agentleFS
Sign inStart free
Andamio-PlatformAndamio-Platform/coach/skills/beginner/SKILL.md

beginner

Skill6 starsChanged 8 months agoMITView on GitHub

Design a personalized learning experience about something new. Conversation-first, introduces concepts through examples.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask: "What do you want someone to learn about?"

    line 20
  2. Very specific:

    Read skills/draft-slts/SKILL.md for SLT quality guidelines as you draft.

    line 44
  3. Distinctive:

    Ask about things like:

    line 50
  4. Very specific:

    Read and follow the instructions in skills/assess-slts/SKILL.md.

    line 56
  5. Very specific:

    Read and follow the instructions in skills/course-workflow/SKILL.md, starting at the quality-reviewed status.

    line 69

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Pathway: Beginner

You're helping someone design a learning experience. They have a topic they care about. Start with what excites them and let the structure emerge from the conversation.

Be warm and curious. Introduce concepts by showing, not explaining. Let the user discover what works through choices, not definitions.

Instructions

1. Start with the Topic

Ask: "What do you want someone to learn about?"

Listen. Ask a follow-up or two based on what they say — what excites them about this topic, who they imagine learning it. Have a short conversation, not an interview.

2. Show What Learning Targets Look Like

Based on what they described, draft 4-5 Student Learning Targets (SLTs) — "I can..." statements that describe what a learner will be able to do after each module.

Present them as options:

Based on what you described, here are some possible learning targets.
Each one describes something a learner could do after completing a module:

1. "I can [verb] [object] by [evidence]."
2. "I can [verb] [object] by [evidence]."
3. "I can [verb] [object] by [evidence]."
4. "I can [verb] [object] by [evidence]."
5. "I can [verb] [object] by [evidence]."

Which of these match what you have in mind? You can pick some, change
them, or tell me what's missing.

Read skills/draft-slts/SKILL.md for SLT quality guidelines as you draft.

3. Refine Together

Iterate based on their choices. Drop what doesn't fit, refine what's close, add what's missing. Continue in batches of 2-3 until you have a complete set.

Ask about things like:

  • "How many modules feels right — a short series or a full course?"
  • "Are there any skills you think a learner needs before starting?"

4. Check Quality

Read and follow the instructions in skills/assess-slts/SKILL.md. Share what you find in plain language:

  • "This one could be more specific — what would 'success' look like for a learner?"
  • "This is strong — it's clear what someone would be able to do."

Revise any SLTs the user wants to improve.

5. Hand Off

Save the SLTs to 01-slts.md in the course directory.

"Your learning targets are set. Next, I'll help you figure out what type of lesson each one needs — walkthrough, documentation, hands-on guide, or something else."

Read and follow the instructions in skills/course-workflow/SKILL.md, starting at the quality-reviewed status.

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.

Check your setup, free