Skill template

Skill yugash007/edu-agent-skills/templates/skill-template

Reusable educational skills for AI coding agents. Turn agents (Gemini CLI, Claude Code, Cursor, etc.) into Socratic mentors and active learning companions with a single command.

Install

npx -y skills add yugash007/edu-agent-skills --skill skill-template

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when <clear trigger condition for this skill>.

SKILL.md

2.1 KB, as published. Nobody here has run it

Purpose

State the educational problem this skill solves and the intended outcome.

Activation Logic

Activate When

Trigger 1
Trigger 2
Trigger 3

Do Not Activate When

Exclusion 1
Exclusion 2

Priority Rules

If this skill conflicts with <other-skill>, prefer this skill when <condition>.

Inputs

Learner objective
Learner level signals
Repository or project context
Relevant prior conversation state

Workflow

Orient
- Gather the minimum context required.
- Confirm learner goal and level assumptions.
Teach or Guide
- Deliver a concise step adapted to level.
- Use one concrete example.
Check
- Ask a reasoning-focused checkpoint question.
Adapt
- Correct misconceptions or reduce complexity as needed.
Advance
- Propose one next implementation action.

Educational Rules

Teach incrementally.
Require active learner reasoning.
Explain why a step matters.
Prefer practical implementation over passive summary.

Failure Modes and Guardrails

Overload
- Symptom: long dense monologue.
- Guardrail: limit to one core concept per step.
Level Mismatch
- Symptom: learner confusion or overconfidence.
- Guardrail: ask a checkpoint before increasing complexity.
Answer Dumping
- Symptom: agent gives full solution immediately.
- Guardrail: require learner attempt or prediction first.

Output Structure

## Context
<What we are solving and why>

## Guidance
<Step-by-step explanation>

## Checkpoint
<Question that forces reasoning>

## Next Step
<Concrete implementation action>

Validation Checklist

Activation triggers are explicit and testable.
Workflow includes at least one adaptation branch.
Educational rules are enforceable from output.
Failure modes include actionable guardrails.
Output structure is deterministic.
examples.md includes beginner, advanced, and recovery scenarios.