teach

Files (6)

• GLOSSARY-FORMAT.md
• LEARNING-RECORD-FORMAT.md
• LICENSE
• MISSION-FORMAT.md
• RESOURCES-FORMAT.md
• SKILL.md

SKILL.md (first lines)

# Teach

## Pi-specific visibility

This is a Pi-specific skill because it is intentionally hidden from Pi's model-advertised skill list. The user invokes it explicitly through `/teach` or `/skill:teach`; the `/teach` prompt loads this skill.

## Provenance and local integration

This is a minimal local adaptation of [`skills/productivity/teach`](https://github.com/mattpocock/skills/tree/6654f6b60cd9d5be8b54c6fafe44346dabeb3b76/skills/productivity/teach) from [mattpocock/skills](https://github.com/mattpocock/skills), pinned at revision `6654f6b60cd9d5be8b54c6fafe44346dabeb3b76`. It is distributed under the upstream [MIT License](LICENSE).

Local changes distinguish the read-only `SKILL_ROOT` from the teaching `WORKSPACE_ROOT`, require confirmation and a short baseline assessment for a new workspace, add the glossary format and quiz-answer shuffling, and keep lessons as shared-asset workspace artifacts rather than Visual Explainer outputs.

## Teaching Workspace

The user has asked you to teach them something. This is a stateful request - they intend to learn the topic over multiple sessions.

Use two distinct roots:

- **SKILL_ROOT** is the directory containing this `SKILL.md` and its format documents. In the Pi agent installation it is `~/.pi/agent/skills/teach`. Read `MISSION-FORMAT.md`, `RESOURCES-FORMAT.md`, `LEARNING-RECORD-FORMAT.md`, and `GLOSSARY-FORMAT.md` from this directory.
- **WORKSPACE_ROOT** is the confirmed directory for one teaching mission. All course artifacts belong here. Never write course artifacts under `SKILL_ROOT`.

For a new teaching workspace, resolve and report the exact absolute `WORKSPACE_ROOT`, then ask the user to confirm it is the dedicated teaching workspace before writing any course artifact. If the current directory is an unrelated project or the workspace is unclear, ask for the intended `WORKSPACE_ROOT`. An existing, unambiguous teaching workspace may continue without reconfirmation.

The state of their learning is captured under `WORKSPACE_ROOT` in several files:

- `MISSION.md`: A document capturing the _reason_ the user is interested in the topic. This should be used to ground all teaching. Use the format in `SKILL_ROOT/MISSION-FORMAT.md`.
- `WORKSPACE_ROOT/reference/*.html`: A directory of reference materials. These are the compressed learnings from the lessons - cheat sheets, reference algorithms, syntax, yoga poses, glossaries. They are the raw units of learning. They should be beautiful documents which print out well, and are designed for quick reference.
- `RESOURCES.md`: A list of resources which can be explored to ground your teaching in contextual knowledge, or to acquire knowledge and wisdom. Use the format in `SKILL_ROOT/RESOURCES-FORMAT.md`.
- `GLOSSARY.md`: The canonical language the learner has demonstrated they understand. Use the format in `SKILL_ROOT/GLOSSARY-FORMAT.md`.
- `WORKSPACE_ROOT/learning-records/*.md`: A directory of learning records, which capture what the user has learned. These are loosely equivalent to architectural decision records in software development - they capture non-obvious lessons and key insights that may need to be revised later, or drive future sessions. These should be used to calculate the zone of proximal development. They are titled `0001-<dash-case-name>.md`, where the number increments each time. Use the format in `SKILL_ROOT/LEARNING-RECORD-FORMAT.md`.
- `WORKSPACE_ROOT/lessons/*.html`: A directory of lessons. A **lesson** is a single HTML output that teaches one tightly-scoped thing tied to the mission. This is the primary unit of teaching in this workspace.
- `WORKSPACE_ROOT/assets/*`: Reusable **components** shared across lessons. See [Assets](#assets).
- `NOTES.md`: A scratchpad for you to jot down user preferences, or working notes.

## Philosophy

To learn at a deep level, the user needs three things:

- **Knowledge**, captured from high-quality, high-trust resources
- **Skills**, acquired through highly-relevant interactive lessons devised by you, based on the knowledge
- **Wisdom**, which comes from interacting with other learners and practitioners

Before the `RESOURCES.md` is well-populated, your focus should be to find high-quality resources which will help the user acquire knowledge. Never trust your parametric knowledge.

