By mikewelsh801
Turns Claude Code into your calm, encouraging painting instructor. Happy little code, happy little accidents.
"We don't make mistakes — just happy little accidents."
A Claude Code plugin that swaps Claude's voice for the calm, encouraging tone of the one and only Bob Ross. Same engineering capability, just delivered with a little more warmth and a lot less panic.
bob-ross output style — Claude still reads files, writes code, runs tests, and reviews diffs the way it always does. It just narrates the work like a gentle painting instructor. Code, comments, and commit messages stay professional; the Bob Ross voice lives in the prose to you./happy-accident slash command — Paste a failing test, a stack trace, or a scary-looking error. Claude will take a breath, reframe what actually happened, put it in proportion, and suggest one concrete next brushstroke. Good for the moments when CI goes red and your blood pressure goes up.Inside a Claude Code session:
/plugin marketplace add https://github.com/MikeWelsh801/Bob-claude.git
/plugin install bob-ross@bob-ross-plugins
Then activate the output style:
/config
Navigate to Output style → pick Bob Ross. Start a new session so the voice takes effect.
Or, set it directly in .claude/settings.local.json:
{
"outputStyle": "bob-ross"
}
If you've cloned this repo and just want to try it:
claude --plugin-dir /path/to/bob_ross
Before:
Reading the file now. The test failed due to a null reference on line 42. Adding a guard.
After:
Let's take a little peek at this file and see what we're working with. Ah — happy little accident here, this value showed up to the party as
nulland the test wasn't quite expecting company. We'll add a gentle guard right there, and she'll be just fine.
keep-coding-instructions: true, so all of Claude Code's normal engineering guidance stays in place. Only the tone changes.Bump version in .claude-plugin/plugin.json and .claude-plugin/marketplace.json, push to main, and users run:
/plugin marketplace update bob-ross-plugins
to pull the newer version.
MIT. Paint whatever you want with it.
Now then — let's get started. We're gonna have a good time.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub mikewelsh801/bob-claude --plugin bob-rossSenior craftsman methodology for AI-assisted development. DDD, Clean Architecture, TDD, and systematic workflows that transform Claude into a disciplined software engineer.
Delegation system with workflow orchestration, specialized agents, and parallel execution for Claude Code
AlgoKiller — ARM64 trace evidence analysis & cipher algorithm recovery. Bundles the AlgoKiller methodology as skills + a local MCP server (28 tools) that drives the native ak_search engine over GB-scale trace files. v1.2.0 adds two trace tools targeted at OLLVM-flattened binaries — `trace_function` (PC-level invocation analyzer with depth-counter ret boundary, replaces manual trace_search + trace_context loop for stripped helpers) and `trace_immseq` (anchor-driven prev_reg sequence extraction, recovers table-consumption order from jump-table-dispatcher functions). Formalizes R9 (`regN=X -> regN=Y` prev/new semantics — single most common LLM misread in obfuscated code) and FIX #8 (algorithm-name claims require trace_cryptoinstr/trace_constscan/trace_immseq/trace_function fingerprint corroboration before conclude(>=medium)). Loosens five over-strict gates: trace_search limit 100→500, B2 same-args rule exempts hint-driven fallback paths, cross-session [H<n>] references become non-blocking warnings instead of hard errors. Tests 128 → 149 PASS.
Long-term memory for Claude Code. Recalls architecture, conventions, and decisions across sessions — so Claude explains your codebase without file traversal, follows your patterns, and never re-asks what it already learned.