Worked-Example To Faded-Practice Sequence
Builds a cognitive-load-optimized progression from fully worked examples to independent practice for procedural skills.
Prompt
ROLE: You are a cognitive-load theorist designing instruction for procedural skills using the worked-example and completion-problem effects. CONTEXT: Skill or procedure: [SKILL]. Subject/level: [LEVEL]. Typical learner errors: [ERRORS]. Prerequisite skills assumed: [PREREQS]. Practice time: [MINUTES]. TASK: Build a faded-guidance sequence. 1. Present ONE fully worked example with every step shown and the reasoning narrated (especially at decision points). 2. Create a 'completion problem' where the first steps are done and the learner finishes the rest. 3. Create a 'completion problem' with more steps removed (fading guidance). 4. Provide a fully independent problem at the same difficulty. 5. Provide one transfer problem in a new surface context. 6. For each step in the worked example, flag where [ERRORS] typically occur and add a guardrail prompt. OUTPUT FORMAT: Five labeled stages (Worked → Completion-1 → Completion-2 → Independent → Transfer), with answer keys. Include an 'error hotspots' note tied to the worked example. CONSTRAINTS: Reduce extraneous load — no irrelevant decoration or split-attention. Fade guidance gradually; don't jump from full support to nothing. Keep difficulty constant across stages 1-4 (only support changes); only stage 5 changes context.
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueForces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.
Learn this techniqueIncludes worked examples so the model matches your format and quality by pattern, not description.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.
More in Education & Curriculum
Backward-Design Unit Planner
Builds a complete Understanding by Design unit working backward from enduring understandings to assessments to daily lessons.
Bloom's Taxonomy Objective Ladder
Generates a vertically aligned set of learning objectives across all six Bloom's levels with matched verbs and quick checks.
Differentiated Lesson Tiering Engine
Adapts one core lesson into three readiness tiers plus accommodations for IEP, ELL, and gifted learners without lowering the standard.
Socratic Seminar Question Architect
Designs a layered Socratic seminar with opening, core, and closing questions plus facilitation moves to keep discussion student-led.