agentleFS
ChewbaccaRoarsChewbaccaRoars/pathfinder-skills/skills/teach-back/SKILL.md

teach-back

Skill2 starsChanged 8 months agoMITView on GitHub

Helps users teach what they built to others. Generates teaching guides, workshop outlines, and coaches the user on simplifying their explanations. Use when someone wants to train teammates or share knowledge.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    After any build, challenge the user:

    line 18
  2. Distinctive:

    Create a structured guide the user can follow when teaching someone else.

    line 29
  3. Distinctive:

    If the user wants to teach a group, generate a workshop plan:

    line 72
  4. Distinctive:

    If the user is training someone to become a trainer themselves:

    line 105

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Teach Back

Overview

The best way to solidify your learning is to teach it to someone else. This skill helps users become teachers — turning their builds into lessons they can share with teammates.

Keywords: teach, train, workshop, mentor, share knowledge, onboard, explain, guide, train the trainer

How It Works

Step 1 — The Teach-Back Test

After any build, challenge the user:

"You just built something real. Now imagine explaining it to a teammate who's never done this before. How would you describe what this does — no jargon, just plain words?"

Let them try. Then coach them:

  • "That's good — but 'API call' might lose them. What if you said 'it asks another website for information'?"
  • "You skipped the 'why' — lead with why this matters before explaining how it works"
  • "Perfect. That's exactly how you'd explain it in a 5-minute demo."

Step 2 — Generate a Teaching Guide

Create a structured guide the user can follow when teaching someone else.

Format:

## Teaching Guide: [What You're Teaching]
**Audience**: [who this is for]
**Time needed**: [X minutes]
**What they'll walk away with**: [concrete outcome]

### Before You Start
- Make sure they have [prerequisites: Google account, access to X, etc.]
- Open [tool/site] on your screen so you can show them

### The Hook (2 minutes)
[Start with why this matters. Show the pain point they'll recognize.]
"Have you ever had to [painful manual task]? What if I told you we could make that happen automatically?"

### The Demo (5 minutes)
[Walk through the finished product. Show the input, the magic, the output.]
- Show them [step 1]
- Point out [interesting part]
- "See how it just did [X]? That used to take [Y] minutes."

### The Build-Along (10-15 minutes)
[Now they do it themselves, with you guiding.]
1. [Step with exact instructions]
2. [Step with exact instructions]
3. [Pause here — ask if they have questions]
4. [Continue...]

### The "Aha" Moment
[The point where they see it work for the first time.]
"Go ahead and click Run. Watch what happens."
[Let them experience it. Don't explain — let them react.]

### Wrap-Up (3 minutes)
- "You just built [X]. From scratch. In [Y] minutes."
- "Here's what you could customize: [2-3 options]"
- "If you get stuck, [where to get help]"

Step 3 — Workshop Format (for groups)

If the user wants to teach a group, generate a workshop plan:

## Workshop: [Title]
**Duration**: [30/60/90 minutes]
**Group size**: [recommended]
**Skill level**: No prior experience needed

### Pre-Work (send 1 day before)
- [ ] Make sure you have [account/access]
- [ ] Open [URL] and bookmark it
- [ ] Think of one task you do repeatedly that you wish was automated

### Agenda
| Time | Activity | Notes |
|:-----|:---------|:------|
| 0:00 | Welcome + Why This Matters | Share your story. Why did YOU learn this? |
| 0:05 | Live Demo | Show the finished product. Build excitement. |
| 0:10 | Build-Along | Everyone builds together. You lead, they follow. |
| 0:30 | Customize | Each person adapts it to their own use case |
| 0:45 | Show and Tell | 2-3 volunteers share what they customized |
| 0:55 | What's Next | Resources, next session, how to get help |

### Facilitator Tips
- Go slower than you think you need to
- After each step, ask "Is everyone with me?" and actually wait
- When someone gets stuck, walk to their screen — don't shout instructions
- Celebrate every success, no matter how small
- It's okay if people don't finish — they learned something either way

Step 4 — Train the Trainer

If the user is training someone to become a trainer themselves:

"Now that you've taught this, let's prepare [person] to teach it without you."

Generate a "Trainer Handoff Kit":

  • The teaching guide (from Step 2)
  • Common questions and how to answer them
  • Common mistakes learners make and how to help
  • "If they get stuck on X, try Y"
  • A feedback form template to improve the next session

Trigger Phrases

  • "Help me teach this"
  • "I want to train my team"
  • "How do I explain this to someone?"
  • "Create a workshop"
  • "Train the trainer"
  • "Teach back"

Tone

  • Empowering: "You're not just a builder now — you're a teacher"
  • Practical: focus on what actually works in a room full of learners
  • Patient: "Teaching is harder than building. Give yourself grace."
  • Multiplying: "Every person you teach can teach two more"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.