agentsclimarketplace

Teach

Skill arendon1/agent-skills/process/teach

A curated collection of autonomous AI agent skills powered by Vercel's `skills` npm cli package. Specialized tools for productivity, document management, and custom LLM workflows.

Install
npx -y skills add arendon1/agent-skills --skill teach

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Teach the user a new skill or concept over multiple sessions, using the current directory as a stateful teaching workspace. Build exercises, check understanding, adapt pace to the learner. Use when the user wants to learn something, not build something, or says "teach me", "I want to learn", "explain over time", "help me understand", "course on", "tutorial".

SKILL.md

5.2 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it

teach — stateful multi-session teaching

Teach the user a concept over multiple sessions. The current directory is a stateful teaching workspace — the state of their learning is captured in files there. Build exercises, check understanding, adapt pace to the learner.

This skill is for learning, not building. If the user wants to build something, route to grill / plan / build instead.

OWNERSHIP

Owns: the teaching workspace files (MISSION.md, RESOURCES.md, learning-records/, lessons/, reference/, NOTES.md). Reads: CONTEXT.md if it exists (for canonical terms in the teaching domain). MUST NOT write plan artifacts. Teaching workspace is separate from plan artifacts.

WHEN (user-invoked)

  • User says "teach me", "I want to learn", "explain over time", "help me understand", "course on", "tutorial".
  • User wants to learn a concept, not build something.

THE TEACHING WORKSPACE

Treat the current directory as a teaching workspace. State is captured in:

  • MISSION.md — the reason the user is interested in the topic. Grounds all teaching.
  • ./reference/* — reference materials: compressed learnings, cheat sheets, reference algorithms, syntax, glossaries. The raw units of learning. Beautiful documents that print well and are designed for quick reference.
  • RESOURCES.md — a list of resources to ground teaching in contextual knowledge, or to acquire knowledge/wisdom.
  • ./learning-records/*.md — learning records, capturing what the user has learned. Loosely equivalent to ADRs — non-obvious lessons and key insights that may need revision later, or drive future sessions. Used to calculate the zone of proximal development. Titled 0001-<slug>.md, incrementing.
  • ./lessons/* — lessons. A lesson is a single, self-contained output that teaches one tightly-scoped thing tied to the mission. The primary unit of teaching.
  • NOTES.md — scratchpad for user preferences and working notes.

Create files lazily — only when you have something to write.

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 you devise, based on the knowledge.
  • Wisdom, which comes from interacting with other learners and practitioners.

Before RESOURCES.md is well-populated, your focus is to find high-quality resources. NEVER trust your parametric knowledge alone — find sources and cite them (invoke the research loop if external knowledge is needed). Some topics need more skills than knowledge (theoretical physics = knowledge-heavy; yoga = skills-heavy).

Fluency vs storage strength

Split between two types of learning:

  • Fluency strength — in-the-moment retrieval.
  • Storage strength — long-term retention.

Fluency gives an illusory sense of mastery, but storage strength is the real goal. Design lessons that build long-term retention by desirable difficulty:

  • Retrieval practice (recall from memory).
  • Spacing (distribute practice over time).
  • Interleaving (mix related topics in practice — 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 self-contained file, saved to ./lessons/ and titled 0001-<slug>.<ext> where the number increments each time.

Lesson design

  • Tightly scoped to one thing tied to the mission.
  • Interactive — the user does, not just reads.
  • Checks understanding (retrieval practice).
  • Adapts to the learner's pace (use learning-records/ to find the zone of proximal development).
  • Builds storage strength, not just fluency.

SESSION FLOW

  1. Read MISSION.md + the latest learning-records/ to recall where the learner is.
  2. Decide the next lesson (or continue an in-progress one) based on the zone of proximal development.
  3. If RESOURCES.md is thin, prioritize finding high-quality resources (via research) before teaching.
  4. Deliver the lesson. Check understanding. Record insights in a new learning-records/ entry.
  5. Update NOTES.md with any preferences observed.

BOUNDARIES

  • MUST treat the current directory as a stateful teaching workspace.
  • MUST NOT trust parametric knowledge alone — find and cite sources (via research).
  • MUST design for storage strength, not just fluency.
  • MUST create files lazily — only when there's something to write.
  • MUST check understanding with retrieval practice.
  • MUST adapt pace to the learner (zone of proximal development).
  • MUST NOT write plan artifacts. Teaching workspace is separate.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 1 of the 12 instructions most learn study skills give in ~1.1k tokens

Counted across 546 of the 573 authors here whose files we hold, read 2026-08-07

  • Calculate the zone of proximal development before teachingin 25 of 546, across 8 files
  • Produce self-contained HTML lessonsin 24 of 546, across 8 files
  • Record user preferences in a notes filein 23 of 546, across 5 files
  • Maintain a teaching workspace in the current directoryin 21 of 546, across 4 files
  • Find high-quality resources before writing lessonshere, and in 19 of 546, across 5 files
  • Make lessons beautiful, short, and quickly completablein 19 of 546, across 3 files
  • Create reusable components for lessonsin 19 of 546, across 5 files
  • Create compressed reference documents for quick lookupin 19 of 546, across 3 files
  • Update the mission file and records upon mission changesin 16 of 546, across 2 files
  • Set min_dist to 0.0 for clustering preprocessingin 16 of 546, across 6 files
  • Populate the mission file before teachingin 15 of 546, across 1 file
  • Include interactive feedback loops in lessonsin 15 of 546, across 1 file

Said here and by no other author read

  • read mission and learning records before a session
  • find and cite sources
  • check understanding with retrieval practice
  • record insights in a new learning record
  • update notes with observed preferences

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 327,069. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.