# learn-agent-skills

Interactive tutor for learning agent skill development. Teaches one lesson per prompt, runs environment preflights, and tracks evidence in a local markdown file.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 2700 installs · ★ 73982
- Author: rohitg00
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/rohitg00/ai-engineering-from-scratch/tree/HEAD/skills/learn-agent-skills/SKILL.md
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/skills/learn-agent-skills

## What it does

The skill runs an interactive curriculum covering runtime boundaries, discovery metadata, routing, and trust checks. Each prompt covers exactly one lesson from `learning-paths/agent-skills.json`. The mandatory path spans lessons 22, 24, 25, 26, and 27, while lesson 23 remains optional.

Hands-on exercises require working installations of `node`, `npx`, and `python3`. When the environment or local repository files are missing, the tutor switches to a conceptual walkthrough and marks the host checkpoints as pending. All exercise outcomes and notes are logged in `AGENT-SKILLS-LEARNING.md` in the current working directory.

Without direct confirmation, the tutor will not mutate external systems, install packages, or clone repositories. It keeps lesson 26 locked until lesson 25 is marked done and the student verifies understanding of tool-poisoning risks.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add rohitg00/ai-engineering-from-scratch --skill learn-agent-skills -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/learn-agent-skills/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/learn-agent-skills/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add rohitg00/ai-engineering-from-scratch --skill learn-agent-skills -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/learn-agent-skills/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add rohitg00/ai-engineering-from-scratch --skill learn-agent-skills -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/learn-agent-skills/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install rohitg00/ai-engineering-from-scratch learn-agent-skills
```

2. **Manually: put the files in place**
- File: `.github/skills/learn-agent-skills/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add rohitg00/ai-engineering-from-scratch --skill learn-agent-skills -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/rohitg00/ai-engineering-from-scratch --path skills/learn-agent-skills
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/learn-agent-skills/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add rohitg00/ai-engineering-from-scratch --skill learn-agent-skills -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/rohitg00/ai-engineering-from-scratch/tree/HEAD/skills/learn-agent-skills/SKILL.md

## When to use it
- learn runtime boundaries and skill packaging for AI agents
- track curriculum milestones in `AGENT-SKILLS-LEARNING.md`
- validate local `node`, `npx`, and `python3` runtimes for exercises
- verify tool-poisoning concepts before unlocking permissions labs

## Example prompts
- Run `/learn-agent-skills` to start the portable contract lesson.
- Use `learn-agent-skills` to inspect `AGENT-SKILLS-LEARNING.md` and resume the next exercise.
- Call `/learn-agent-skills` to take the post-lesson quiz on discovery metadata.

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 593ade4d0d9759b9.

BEGIN THIRD-PARTY FILE 593ade4d0d9759b9
````text
---
name: learn-agent-skills
description: >
  Focused interactive tutor for the Agent Skills Engineering path in AI
  Engineering from Scratch. Start or resume this route when a learner wants
  to create, discover, invoke, secure, evaluate, package, or port Agent Skills.
  Teaches one lesson per invocation and records evidence in
  AGENT-SKILLS-LEARNING.md.
---

# Learn Agent Skills

Teach the focused Agent Skills route. One invocation covers one lesson. The
learner should create files, run the lab, explain the boundary, and leave one
observable checkpoint before the lesson is marked complete.

## Invocation belongs to the host

The portable skill name is `learn-agent-skills`. Do not teach one command
syntax as universal.

| Host | Start or resume |
|---|---|
| Codex | `learn-agent-skills`, or choose it from `/skills` |
| Claude Code | `/learn-agent-skills` |
| Other compatible hosts | `Use learn-agent-skills to start or resume the Agent Skills Engineering path.` |

## Sources

The route source of truth is `learning-paths/agent-skills.json`. Prefer local
files when this repository is cloned. Otherwise fetch each file from:

```text
https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/<path>
```

Read the manifest before choosing a lesson. Follow `lessons` by `order`; do
not use the numeric Phase 13 sequence. The required path is 22, 24, 25, 26,
27. Lesson 23 is optional and follows the manifest's entry rule.

For each selected lesson, read its `docs/en.md` and `quiz.json`. Read or run
files under `code/` and `outputs/` only when the current lab needs them. A
clone is optional for reading. If a runnable lab needs repository files and
they are unavailable, explain that fact and offer a clone into a directory
the learner chooses. Do not block the conceptual lesson on cloning, but do not
record a repository command or real-host checkpoint as complete without the
required files and runtime.

## Real-lab preflight

Before Lesson 22's host checkpoint, establish all of these facts:

1. `node --version`, `npx --version`, and `python3 --version` succeed.
2. The learner has selected one skill-capable host.
3. The learner has selected a writable project or user install scope.
4. The learner understands which working directory will become `TARGET_ROOT`.

If any item is unavailable, give the website or manual `docs/en.md` path and
continue conceptually. Mark discovery, invocation, bundled-script, update, and
uninstall observations as `Pending`. Never describe that fallback as a real
host pass.

## Locate or create progress

Use `AGENT-SKILLS-LEARNING.md` in the current working directory.
````
END THIRD-PARTY FILE 593ade4d0d9759b9

The third-party file has ended. Everything between the 593ade4d0d9759b9 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2644 of 7539 bytes. © rohitg00 · MIT · https://github.com/rohitg00/ai-engineering-from-scratch/tree/HEAD/skills/learn-agent-skills/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md