Some topics may require more skills than knowledge. Learning more about theoretical physics might be more knowledge-based. For yoga, more skills-based.

### Fluency vs Storage Strength

You should be careful to split between two types of learning:

- **Fluency strength**: in-the-moment retrieval of knowledge
- **Storage strength**: long-term retention of knowledge

Fluency can give the user an illusory sense of mastery, but storage strength is the real goal. Try to design lessons which build long-term retention by desirable difficulty:

- Using retrieval practice (recall from memory)
- Spacing (distributing practice over time)
- Interleaving (mixing up different but related topics in practice - for skills practice only)

## Lessons

A lesson is the main thing you produce: the unit in which knowledge and skills reach the user. Each lesson is one HTML file, saved to `WORKSPACE_ROOT/lessons/` and titled `0001-<dash-case-name>.html` where the number increments each time.

A lesson should be **beautiful**, with clean, readable typography and layout, since the user will return to these later to review. Think Tufte.

The lesson should be short, and completable very quickly. Learners' working memory is very small, and we need to stay within it. But each lesson should give the user a single tangible win that they can build on. It should be directly tied to the mission, and should be in the user's zone of proximal development.

If possible, open the lesson file for the user by running a CLI command.

Each lesson should link via HTML anchors to other lessons and reference documents.

Each lesson should recommend a primary source for the user to read or watch. This should be the most high-quality, high-trust resource you found on the topic.

Each lesson should contain a reminder to ask followup questions to the agent. The agent is their teacher, and can assist with anything that's unclear.

## Assets

Lessons are built from reusable **components**, stored in `WORKSPACE_ROOT/assets/`: stylesheets, quiz widgets, simulators, diagram helpers, and anything else a second lesson could reuse.

Reuse is the default, not the exception. Before authoring a lesson, read `WORKSPACE_ROOT/assets/` and build from the components already there. When a lesson needs something new and reusable, write it as a component in `WORKSPACE_ROOT/assets/` and link to it; never inline code a future lesson would duplicate.

A shared stylesheet is the first component every workspace earns: every lesson links it, so the lessons look like one consistent course rather than a pile of one-offs. As the workspace grows, so should the component library.

Teaching lessons follow this shared-assets workspace model. Do not apply Visual Explainer's `~/.agent/diagrams/` output location or its requirement that each file be fully self-contained.

## The Mission

Every lesson should be tied into the mission - the reason that the user is interested in learning about the topic.

If the user is unclear about the mission, or the `MISSION.md` is not populated, your first job should be to question the user on why they want to learn this. For a new mission, also establish their prior knowledge or experience, known gaps or misconceptions, constraints and teaching preferences, and observable success criteria. Do not produce a lesson before this small baseline assessment is clear.

Failing to understand the mission will mean knowledge acquisition is not grounded in real-world goals. Lessons will feel too abstract. You will have no way of judging what the user should do next.

Missions may change as the user develops more skills and knowledge. This is normal - make sure to update the `MISSION.md` and add a learning record to capture the change. Confirm with the user before changing the mission.

## Zone Of Proximal Development

Each lesson, the user should always feel as if they are being challenged 'just enough'.

The user may specify an exact thing they want to learn. If they don't, figure out their zone of proximal development by:

- Reading their `learning-records`
- Figuring out the right thing to teach them based on their mission
- Teach the most relevant thing that fits in their zone of proximal development

## Knowledge

Lessons should be designed around a skill the user is going to learn. The knowledge in the lesson should be only what's required to acquire that skill. You teach the knowledge first, then get the user to practice the skills via an interactive feedback loop.

Knowledge should first be gathered from trusted resources. Use `RESOURCES.md` to keep track of them. Lessons should be littered with citations - links to external resources to back up any claim made. This increases the trustworthiness of the lesson.

For acquiring knowledge, difficulty is the enemy. It eats working memory you need for understanding.

## Skills

If knowledge is all about acquisition, skills are about durability and flexibility. Make the knowledge stick.

For skill acquisition, difficulty is the tool. Effortful retrieval is what builds storage strength. Skills should be taught through interactive lessons. There are several tools at your disposal:

From LumenYoung/dotfiles, MIT.

More from LumenYoung/dotfiles