Concept Rediscovery Walk
Guides a learner to invent a math or ML concept themselves through a Socratic walk — a sequence of small guessable questions that ends with the learner stating the formal definition unprompted. The 3Blue1Brown signature move. Use when the learner is meeting a foundational concept (eigenvectors, gradient, attention, softmax, KL divergence) for the first time, when prior exposure produced memorization without understanding, or when the user says "explain it from scratch", "I want to really get it", "build it up for me", or "where does this come from".
Install
/plugin marketplace add lyndonkl/claudeThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add lyndonkl/claude --skill concept-rediscovery-walkgit clone --depth 1 https://github.com/lyndonkl/claude.git /tmp/claude
mkdir -p ~/.claude/skills
cp -r /tmp/claude/skills/concept-rediscovery-walk ~/.claude/skills/concept-rediscovery-walkPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Concept Rediscovery Walk ## Table of Contents 1. [Workflow](#workflow) 2. [The Three Cuts](#the-three-cuts) 3. [Question Types](#question-types) 4. [Common Patterns](#common-patterns) 5. [Guardrails](#guardrails) 6. [Quick Reference](#quick-reference) The principle is simple: a learner who *guesses* the equation `Av = λv` from "what would survive a transformation unchanged?" owns eigenvectors in a way that no exposition can match. This skill structures the walk that makes that guess possible. **Quick example (Eigenvectors):** > **Set the seed:** "Picture any 2D matrix as a transformation that bends the plane — most arrows get rotated and stretched. But are there special arrows that *only* get stretched, not rotated?" > > **Let them guess:** "What would such an arrow satisfy, if A is the matrix?" > *Learner:* "Av is parallel to v?" > > **Tighten:** "Right — and 'parallel' means equal up to a scalar. So we need…?" > *Learner:* "Av = λv for some number λ." > > **Name what they invented:** "You just wrote the eigenvector equation. v is an eigenvector, λ is its eigenvalue. Now we never have to introduce them — you derived them." Ten lines. The learner did most of the talking. That is the move. ## Workflow Copy this checklist and track your progress:
Details
- Skill name
concept-rediscovery-walk- Repository
- lyndonkl/claude
- Path
skills/concept-rediscovery-walk/SKILL.md- Repo updated
- 1 September 2026
FAQ
What does the Concept Rediscovery Walk skill do?
Guides a learner to invent a math or ML concept themselves through a Socratic walk — a sequence of small guessable questions that ends with the learner stating the formal definition unprompted. The 3Blue1Brown signature move. Use when the learner is meeting a foundational concept (eigenvectors, gradient, attention, softmax, KL divergence) for the first time, when prior exposure produced memorization without understanding, or when the user says "explain it from scratch", "I want to really get it", "build it up for me", or "where does this come from".
How do I install the Concept Rediscovery Walk skill?
Claude Code plugin: /plugin marketplace add lyndonkl/claude. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Concept Rediscovery Walk popular?
It lives in lyndonkl/claude, which has 200 GitHub stars and 25 forks.
Related skills
Abstraction Concrete Examples
200lyndonkl/claude
Builds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels. Bridges communication gaps, reveals hidden assumptions, and tests whether abstract ideas work in practice. Use when explaining concepts at different expertise levels, moving between abstract principles and concrete implementation, identifying edge cases by testing ideas against scenarios, designing layered documentation, decomposing complex problems into actionable steps, or bridging strategy-execution gaps.
Academic Letter Architect
200lyndonkl/claude
Guides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm. Use when writing recommendation letters for students, postdocs, or colleagues, or when user mentions recommendation letter, reference, nomination, letter of support, endorsement, or needs help with strong advocacy and comparative statements.
Adr Architecture
200lyndonkl/claude
Documents significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood. Creates a decision trail that helps teams understand why decisions were made. Use when choosing between technology options, making infrastructure decisions, establishing standards, migrating systems, or when user mentions ADR, architecture decision, technical decision record, or decision documentation.
Corporate Governance Analysis
200lyndonkl/claude
Assesses who actually controls a company and whether management is accountable — board independence, dual-class and voting structures, cross-holdings and pyramids, the marginal investor, and the gap between stated and real accountability. Use in a corporate finance analysis, when setting the objective function for a valuation, when assessing the odds that bad management gets replaced, or when valuing control.
Causal Inference Root Cause
200lyndonkl/claude
Systematically investigates causal relationships to identify true root causes rather than correlations or symptoms. Distinguishes genuine causation from spurious associations, tests competing explanations, and designs interventions addressing underlying drivers. Use when investigating why something happened, debugging systems, analyzing failures, evaluating policy impacts, or when user mentions root cause, causal chain, confounding, spurious correlation, or asks "why did this really happen?
Dagster
213TerminalSkills/skills
Dagster is a data pipeline orchestrator built around the concept of software-defined assets. Learn to define assets, ops, jobs, schedules, sensors, and resources for building maintainable data platforms.
Browse the most popular Claude skills, all finance & crypto skills, or write your own with the skills generator.