Teach Back

Find out what the user actually understands about a topic by having them explain it back (the Feynman technique), then probe the gaps one question at a time and end with a one-page cheat sheet and spaced review questions. Works for anything they are studying or have just read, watched or built: a paper, a course, a codebase, an interview topic, a concept. Use when the user says "quiz me", "test my understanding", "help me study", "I'm preparing for an interview on X", "did I get this right", or "make me a cheat sheet".

517 stars 39 forksLearning & Education

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add dotslashsimran/simcraft --skill teach-back
Manual install
git clone --depth 1 https://github.com/dotslashsimran/simcraft.git /tmp/simcraft
mkdir -p ~/.claude/skills
cp -r /tmp/simcraft/skills/learning/teach-back ~/.claude/skills/teach-back

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Teach back

The test of understanding is explaining it simply. If the user can't explain it in plain words, there's a gap, and the gap is the part worth studying. This skill finds the gaps, fills them, and checks again later.

## 1. Set up

Ask one question at a time:
1. What's the topic, and how deep do they need it? ("Enough for a system design interview" is different from "enough to use it at work".)
2. Do they have source material? A paper, notes, a doc, a repo or a video transcript. If they do, read it, and base every question and correction on it, quoting it when you correct.

## 2. They explain, you listen

Ask them to explain the topic as if to a smart friend who's never heard of it. Voice note style is fine. Don't interrupt and don't correct yet.

Then sort what they said into three groups (show this to them briefly):
- **Solid**: correct and in their own words.
- **Fuzzy**: roughly right but vague, hand-wavy, or using jargon they didn't unpack.
- **Missing or wrong**: important parts they skipped, or got wrong.

## 3. Probe the gaps

Work through the fuzzy and missing parts, most important first, **one question at a time**:
- Ask "why" and "what would happen if" questions, not definitions. "What breaks if the cache never expires?" tests more than "What is a TTL?"
Read the full skill on GitHub

Details

Skill name
teach-back
Path
skills/learning/teach-back/SKILL.md
License
MIT
Repo updated
9 November 2026

FAQ

What does the Teach Back skill do?

Find out what the user actually understands about a topic by having them explain it back (the Feynman technique), then probe the gaps one question at a time and end with a one-page cheat sheet and spaced review questions. Works for anything they are studying or have just read, watched or built: a paper, a course, a codebase, an interview topic, a concept. Use when the user says "quiz me", "test my understanding", "help me study", "I'm preparing for an interview on X", "did I get this right", or "make me a cheat sheet".

How do I install the Teach Back skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add dotslashsimran/simcraft --skill teach-back. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Teach Back popular?

It lives in dotslashsimran/simcraft, which has 517 GitHub stars and 39 forks.

Related skills

API Design Review

517

dotslashsimran/simcraft

Review the design of an API surface, meaning an HTTP API (OpenAPI spec or route code), an SDK's public classes and functions, or a CLI. Checks naming and consistency, resource modelling, error design (stable codes, RFC 9457 problem details, request ids), versioning and breaking changes, pagination, filtering, idempotency and retries, rate limits, timeouts, long-running operations, webhooks, auth, partial updates, ID, time and money formats, SDK ergonomics and CLI conventions. Uses scripts to lint OpenAPI files, classify changes between two spec versions as breaking or safe, and dump an SDK's p

Software Development39

Benchmark Honestly

517

dotslashsimran/simcraft

Build benchmarks that survive scrutiny and catch the classic lies (dead code elimination, lazy results, constant folding, warm caches, coordinated omission, averages hiding GC pauses, unequal work, noisy machines). Defines the question first, controls and discloses the environment, uses warmups, interleaved repeats, medians, bootstrap confidence intervals and Mann-Whitney tests, and ends with a one-line verdict that includes the CI. Bundles a command runner, an environment reporter and an open-loop latency tester. Use when the user says "benchmark this", "is this faster", "compare performance"

Software Development39

Bisect Anything

517

dotslashsimran/simcraft

Find the exact commit (or dependency version, config value, or input) that caused a regression by turning it into an automatic pass/fail check and running git bisect run in a separate worktree, then shrink the bad commit to the hunk that matters and explain it. Handles failing tests, changed output, slowdowns, crashes, visual changes, server behaviour, flaky checks, unbuildable commits and merge-heavy history. Use when the user says "what broke this", "find the commit that", "when did this start", "it used to work", "regression", "git bisect", "which version broke it", or "which change made it

Git & Code Review39

Rl Execution

564

agiprolabs/claude-trading-skills

Reinforcement learning for trade execution optimization including order splitting, adaptive timing, and impact minimization

Learning & Education113

System Design From Scratch

517

dotslashsimran/simcraft

Design a backend or distributed system by building a tiny but real working version of it, proving its properties with invariant tests, a load test (throughput and p50/p95/p99 latency) and fault injection (crashed nodes, dropped or delayed messages, partitions, clock skew, full disks), then writing a design doc with the numbers, alternatives, where it breaks, how Redis, Kafka, Cassandra or etcd do it, and an interview-ready summary. Works for rate limiters, job queues with retries and visibility timeouts, consistent hashing, LSM-tree key-value stores, write-ahead logs, Raft leader election, cac

Learning & Education39

10 Learn

564

ai-driven-dev/framework

Capture durable project learnings. Use when the user wants to remember, record, or formalize a decision, convention, lesson, pitfall, reusable workflow, or review finding. Not for preferences or temporary notes.

Learning & Education65

Browse the most popular Claude skills, all learning & education skills, or write your own with the skills generator.