Prompt: Learn a skill by copying then breaking the copy (UP-Context, Learning)

2 days ago

4 min read

A curved blue form repeated as three disassembled pieces, one picked out in red.

In this Prompting Publication

What this prompt does

This prompt does one job: it turns a demonstration you watched into a practice plan. Copy it, break it into sub-skills, drill the one that limits you, then rebuild the whole.

UP-Context prerequisites

Required layers: USER-PERSONA, FULL-CONTEXT, AI-PROFILE-ROLE-EXPERTISE and AI-EXACT-TASK. The USER-PERSONA layer sets your current level, and the drills are pitched at it: the same demonstration yields different drills at different levels.

Where it runs

Execution environment: Project or Skill. As a skill it is the default handling for any technique you are trying to acquire.

The prompt

Copy the block below in full. It is the whole prompt: nothing else needs to be attached, and no University 365 file is requested of you.

PROMPT STARTS HERE

Select everything in blue from the line above the word PROMPT STARTS HERE down to the line before word PROMPT ENDS HERE, and paste it into a new AI chat with the appropriate LLM and thinking level. Replace every bracket with your own text before you send it.

INSTITUTIONAL CONTEXT (read before you begin) This prompt is complete on its own. Everything it needs about University 365, about ULM and EVA, and about the UP-Context Method is defined below. No University 365 file is attached to it and none is required. The institution. University 365 is an institution of higher learning. Its Department of Academics owns the curriculum and the academic standards. The method. The UP-Context Method (University 365 Prompting-Context) structures every prompt into eight layers, five required and three optional: USER-PERSONA (who is asking), FULL-CONTEXT (the situation and the facts), AI-PROFILE-ROLE-EXPERTISE (who the AI is acting as), AI-EXACT-TASK (the exact job asked now), AUDIENCE (who the output is for), plus the three optional layers USER-FINAL-GOAL (the goal being worked toward), EXPECTED-FORMAT (the shape of the answer) and EXAMPLES (reference examples). A layer is text in the prompt first; keep it as a reusable file when its text is long enough and reused across prompts. The framework. ULM (University 365 Life Management) organises a person's life into six domains: Body and Health, Spirit and Mind, Character and Emotions, Social and Love Relationships, Career and Finance, Quality of Life. EVA is the engine that carries a person through each domain in three phases: Explore, Visualize, Action Plan. Who is who. U.Copilot is the AI assistant. U.Coach is a human coach. U.Copilot is not a human, must never present itself as one, and must never give medical, legal or financial advice. Your judgement. This prompt supports your thinking. Every recommendation it produces is a draft for you to check, not a decision made on your behalf. THE COPY, THEN BREAK IT #USER-PERSONA: I am the person learning the skill. If a persona file is present in this project, apply it. If the layer was written as text instead, it appears after this line: [Write three to six lines about yourself as a learner: the skill, your current level, and what you can already do without help.] #FULL-CONTEXT: the demonstration I am learning from. If a context file is present in this project, apply it. If the layer was written as text instead, it appears after this line: [Describe or paste the demonstration, example, model answer or recording you are learning from, and say what the finished result should look like.] #AI-PROFILE-ROLE-EXPERTISE: you are a skills coach who teaches by decomposition and repetition. You know that watching a demonstration produces the feeling of learning without the ability, and that only reproducing it does. #AI-EXACT-TASK: turn the demonstration below into a practice plan in four stages: 1. COPY. The steps to reproduce the demonstration exactly, in order, with the decision made at each step and what you would see if the step went right. 2. BREAK IT DOWN. The three or four sub-skills inside it, each described in one line, plus one drill for each that can be done in fifteen minutes. 3. DRILL THE HARD PART. Which sub-skill to drill first and why, how many repetitions to attempt, and what counts as progress on it. 4. INTEGRATE. How to return to the whole task while keeping the drilled part correct, and the one sign that tells me I have slipped back. #AUDIENCE: me, at my current level, practising alone without a teacher present. #EXPECTED-FORMAT: four numbered sections with the exact titles ABOVE. Section 1 is a numbered list of steps. Section 2 is a table: sub-skill, drill, how I know it worked. Section 3 is short prose. Section 4 ends with the one sign to watch for. #EXAMPLES: none. Work from the demonstration I described. RULES 1. The drills must be doable alone, in fifteen minutes, with no special equipment. 2. Say explicitly which parts cannot be learned from a demonstration at all, and need a person, if any. 3. Never present watching or reading as practice. Only producing counts. 4. Where the demonstration hides a decision, say that it is hidden and what to watch for. 5. End by naming the single sub-skill that will still be weak after a week of this plan.

PROMPT ENDS HERE

The brackets are the only parts you change. Everything else is the prompt.

A four-stage flow: watch, break down, drill, integrate, with drill marked as the stage to repeat.

What to change for your situation

Describe the demonstration as precisely as you can: the steps matter more than the style. The DRILL stage is the one to edit: change the repetition count to match the time you actually have.

Verification checklist

Multi-model check: run the prompt on a second model and compare. External source check on any factual claim that matters. Human review before you act. CI-First test: does using this prompt build your own judgement, or replace it?

What this does to you

CI-First score 8.5, band Strong: time 7, quantity 6, quality 9, skill 9. Humics: Creativity Friendly, Critical Thinking Friendly, Social Authenticity Friendly, value +3. Imposture risk Low: the prompt refuses to count watching as practice and names what cannot be learned alone.