Hire an AI post-course skill reviewer

Everything it can hand back

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

• A skill table with the course goal, the role expectation, the evidence found and a mark for each skill
• Self-reports and certificates listed apart, so they do not pass as proof
• A list of what gets in the way of using the skills, tied to evidence
• A practice plan with supervisor support and a date to check again
• A summary of missing evidence and one next step

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: A team finished a course some weeks ago and you want to know if anything changed.

• Skill evidence table. Each skill with the course goal, role expectation, evidence found and a mark.
• Self-reports list. Certificates and comments kept apart, with what each can and cannot show.
• Transfer barriers. What gets in the way of using the skills, with the evidence and who can change it.
• Practice plan. Practice on real work, supervisor support, evidence to collect and a date to check again.
• Hand-back summary. Files saved, evidence missing, checks not done and one next step.

How the work is checked

• Every mark cites a work sample and its date.
• No certificate, score or self-report is counted as evidence of skill in use.
• Every barrier is tied to evidence or written as a question.
• The plan does not claim any improvement.
• 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

• Role skills framework builder. Sets out the skills the course aimed at and what each looks like at work, then matches each to your work samples. It labels missing or clashing evidence and hands the table to the plan step.
• Training program builder. Turns the gaps into practice on real work, supervisor support and a later evidence check. It does not claim the plan has worked.
• Check and hand back. Checks that every mark cites a sample and that self-reports are kept apart. It lists what is missing and gives one next step.

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-training-transfer-after-a-course 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-training-transfer-after-a-course/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

• The course's learning objectives, as written before it ran
• Samples of real work from after the course, with dates and names removed
• What the role expects at work, such as a job description or standards
• The follow-up window you agreed, with start and end dates
• Feedback from managers or colleagues, only where people agreed to share it (optional)
• Notes on what else changed at work in that time, such as new tools or staff changes (optional)

Helpful context (optional)

• Dated work samples from before the course, so change can be seen.
• A named supervisor who can confirm what the samples show.

Tools and access

• Claude, ChatGPT or Gemini with file support: They can read work samples and documents you paste. None of them can watch anyone work.
• Any good chat AI: This is a writing and structuring job that any strong chat AI does well.
• Any good chat AI: This is a planning and writing job. Claude, ChatGPT and Gemini all do it well.

Functions and deliverables

• Post-course skill reviewer: Compare real work after a course with the target skill. Find gaps and plan practice, support and a later check.
  • A skill table with the course goal, the role expectation, the evidence found and a mark for each skill
  • Self-reports and certificates listed apart, so they do not pass as proof
  • A list of what gets in the way of using the skills, tied to evidence
  • A practice plan with supervisor support and a date to check again
  • A summary of missing evidence and one next step
• Job skills and level planner: Build a skills framework for your roles: key skills, what good looks like at each level, and interview questions with scoring guides.
  • Skills every role shares, and skills for each role
  • One example behaviour per skill at four levels
  • A profile per role with the 5 to 7 key skills and level needed
  • Interview questions with scoring guides
  • Review wording and learning ideas for each skill
  Source: Tuan Duc Tran.
• Training program builder: Turn a skills gap into a training plan: ranked gaps, clear learning objectives, a session outline and a coaching plan for after.
  • A needs table with the top gaps ranked by priority
  • Three to five learning objectives
  • A session outline with a practice task in each session
  • A coaching and follow-up plan for managers
  • Questions to check what stuck
  Source: Tuan Duc Tran.
• Job post writer: Share a role, level, team, and first-year goal. Get a clear job description, a bias review, and questions for gaps.
  • A finished job description
  • A bias check on the wording
  • Questions that fill any gaps
  • A rewrite of weak sections
  Source: Carlo Pezzuto.
• 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

• A team finished a course some weeks ago and you want to know if anything changed.
• A manager says "they all went on the course, but nothing is different".
• You must report on training spend and have work samples, not only survey scores.
• You are choosing what follow-up help to give after a workshop.

Limits to check before starting

• The course has not run yet. Plan it with the Manager training and practice session planner workflow or the Staff training session planner.
• You only have survey scores and certificates. Collect work samples first, because scores cannot show use at work.
• You want to judge one person's performance for pay or discipline. This is not built for that. Use your HR process.
• You are planning an internship or placement. Use the Internship learning and review planner workflow.

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. The site builds it as a zip with HANDOFF.md and every skill file this workflow uses. If you cannot download it, paste the steps from this page into your AI in order.
• Give the folder to Claude, ChatGPT or Gemini and say "Follow HANDOFF.md".
• Paste the learning goals, the role expectations and the work samples with their dates. Say what the follow-up window is.
• Ask to see the skill table before the plan is written. Check each mark against the sample it cites and fix any you disagree with.
• Share the plan with the supervisor. Run the check again after the follow-up window.

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-training-transfer-after-a-course 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.