Skip to content
Back to search

alvarmethod

One-to-one AI teaching skills (Alvar method) for Codex, Claude Code, Grok, Pi, and OpenCode

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/vasanthsreeram--alvarmethod/badge.svg)](/listings/vasanthsreeram--alvarmethod)

HTML

<a href="/listings/vasanthsreeram--alvarmethod"><img src="/api/listings/vasanthsreeram--alvarmethod/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

`npx skills` (preferred)

The [open skills CLI](https://github.com/vercel-labs/skills). Discovers every `skills/*/SKILL.md` in this repo.

# global, every detected agent, no prompts
npx skills add vasanthsreeram/Alvarmethod -g --all

# list what’s in the pack
npx skills add vasanthsreeram/Alvarmethod --list

# one skill
npx skills add vasanthsreeram/Alvarmethod --skill teach -g -y

# one harness
npx skills add vasanthsreeram/Alvarmethod -g -y -a claude-code -a grok -a pi -a opencode -a codex

Update later:

npx skills update -g

`npx` this repo

No extra CLI — runs [`install.sh`](install.sh) from GitHub:

npx github:vasanthsreeram/Alvarmethod
npx github:vasanthsreeram/Alvarmethod --list
npx github:vasanthsreeram/Alvarmethod --claude --grok

Clone

git clone https://github.com/vasanthsreeram/Alvarmethod.git
cd Alvarmethod
./install.sh          # all known agent dirs
./install.sh --project
./install.sh --uninstall

| Agent | Global path | |-------|-------------| | Codex | `~/.codex/skills` + `~/.agents/skills` | | Claude Code | `~/.claude/skills` | | Grok | `~/.grok/skills` | | Pi | `~/.pi/agent/skills` | | OpenCode | `~/.config/opencode/skills` |

