teach · Skill Details

Mechanism

When It Triggers · How It Works · What It Produces

Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.

Trigger: User-invoked with the learning topic as argument. /ask-matt lists it as a standalone skill off the main flow.
Mechanism: Uses the current directory as a stateful teaching workspace, auto-creating and managing: MISSION.md (learning motivation), RESOURCES.md (learning resources), reference/ (printable cheat sheets), lessons/ (self-contained HTML), learning-records/ (ADR-like knowledge captures), NOTES.md (preferences), assets/ (reusable components). Teaching loop: determine zone of proximal development → acquire knowledge from resources → design lesson → teach with interaction → record learning → advance. Lessons are short (~5 min). Uses retrieval practice, spaced learning, and interleaving for long-term retention.
Output: A structured self-learning workspace with continuously updated MISSION, RESOURCES, lesson series, learning records, and reference materials. Each lesson is an openable HTML file linking to other lessons and references. Learning persists across multiple sessions.

Use Cases

Two Typical Use Cases

Scenario 01

Learning a new programming language

A developer wants to learn Rust. Invoking `/teach` with "I want to learn Rust to build CLI tools." The skill first learns their motivation via questioning and writes MISSION.md, then finds high-quality primary resources for RESOURCES.md. The first lesson is a self-contained HTML file on "Rust's ownership system" with interactive quizzes (retrieval practice). Every concept is sourced. After the session, reference docs and learning records are created. Lessons use spaced repetition scheduling.

Scenario 02

Learning non-programming skills (e.g., yoga)

A user wants to learn yoga. Invoking `/teach`, the skill switches to skill-oriented mode (vs knowledge-oriented for programming). It creates MISSION.md, designs the first lesson as "5 basic yoga poses with step-by-step guidance" and visual diagrams in HTML, shown in the browser. Subsequent lessons progress according to the user's zone of proximal development, each completable in ~5 minutes with low cognitive load.

Skill Relationships

Which Skills I Use · Which Skills Use Me

Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.

Tier 1 · These Skills Use Me

ask-mattWorkflow

Tier 2 · Current Skill

teachWorkflow

Tier 3 · I Use These Skills

No explicit dependency on other Skills

Full Relationship Graph

Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.

Skill File

SKILL.md

Open in GitHub ↗

SKILL.mdLoading from GitHub…

Skill Composition

Open in GitHub ↗

SKILL.md16.7%
other83.3%

▸skills/teach/
▸teach
- ·GLOSSARY-FORMAT.md
- ·LEARNING-RECORD-FORMAT.md
- ·MISSION-FORMAT.md
- ·RESOURCES-FORMAT.md
- ·SKILL.md
- ▸agents
  - ·openai.yaml

Per the Agent Skills spec, SKILL.md is the only required file. The colored bars classify the rest into the three spec-aligned optional directories (scripts / references / assets) and an 'other' bucket. The full directory tree is below.

Related in Skillset

You May Also Need These Skills

ask-matt

A router skill for the entire skillset: when the user can't remember which skill to use or which flow fits their situation, they invoke this to get a recommendation. It describes the main "idea → ship" flow (grill-with-docs → to-spec/to-tickets → implement), plus on-ramps (triage, diagnosing-bugs, wayfinder), codebase health (improve-codebase-architecture), vocabulary layers (domain-modeling, codebase-design), and standalone skills (grill-me, prototype, research, teach). Following its map leads users to the correct workflow entry point.

Workflow

code-review

A two-axis code review skill: reviews a diff (from a fixed point to HEAD) along both Standards (coding standards + Fowler smell baseline) and Spec (faithful implementation of the originating issue/PRD). Both axes run as parallel sub-agents to avoid context pollution. The report aggregates findings without merging conclusions, ensuring "passes standards but implements the wrong thing" and "implements the right thing but breaks conventions" are both surfaced independently.

Workflow

codebase-design

A shared vocabulary skill for deep module design: provides a precise set of design terms (Module, Interface, Depth, Seam, Adapter, Leverage, Locality) guiding agents and developers to design "deep modules" — a lot of behaviour behind a small interface. Includes design principles (the deletion test, the interface is the test surface) and testability guidelines. A reference skill consumed by other skills (e.g., improve-codebase-architecture, tdd) and invoked directly by engineers.

Style Guide

diagnosing-bugs

A disciplined diagnosis loop for hard bugs and performance regressions. The core idea is to first build a tight feedback loop — no hypothesis phase without one. Six phases: build feedback loop → reproduce + minimise → generate 3-5 falsifiable hypotheses → instrument by prediction → fix + regression test → cleanup + post-mortem. If the codebase architecture can't lock down the bug, it recommends handing off to the improve-codebase-architecture skill.

Workflow