# Learning Plan Verification

## When to use this reference

- Stress-testing custom study roadmaps, skills acquisition plans, or schedules
- Verifying target topics, practice methods, and feedback loops
- Reviewing curriculum outlines, coding tutorials, or textbook reading roadmaps
- Assessing learning targets, metrics, or required project boundaries

## When not to use this reference

- Critique of high-level company or product strategies → Use `business-strategy-grill.md`
- Verifying code models or API specifications → Use `technical-design-grill.md`
- Generating raw study summaries or writing explanations of technical topics

## Question Priority

1. **Learning Goal** — What is the specific target skills or outcomes?
2. **Evaluation Metric** — How do we prove the target skills have been acquired?
3. **Time Commitment** — How many hours per week are allocated? For how many weeks?
4. **Prerequisites & Current Level** — What background context or skills do we already have?
5. **Topics to Cover** — What is the sequence of concepts to learn?
6. **Practice & Implementation** — How do we apply the theory to practice?
7. **Feedback & Loop** — How do we identify gaps and correct errors?
8. **Diminishing Returns Point** — Are we learning irrelevant or overly deep topics?

## Strong Question Patterns

- "What is your main goal? (e.g., 'To build a full-stack Next.js app from scratch' vs. 'To pass an exam')"
- "What is your validation criteria? What output will prove you acquired the skill?"
- "How many hours per week can you consistently commit? Over-ambitious plans usually fail."
- "How will you get feedback when you get stuck or make mistakes? Do you have a mentor, community, or test framework?"

## Weak Question Patterns

- "Is this study plan good?"
- "Do you think this technology is promising?"
- "Will you study hard?"

## Recommended Option Rules

- **Goal Metric Ambiguity**: Recommend `(Recommended) Complete a small, functional toy project demonstrating the core skill` and include finishing a lecture/passing a test to build the option set.
- **Time Commitment Ambiguity**: Recommend `(Recommended) A realistic, sustainable commitment of 5 hours per week for 4 weeks` and include full-time/irregular options to build the option set.
- **Feedback Loop Ambiguity**: Recommend `(Recommended) Summarize concepts into a 1-page guide and explain it to others to find gaps` and include solo review to build the option set.

## Handling Vague Answers

- "I want to learn everything about AI" → Narrow down: "Within 4 weeks, what is the single sub-topic or model architecture you must understand first?"
- "I'll study in my free time" → Quantify: "Let's set a concrete target of '30 minutes every morning before work'. Shall we use this as our study schedule?"
- "I'll just search Google if I get stuck" → Map loop: "Shall we set up a rule to spend maximum 30 minutes searching, and if still stuck, ask a specific question in a community?"

## Stopping Conditions

In addition to common stopping conditions, ensure:
- The target skill/outcome is clearly defined.
- A functional project target (evaluation metric) is established.
- The time budget (weekly hours, total weeks) is quantified.
- The concept learning sequence is mapped.
- An error-correction feedback loop is defined.

## Final Synthesis Required Items

Add the following to the common final synthesis format:
- Clear Learning Goals
- Output Verification Project
- Time Budget Constraint
- Weekly Learning Roadmap (Outline)
- Feedback & Error Correction Plan