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 160 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <img src="docs/assets/banner.svg" alt="Alvarmethod — probe, plan, teach" width="960" />
  3. </p>
  4. <p align="center">
  5. <strong>One teacher. One mind.</strong><br/>
  6. Portable agent skills that run Eero Alvar’s AI learning loop.
  7. </p>
  8. <p align="center">
  9. <a href="https://github.com/vasanthsreeram/Alvarmethod/stargazers"><img src="https://img.shields.io/github/stars/vasanthsreeram/Alvarmethod?style=flat-square&color=c9a227" alt="stars" /></a>
  10. <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-2d6a4f?style=flat-square" alt="MIT" /></a>
  11. <a href="https://agentskills.io"><img src="https://img.shields.io/badge/Agent%20Skills-SKILL.md-111827?style=flat-square" alt="Agent Skills" /></a>
  12. <a href="https://youtu.be/kzcI5F4tGiU"><img src="https://img.shields.io/badge/method-Eero%20Alvar-b45309?style=flat-square" alt="Eero Alvar" /></a>
  13. </p>
  14. ```bash
  15. npx skills add vasanthsreeram/Alvarmethod -g --all
  16. ```
  17. That’s the install. Works in **Claude Code**, **Codex**, **Grok**, **Pi**, **OpenCode**, Cursor, and the rest of the [skills CLI](https://skills.sh) agents.
  18. Then open a **learning folder** (not this repo) and say:
  19. ```text
  20. /teach I want a solid introduction to <topic>
  21. ```
  22. You should get a **quiz picker** (not A/B/C/D in chat) → a mermaid DAG → **one** reasoning step → a lock-in quiz.
  23. ---
  24. ## Quick install
  25. ### `npx skills` (preferred)
  26. The [open skills CLI](https://github.com/vercel-labs/skills). Discovers every `skills/*/SKILL.md` in this repo.
  27. ```bash
  28. # global, every detected agent, no prompts
  29. npx skills add vasanthsreeram/Alvarmethod -g --all
  30. # list what’s in the pack
  31. npx skills add vasanthsreeram/Alvarmethod --list
  32. # one skill
  33. npx skills add vasanthsreeram/Alvarmethod --skill teach -g -y
  34. # one harness
  35. npx skills add vasanthsreeram/Alvarmethod -g -y -a claude-code -a grok -a pi -a opencode -a codex
  36. ```
  37. Update later:
  38. ```bash
  39. npx skills update -g
  40. ```
  41. ### `npx` this repo
  42. No extra CLI — runs [`install.sh`](install.sh) from GitHub:
  43. ```bash
  44. npx github:vasanthsreeram/Alvarmethod
  45. npx github:vasanthsreeram/Alvarmethod --list
  46. npx github:vasanthsreeram/Alvarmethod --claude --grok
  47. ```
  48. ### Clone
  49. ```bash
  50. git clone https://github.com/vasanthsreeram/Alvarmethod.git
  51. cd Alvarmethod
  52. ./install.sh # all known agent dirs
  53. ./install.sh --project
  54. ./install.sh --uninstall
  55. ```
  56. | Agent | Global path |
  57. |-------|-------------|
  58. | Codex | `~/.codex/skills` + `~/.agents/skills` |
  59. | Claude Code | `~/.claude/skills` |
  60. | Grok | `~/.grok/skills` |
  61. | Pi | `~/.pi/agent/skills` |
  62. | OpenCode | `~/.config/opencode/skills` |
  63. ---
  64. ## The method
  65. Credit: **[Eero Alvar — *How I Use AI to Learn Things*](https://youtu.be/kzcI5F4tGiU)** (2026-08-14). This pack implements that loop as Agent Skills. It is not his original Pi quiz / Obsidian setup. Captions: [`source/eero-alvar-how-i-use-ai-to-learn-things.md`](source/eero-alvar-how-i-use-ai-to-learn-things.md).
  66. Many-to-many learning leaks:
  67. | Direction | Waste |
  68. |-----------|--------|
  69. | One outlet → many students | Never fitted to *your* edge |
  70. | One student → many outlets | Switching cost + the brain hedges on sources it does not trust |
  71. Fix: **one interface, many sources.** Trust is engineered (verify). Struggle stays in the material. The system eats logistics.
  72. ```mermaid
  73. flowchart LR
  74. A[Probe<br/>edge of this mind] --> B[Plan<br/>mermaid DAG]
  75. B --> C[Teach<br/>one node]
  76. C --> D[Lock-in quiz]
  77. D -->|pass| C
  78. D -->|fail| E[Insert prereq]
  79. E --> C
  80. ```
  81. 1. **Probe** — graded MCQ in the harness picker, start wide, binary-search every strand
  82. 2. **Plan** — mermaid DAG for *this* mind, shown *before* teaching
  83. 3. **Teach** — one reasoning step, picture if needed, quiz, next node
  84. ---
  85. ## Skills
  86. | Skill | Job |
  87. |-------|-----|
  88. | `teach` | Full loop: probe → plan → one-step teaching |
  89. | `probe` | Understanding map only |
  90. | `learn-profile` | Write `.alvar/LEARNER.md` |
  91. | `learn-visual` | One SVG, look at it, fix it |
  92. | `learn-verify` | Fact-check a claim before it is taught as fact |
  93. Quizzes **must** use the native picker:
  94. | Agent | Tool |
  95. |-------|------|
  96. | Grok / Codex | `ask_user_question` |
  97. | Claude Code | `AskUserQuestion` |
  98. | OpenCode | `question` |
  99. | Pi | `quiz` / `ask_user` / `askUserQuestion` |
  100. If the agent pastes A/B/C/D, say **“use the quiz tool.”** If it dumps a textbook, say **“one node only.”**
  101. Session files land in the learning folder:
  102. ```text
  103. .alvar/LEARNER.md
  104. .alvar/maps/<topic>.md
  105. .alvar/sessions/<date>-<topic>.md
  106. .alvar/visuals/…
  107. ```
  108. Point Obsidian at `.alvar/` if you want LaTeX preview.
  109. ---
  110. ## Contributing
  111. See [CONTRIBUTING.md](CONTRIBUTING.md). Edit skills **here**, then reinstall. Don’t patch the copies under `~/.claude` / `~/.grok`.
  112. ## License
  113. MIT for the skills, installer, and docs.
  114. The video and spoken method are **Eero Alvar’s**. Watch the original: [youtu.be/kzcI5F4tGiU](https://youtu.be/kzcI5F4tGiU).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.