Skip to content
Education
Skill

/concept-coach

Build durable understanding by finding a learner's frontier, agreeing on a dependency route, developing one connection at a time, and checking each connection. Use for tutoring, studying, guided practice, and explanations meant to be retained.

From plugin
conceptloom
2031 skill1 agent

Claude Code

$ npx -y skills add Zproger/ConceptLoom --skill concept-coach --agent claude-code

SKILL.md

concept-coach.SKILL.md
name: concept-coach
description: Build durable understanding by finding a learner's frontier, agreeing on a dependency route, developing one connection at a time, and checking each connection. Use for tutoring, studying, guided practice, and explanations meant to be retained.

Concept Coach

Teach so the learner can recreate the conclusion from ideas they trust.

Read [the coaching reference](references/coaching-reference.md) before beginning a learning session. Follow Locate, Weave, and Build without collapsing them into a generic explanation.

Learning sessions must survive restarts. Start a notebook and persist progress with `loom_save_learning_state` throughout the lesson. If the learner asks to continue or resume, call `loom_load_learning_state` before responding with lesson content.

After every learner response, persistence must be your next action. Save route approval as `phase=build` before asking the first teaching question. Assess checkpoints with `sessionId` and an exact `nextStep`; assessment saves progress in the same call. Never send the next lesson message first.

Use `AskUserQuestion` for preferences and for presenting checkpoint choices. Grade only knowledge questions, using `loom_frame_checkpoint` before asking and `loom_assess_checkpoint` after the learner selects keys.

Choose evidence-appropriate checkpoints: choice for recognition, free recall for reconstruction, prediction or debugging for application, and transfer for a new context. Record confidence when useful and pass a stable `evidenceConcept`. At resume, check `loom_list_due_reviews` before reteaching saved material.

Delegate source verification to the `evidence-scout` subagent when facts are uncertain or time-sensitive. Prefer a compact text diagram; use a Mermaid block only when it makes a larger relationship clearer. Wait for learner approval after proposing the dependency route.

Read more
Stats
205
Stars
20
Forks
Maintained
Maintenance
JavaScript
Language
MIT
License
Last commit
Created
Added

Repo: Zproger/ConceptLoom

@zproger
Ships withconceptloom

A portable AI learning workflow for Codex, Claude Code, OpenCode, and DeepSeek Harness. Concept Loom turns a coding agent into a structured learning partner.

2031 skill1 agent
Get the whole plugin

Stars on GitHub

Momentum

stars in total
203
Star history of Zproger/ConceptLoom on GitHub, a chart by star-history.com

More skills from other plugins.

lesson-quiz

lesson-quiz

Test a learner on a single Claude Code tutorial lesson (01-10) with 10 questions, scoring answers and flagging weak spots. Use…

@luongnv89@luongnv89Install Skill
build-personal-skill

build-personal-skill

Evidence-based creation of a reusable personal course-making Skill from the user's own classroom and chat history. Use when the…

@thu-maic@thu-maicInstall Skill

Questions about concept-coach.

Which coding agents can use concept-coach?
concept-coach installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.