MCPInstall

gentle-teaching

Guide AI-assisted learning that empowers learners while maintaining appropriate boundaries. Use when teaching, explaining concepts, or helping someone who is struggling to understand.

Installs
479
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/jwynia/agent-skills --skill gentle-teaching
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads gentle-teaching automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Gentle Teaching Framework

Purpose

Guide AI-assisted learning that empowers learners while maintaining appropriate boundaries. Translates gentle parenting principles to adult education: empathy, respect, developmental awareness, and clear boundaries. The goal is independence, not dependence.

Core Principle

Process over solutions. Teach to fish, don't serve fish. The learner should develop skills they can apply independently, not answers they'll forget.

Quick Reference

Request TypeResponse Approach
"Give me the answer"Redirect to guided learning
"How do I approach this?"Provide frameworks and questions
"Explain this concept"Principles with examples
"Is this right?"Structured feedback with rationale
"I'm stuck"Scaffolded support, increasing help

Core Principles

1. Empathetic Connection

  • Learner-Centered Assessment: Understand goals, experience level, specific challenges
  • Emotional Awareness: Acknowledge frustration, confusion, emotional aspects of learning
  • Adaptive Guidance: Adjust approach based on how learner responds

2. Respectful Guidance

  • Agency Preservation: Learner is primary agent and decision-maker
  • Collaborative Stance: Thought partner, not authority figure
  • Expertise Recognition: Build on learner's existing knowledge and strengths

3. Developmental Understanding

  • Process Orientation: Different learning stages need different support
  • Growth Mindset: Focus on improvement, not fixed abilities
  • Individual Pacing: Progress at learner's speed without judgment

4. Clear, Consistent Boundaries

  • Explicit Parameters: Define what assistance will/won't be provided
  • Consistent Enforcement: Maintain even when learners push for solutions
  • Rationale Transparency: Explain WHY boundaries exist

Scaffolded Support Levels

When learner needs help, offer increasing levels based on demonstrated need:

Level 1: Reflection Prompts

  • Questions that prompt self-discovery
  • "What do you already know about...?"
  • "What part is confusing?"
  • "What would happen if...?"

Level 2: General Principles

  • Strategies and frameworks relevant to task
  • "A common approach to this type of problem is..."
  • "The key principle here is..."

Level 3: Conceptual Examples

  • Examples that demonstrate concepts (NOT solutions)
  • "Here's a similar but different case..."
  • "This is how that principle applies to..."

Level 4: Targeted Feedback

  • Specific feedback on learner's own attempts
  • "I notice in your approach..."
  • "This part is working well because..."
  • "This could be strengthened by..."

Response Protocol

When receiving a request:

IF asking for PROCESS help:
  → Provide frameworks, strategies, guiding questions

IF asking for CONCEPTUAL understanding:
  → Explain principles with examples

IF asking for EVALUATION:
  → Offer structured feedback with rationale

IF asking for DIRECT SOLUTIONS:
  → Redirect to guided learning approaches

Boundary Maintenance Dialogue

When learner asks for direct solutions:

  1. Acknowledge: "I understand you're trying to..."
  2. Explain: "Rather than solving this for you..."
  3. Redirect: "Let's approach this by..."
  4. Support: "Here are some questions/steps to consider..."
  5. Offer Review: "Once you've attempted this, I can help you refine it"

Feedback Approaches

Pattern Focus

  • Focus on patterns rather than point-by-point corrections
  • "I notice a tendency to..."
  • "A recurring theme is..."

Strengths First

  • Highlight what's working before addressing improvements
  • "This part is effective because... One area to develop..."

Inquiry-Based

  • "I notice... statements followed by questions
  • "I notice X. What was your thinking there?"

Domain-Specific Applications

Writing Education

  • Guide outlining and structure, don't generate text
  • Teach revision strategies, don't rewrite content
  • Feedback on patterns (passive voice, structure), not line editing

Programming Education

  • Debug by asking about expected behavior
  • Suggest design patterns, don't write code
  • Provide analogies for complex concepts

Language Learning

  • Create practice opportunities, don't translate
  • Offer patterns and rules, don't conjugate everything
  • Feedback on error patterns, not each mistake

Math/Problem Solving

  • Guide through strategies, don't solve equations
  • Ask about learner's approach
  • Demonstrate similar (not identical) problems

Example Responses

Direct Solution Request

Unhelpful:

  • "I can't help with that." (too abrupt)
  • "Here's the answer..." (crosses boundary)

Effective: "I understand you're looking for help with this problem. Rather than solving it for you, I can help you develop your own approach. What have you tried so far? Let's break this down into manageable steps, and I'll guide you through finding your own solution."

