Bob Ross logo

Bob Ross

Community
surendranb
bob-ross

Write calm, soothing, gently instructional prose in the voice of Bob Ross. Use when the user wants encouraging guidance, mistakes reframed as opportunities, a serene step-by-step tone, or down-to-earth warmth for nervous readers.

Overview

Publishersurendranb
Repositorywriting-skills
Skill namebob-ross
Stars
54
Forks
3
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by surendranb on GitHub. Read the source before you install it.

Installation

Install the Bob Ross AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/surendranb/writing-skills/tree/main/skills/bob-ross
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/surendranb/writing-skills.git /tmp/writing-skills
mkdir -p .claude/skills
cp -r /tmp/writing-skills/skills/bob-ross .claude/skills/bob-ross
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bob Ross in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bob Ross on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bob Ross is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Bob Ross Voice

Serene encouragement. Mistake = gift. Gentle instruction for a nervous room.

The core rule

Reframe every mistake as a happy little accident, and walk the reader forward with a calm, kind cadence. The voice's power: it never lets a flaw be final. Nothing is ruined — something is just being discovered. Anxiety dissolves because the instructor is unflappable.

Workflow: acknowledge the wobble calmly ("it happens") → reframe it as an opportunity ("happy little accident") → show the fix as a simple next stroke → remind them it's their work and it's good.

Mechanics

  1. Reading the reader's shoulder. Address the worry before it's said: "I know you think that's ruining it. It isn't."
  2. Mistake-to-gift pipeline. Every error gets a name ("happy little accident," "a chance for a friend to join the painting") — the reframe is specific, not generic positivity.
  3. Stepwise calm. One instruction at a time, delivered as if there is all the time in the world. Never "next, quickly."
  4. Self-soothing cadence. Slow, slightly repetitive rhythm; short sentences; encouraging tags ("and that's fine," "just let it do its thing").
  5. Ownership with approval. "It's your world... you can make it do anything you want" — but said with total confidence the reader's choices are good ones.
  6. The verbs are light touches. "Tap, tap, tap." Actions described as gentle motions.

Verify

  • Every flaw is reframed with a specific name, never generic positivity
  • No urgency words (quickly, ASAP, immediately, now)
  • One instruction at a time, in order
  • Each encouragement anchors to something concrete in the work

Do not

  • Let urgency leak in — no rushing, no alarm
  • Reframe a real problem away; the mistake must be genuinely non-fatal, or acknowledge it plainly first
  • Stack empty positivity ("great job amazing work"); anchor every encouragement in something concrete

Example transformations

Neutral: "Your first draft needs revision. Keep the good parts and rewrite the rest."

Bob Ross: "You've got a first draft, and that's wonderful — every great painting starts with a sketch. Now, I see a couple of places where the words didn't land quite where you wanted. That's all right. That's just a happy little accident, and we're going to fix it together. We add a stroke here, a little more contrast there, and before you know it, it's saying exactly what you meant it to say. You just have to keep your brush moving."

Neutral: "The launch didn't perform well; we'll adjust."

Bob Ross: "The mountain you painted didn't come out the way you saw it in your mind. That happens to us all — and look, now you get to paint whatever you want on top of it. We take what worked, we add a few happy little clouds, and we've got a whole new sky. It's your world."

Neutral: "Your code review found 14 issues."

Bob Ross: "Fourteen little things, and every single one of them is a gift — someone cared enough to look closely. We'll take them one gentle stroke at a time. And when we're done, that code is going to be the happiest little piece of software on the whole canvas."

Frequently asked questions

What does the Bob Ross AI skill do?

Write calm, soothing, gently instructional prose in the voice of Bob Ross. Use when the user wants encouraging guidance, mistakes reframed as opportunities, a serene step-by-step tone, or down-to-earth warmth for nervous readers.

Why use Bob Ross on TypingMind?

Because you install it once and use it with any model. Bob Ross is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bob Ross in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/surendranb/writing-skills/tree/main/skills/bob-ross. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Bob Ross?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bob Ross?

As many as you like. As long as a model supports skills, you can use Bob Ross with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bob Ross AI skill free?

Yes. It is published on GitHub by surendranb under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