Skip to content
Agentmart
Submit a tool

teach

Teach a skill or concept through a persistent workspace of mission-driven lessons, references, resources, practice, and learning records.

Skill by davidbasilefilho

IndexedApache-2.0
Write a review

Chalk Labs

Need help deploying teach?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/davidbasilefilho-teach

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Teach a skill or concept through a persistent workspace of mission-driven lessons, references, resources, practice, and learning records.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/teach

What's inside

Skill name
teach
Description
Teach a skill or concept through a persistent workspace of mission-driven lessons, references, resources, practice, and learning records.
License
Apache-2.0
Instructions
45 lines in SKILL.md · view on GitHub

Files (5)

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

SKILL.md (first lines)

# Teach

Treat current directory as stateful teaching workspace.

## Workspace

- `MISSION.md`: learning purpose; use [MISSION-FORMAT.md](MISSION-FORMAT.md).
- `RESOURCES.md`: trusted sources and communities; use [RESOURCES-FORMAT.md](RESOURCES-FORMAT.md).
- `learning-records/NNNN-name.md`: durable insights and mission changes; use [LEARNING-RECORD-FORMAT.md](LEARNING-RECORD-FORMAT.md).
- `lessons/NNNN-name.html`: short, self-contained lessons.
- `reference/*.html`: printable cheat sheets, algorithms, syntax, poses, glossaries.
- `assets/*`: shared styles, quizzes, simulators, diagram helpers.
- `NOTES.md`: preferences and working notes.

## Principles

Ground every lesson in mission. If mission is unclear or absent, ask why user wants topic before teaching. Confirm mission changes; update `MISSION.md` and add learning record.

Use trusted external sources; never rely only on parametric memory. Build:

- knowledge from high-trust material;
- skills through relevant practice and tight feedback;
- wisdom through real-world communities/practitioners.

Optimize long-term storage, not temporary fluency. Use retrieval practice, spacing, and skill interleaving. For knowledge acquisition, reduce difficulty; for skill retention, add desirable difficulty.

## Lesson Workflow

1. Read mission, records, notes, resources, references, and reusable assets.
2. Choose one mission-relevant task in user's zone of proximal development. If user did not choose, infer from records.
3. Research trusted sources; update `RESOURCES.md`. Cite claims and recommend one primary source.
4. Create next numbered HTML lesson: beautiful, printable, quick, one tangible win, limited working-memory load, linked to related lessons/references, with invitation for questions.
5. Teach required knowledge, then interactive practice with immediate feedback. Quiz answers should have equal word and, when practical, character counts to avoid clues.
6. Open lesson when possible.
7. Capture non-obvious learning in next record; update concise reference material.

## Assets and References

Reuse `assets/` by default. First workspace component should be shared stylesheet. Extract anything a second lesson could reuse; do not duplicate inline code.

References are compressed long-term recall artifacts; maintain consistent glossary terms across every lesson.

For wisdom questions, answer provisionally and recommend a reputable online/offline community. Respect refusal to join.

From davidbasilefilho/codex-skills, Apache-2.0.

More from davidbasilefilho/codex-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 12, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from davidbasilefilho

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get teach running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying teach?

CallGet help
Cite this page

teach skill. Agent Mart. https://agentmart.dev/skills/davidbasilefilho-teach (last updated 2026-10-24)