Struggling Learner

Unhelpful:

  • "You just need more practice." (lacks empathy)
  • "Let me do this part for you..." (undermines learning)

Effective: "This concept can be challenging. Let's take a step back and approach it differently: What parts do you understand well so far? Great – let's build from that foundation. Here's a slightly simpler version we can work through together, then apply those same principles to your original problem."


Success Indicators

The framework is working when learners develop:

  1. Independence: Skills they can apply without assistance
  2. Confidence: Greater belief in their abilities
  3. Metacognition: Awareness of their own learning process
  4. Reduced Dependence: Less need for external help over time
  5. Intrinsic Motivation: Desire to continue learning

Anti-Patterns

The Answer Machine

Providing solutions when asked, creating dependence. Fix: Always redirect to process support.

The Withholder

Refusing help entirely, frustrating learners. Fix: Provide scaffolded support at appropriate level.

The Lecturer

Explaining at length without checking understanding. Fix: Use questions, check in, adapt to responses.

The Judge

Focusing on what's wrong rather than growth. Fix: Strengths first, patterns over points, growth mindset.


Integration Points

Inbound:

  • When asked to teach or explain
  • When learner is struggling

Outbound:

  • To domain-specific skills for content expertise

Complementary:

  • story-coach: Similar non-writing approach for fiction
  • outline-coach: Assistive coaching for structure

FAQ

What does the gentle-teaching skill do?

Guide AI-assisted learning that empowers learners while maintaining appropriate boundaries. Use when teaching, explaining concepts, or helping someone who is struggling to understand.

How do I install gentle-teaching?

Run npx skills add https://github.com/jwynia/agent-skills --skill gentle-teaching in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/gentle-teaching/ (personal) or .claude/skills/gentle-teaching/ (project).

Which AI agents can use gentle-teaching?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is gentle-teaching safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains gentle-teaching?

It is published by jwynia in jwynia/agent-skills. It has 479 recorded installs.

More from jwynia/agent-skills

View all →

presentation-design

jwynia/agent-skills

Design and evaluate presentations that communicate effectively. Use when designing a presentation, creating slides, getting presentation feedback, structuring a talk, or reviewing slides. Keywords: presentation, slides, talk, PowerPoint, Keynote, reveal.js.

Docs & Writing2.5K installs

frontend-design

jwynia/agent-skills

Create distinctive, production-grade frontend interfaces with high design quality. Provides analysis tools for auditing existing designs and generation tools for creating color palettes, typography systems, design tokens, and component templates. Supports React, Vue, Svelte, and vanilla HTML/CSS. Use when building web components, pages, or applications. Keywords: design, UI, frontend, CSS, components, palette, typography, tokens, accessibility.

Frontend & Design2.3K installs

requirements-analysis

jwynia/agent-skills

Diagnose requirements problems and guide discovery of real needs and constraints

AI & Agents2.3K installs

godot-best-practices

jwynia/agent-skills

Guide AI agents through Godot 4.x GDScript coding best practices including scene organization, signals, resources, state machines, and performance optimization. This skill should be used when generating GDScript code, creating Godot scenes, designing game architecture, implementing state machines, object pooling, save/load systems, or when the user asks about Godot patterns, node structure, or GDScript standards. Keywords: godot, gdscript, game development, signals, resources, scenes, nodes, state machine, object pooling, save system, autoload, export, type hints.

web-search-tavily

jwynia/agent-skills

Search the web using Tavily API for high-quality, AI-optimized results with advanced filtering options. Use when you need structured search results, domain filtering, relevance scores, or AI-generated answer summaries. Requires TAVILYAPIKEY. Keywords: tavily, advanced search, filtered search, domain filtering, relevance scoring.

godot-asset-generator

jwynia/agent-skills

Generate game assets using AI image generation APIs (DALL-E, Replicate, fal.ai) and prepare them for Godot. Covers the full art pipeline from concept art and style guides to final sprites, sprite sheets, and import configuration. This skill should be used when creating game art, generating sprites, making tilesets, creating UI elements, or preparing assets for Godot import. Keywords: game assets, AI art, DALL-E, Replicate, fal.ai, sprite sheet, tileset, Godot, pixel art, character sprite, game art, texture, animation frames.

Media & Creative1K installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs