learning-first-principles_skill

Overview

This skill implements a learning-first-principles cognitive framework that diagnoses learning methods, assesses efficiency, and provides concrete optimization advice. It maps user learning behaviors to a core principle chain (Self-learning → Induction → Self-output → Expression restructuring → Logical understanding → Practice) and produces actionable steps to improve learning ROI. Use it to decide whether a plan or content is worth your time and how to make learning more self-driven and effective.

How this skill works

Given a description of learning goals, methods, schedules, or materials, the skill inspects six dimensions: self-learning drive, induction and summary, self-output, expression restructuring, logical reasoning, and practice verification. It flags anti-patterns, links them to the principle chain, estimates current time-ROI, and suggests 1–3 prioritized actions tied to specific principles. The output includes a concise diagnosis, concrete improvement steps, and an expected efficiency shift after optimization.

When to use it

• You want to check if your current study routine follows learning-first-principles
• Evaluating whether a course, book, or plan is worth the time investment
• Diagnosing why concepts are not sticking or transfer to new problems
• Designing a study plan that maximizes active learning and practice
• Optimizing time allocation between passive lessons and hands-on work

Best practices

• Start every learning period with a small project or question to drive curiosity
• Replace passive note-taking with brief self-output tasks (summaries, explanations)
• Distill patterns via induction: write 1–3 transferable rules after each session
• Restructure expression by reframing ideas in new contexts or diagrams
• Always design a minimal practice test to verify understanding within 24–72 hours

Example use cases

• Converting a paid course into a project-driven roadmap with daily practice quotas
• Assessing whether a 2-hour daily class schedule yields sufficient active output
• Diagnosing repeated failure on problem sets and pinpointing missing logical links
• Deciding whether a new topic is worth deep study based on expected transferability
• Turning passive reading into a loop: read → induce patterns → self-output → test