Skip to main content
โ—Free ยท Opal University

Get coached by AI
on how you are using AI.

A free Claude Code skill that scores your recent prompts on Opal University's CLEAR framework and tells you the one move that would level you up. One file. Zero install friction. No account needed.

Why this exists

Everyone is learning AI alone. Nobody knows what good looks like.

Your boss told you to figure out AI. Every LinkedIn post makes you feel 10 steps behind. There is no playbook. No peer at your company is ahead of you to copy.

The thing nobody tells you is that prompting is a learnable skill. There are patterns that make AI respond better, and patterns that waste your time. You just have not had anyone coach you on the difference.

This skill is that coach. In one minute, you will know where you are and what to try next.

How it works

Three steps. Under a minute.

1

Install the skill

One line in your terminal. The skill is a single markdown file. No account, no token, no backend.

2

Prompt Claude Code like you always do

Keep working. The skill stays quiet until you ask for it. Your prompts never leave your machine.

3

Say "coach me"

Claude pulls your recent prompts, scores them on CLEAR, tells you the one move that would level you up.

What you will see

A report card, not a grade.

When you say "coach me," Claude writes you something like this. Specific praise. One real opportunity. One move to try next.

Your AI Readiness Report

Level: Operator

6.4 / 10 across 5 prompts

What is working

Your second prompt named the file (lib/auth.ts) and quoted the error. That is pro-level context and it is why Claude got it right on the first try.

Biggest opportunity

Your Actions score is the weakest. You asked Claude to "make it better" twice without saying what better means. Try this rewrite of your last prompt:

"Rewrite this function so it returns a typed result (union of success or error) instead of throwing. Keep the signature. Under 30 lines. Do not add new dependencies."

Try this on your next prompt

Add one line up front that says what format or length you want back. That alone usually bumps 2 points.

Free 5-day cohort to go deeper: university.optimizely.com

The 5 dimensions

CLEAR

  • C

    Context

    Did you name the file, the error, the constraint?

  • L

    Layout & Logic

    Is the ask organized, or a wall of text?

  • E

    Examples

    Did you show what good looks like?

  • A

    Actions

    Did you say what format, length, scope, tone?

  • R

    Review & Refine

    Constraints, edge cases, "do not do X"?

The 5 levels

Curious โ†’ Principal

  • 0 โ€“ 3

    Curious

    Just getting started. Every prompt is practice.

  • 3 โ€“ 5

    Practitioner

    Finding your rhythm. Prompts are landing more often.

  • 5 โ€“ 7

    Operator

    Steady and reliable. You know what to ask for.

  • 7 โ€“ 8.5

    Coach

    You could teach this. First-try results are the norm.

  • 8.5 โ€“ 10

    Principal

    Top 1%. You treat prompting like engineering.

Install

One line. Paste it.

This creates ~/.claude/skills/opal-coach/SKILL.md and downloads the skill. Restart your Claude Code session after running it.

mkdir -p ~/.claude/skills/opal-coach && curl -fsSL https://university.optimizely.com/skills/opal-coach/SKILL.md -o ~/.claude/skills/opal-coach/SKILL.md

After you paste it

Open a new Claude Code session, work on anything for 3 to 5 prompts, then say "coach me." That is the whole thing.

Want to see the file first?

Read the SKILL.md. It is plain English. No tricks, no telemetry, no network calls.

FAQ

Real questions, answered.

What is a Claude Code skill?+

A markdown file Claude Code reads when you invoke it. Skills live in ~/.claude/skills/. No extensions, no plugins, no installs beyond the file itself. This one is a single SKILL.md.

Does my prompt text leave my machine?+

No. The skill runs locally in your Claude Code session. Claude reads your recent prompts from the session it is already in, scores them, and gives you the report. Nothing gets sent to Opal University.

What is CLEAR?+

The prompt-quality framework Opal University teaches. Five letters: Context, Layout & Logic, Examples, Actions, Review & Refine. Each one is scored 0 to 10, averaged into a composite, mapped to a level.

Do I need a Claude subscription?+

You need Claude Code, the terminal AI coding tool from Anthropic. If you already use Claude Code, this skill plugs right in. If you do not, the skill will not run on its own, it needs Claude Code as the host.

How often should I invoke it?+

Once every 5 to 10 prompts is the sweet spot. More than that and you are coaching instead of building. Less and you lose the feedback loop. The point is awareness, not judgment on every turn.

Is this really free?+

Yes. No account, no credit card, no upsell. It is a plain text file. The 5-day Opal University cohort is also free.

What if my score is low?+

Good. That means there is room to grow. The point of the skill is not to flex, it is to give you a specific thing to try next. A low score today becomes a higher score next week if you apply the tip.

Can I use this if I am not a developer?+

If you use Claude Code, yes. If you prompt in a browser (Claude.ai, ChatGPT), this skill will not help you yet. A browser version is on the roadmap.

Your next move

Install the skill.
Find out where you are.

One minute from now, you will have a report card. Tomorrow, you will prompt better. Next week, your team will notice.