K Teach is an open-source skill and deterministic CLI that follows the open Agent Skills format. It uses a structured teaching loop, a single-source Lesson Bundle mechanism, and cross-session evidence tracking to make AI truly teach you — not just answer you.
$ npm install -g k-teach@latest ✓ installed k-teach 1.x $ k-teach init --tools codex,claude --teach mathematics → created .k-teach/config.yaml → created teachs/mathematics (mission, glossary, logs) → wired Agent integrations for codex, claude ✓ Learning Project ready. Start teaching.
K Teach breaks teaching into verifiable, traceable, reproducible steps, so the AI teacher has a mission, a rhythm, and evidence — like a human teacher.
Establish an observable learning mission and success criteria first, then design each "smallest useful challenge" around it.
Explanations, exercises, feedback, and retrieval rules are stored as one authoritative source; channel outputs are only derived from it.
We only record "demonstrated learning" when the learner explains, retrieves, applies, transfers, or corrects.
The learning workspace keeps the mission, content, evidence, and teaching decisions across sessions — pick up where you left off.
No credentials in storage, local lessons private by default, public publishing requires confirmation, artifacts immutable after release.
SKILL.md is a platform-neutral contract shared by Codex / ChatGPT / Claude / any agent.
From mission to evidence, an eight-step tight loop. Each step is verifiable by the CLI and traceable to the Lesson Bundle.
Define concrete goals and observable success criteria so teaching has direction.
MissionCheck existing knowledge, learning records, trusted sources, and study habits.
AssessChoose a task slightly above the current level that you can start right away.
ChallengeValidate every factual claim against authoritative primary sources — no fabrication.
VerifyFocus on a single lesson's capability: activate prior knowledge → explain → practice → feedback → retrieval without looking back.
BundleText, deterministic SVG diagrams, or optional generated visuals — combine as needed.
MediaWhen intent is unclear, ask first: learning / WeChat / PPT — each derived independently.
GenerateWrite evidence back to the learning record to drive the next round of content choices — the loop continues.
EvidenceWeb lessons, HTML presentations, and WeChat articles are all deterministically derived from the same Lesson Bundle — consistent facts, traceable sources.
A local static learning site; every lesson opens independently, with exercises and retrieval checks.
Derived from a Presentation Brief, with keyboard navigation and presenter notes.
Derived from a Publication Brief, requires explicit authorization, platform-safe expression.
TypeScript source, deterministic CLI, open Agent Skills format — stable, verifiable, easy to publish.
Install the persistent CLI globally, initialize a Learning Project, and let AI take over the teaching.
# 1. Install the persistent CLI globally npm install -g k-teach@latest # 2. Enter your project and initialize cd your-learning-project k-teach init # 3. Specify agents and first Teach (optional) k-teach init --tools codex,claude --teach mathematics # Local preview (binds 127.0.0.1 only) k-teach preview --open