, split attention and missing background. It hands the problem areas and their fixes to the barrier step.
• Lesson barrier spotter. Predicts barriers in the task, the language and the way learners answer, from your class notes. It hands the top design changes to the checks step.
• Lesson understanding check planner. Places short checks where the answer would change your next move. It hands each check and its stage to the sequence step.
• Revised sequence. Puts the fixes and checks into your lesson in time order and adds up the minutes. Your original plan is not edited.

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 check-a-lesson-before-teaching-it 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/check-a-lesson-before-teaching-it/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

• Your lesson plan, with the tasks, handout text and timings
• What learners should know or be able to do by the end
• The year group or level, and what they have already learned
• How many minutes you have
• Notes on your class, such as learners new to English or with reading needs (optional)
• How you check understanding now, such as mini whiteboards (optional)

Helpful context (optional)

• The text of your handout or slides.
• Notes from the last time you taught this lesson, if you did.

Tools and access

• Claude, ChatGPT or Gemini with file support: They can read your plan and handout as pasted text or files. None of them can watch your class.

Functions and deliverables

• Lesson readiness reviewer: Review a lesson for overload and learner barriers, then add short checks that help the teacher choose the next step.
  • A list of where the lesson overloads learners, with an edit for each
  • A list of barriers ranked by how much they matter, with a fix for each
  • A hinge question, cold-call questions and an exit ticket, with what to do after each answer
  • A revised lesson sequence in time order, with each change marked and a total against your minutes
  • A summary of what could not be checked
• Overloaded lesson checker: Share a learning task and learner level. Get likely overload points and specific design fixes.
  • Load diagnosis in three areas
  • The exact points of overload
  • Specific edits to try
  • A lighter version of the task
  Source: Gareth Manning.
• Lesson barrier spotter: Spot the barriers in a lesson before you teach it. Paste your task and describe your class. You get a list of fixes and who needs extra help.
  • Likely barriers by learner group
  • Barriers design can fix
  • Barriers needing individual support
  • Changes to make before 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.
• 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 wrote a lesson and want a second pair of eyes before you teach it tomorrow.
• A lesson ran long or lost the class last time and you plan to teach it again.
• Your class includes learners who read slowly, are new to English or need extra support.
• A colleague handed you their plan and you need to know if it will work for your group.

Limits to check before starting

• You need a whole course or unit mapped out. Use the Course scope and sequence planner.
• You have no lesson yet. Build one first with the Direct teaching lesson builder, then bring it back here.
• You only want to adapt a lesson for access needs. Use the Lesson access and activity planner workflow.
• You only want a five-minute opener. Use the Lesson opener planner.

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, ChatGPT or Gemini and say "Follow HANDOFF.md".
• Paste your lesson plan, the goal, the level, the minutes and your class notes.
• Read the overload list first. Cross out any fix that removes something you need.
• Compare the revised sequence with your minutes, then teach from it. Keep your original plan as a backup.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/check-a-lesson-before-teaching-it 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.