Personal best practices, development environment standards, voice/style guidelines, and tooling patterns for Andrew Bolster's Claude Code sessions.
Data verification hierarchy and quality standards — never fabricate, use placeholders over invented data
Andrew Bolster's development environment — toolchain, aliases, shell setup, and key patterns
Correct git co-authorship attribution — always verify the running model from environment context, never hardcode
Kill processes holding a port using lsof — safe, targeted process management patterns
Convert Office/PDF/binary files to markdown using markitdown via uvx
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.
Personal best practices, development environment standards, voice/style guidelines, and tooling patterns for Andrew Bolster's Claude Code sessions.
These skills are non-work-specific and safe to use in any context.
uv-runPython script execution standards. Enforces uv run over bare python/python3 everywhere — Bash tool calls, Makefiles, command files. Includes the UV script frontmatter template and a Click CLI scaffold.
/bolster:uv-run
markitdownConvert files (PDF, DOCX, PPTX, XLSX, email) to markdown using markitdown via uvx. Covers supported formats, when to use it, and output conventions.
/bolster:markitdown
lsof-patternsFind and kill processes by port. One-liner patterns for graceful and force-kill, multiple ports, and safe port-reuse in dev workflows.
/bolster:lsof-patterns
git-attributionCorrect Claude co-authorship attribution in git commits. Check the running model name from environment context, never hardcode it. Covers heredoc commit message format and fallback to generic "Claude" when uncertain.
/bolster:git-attribution
dev-environmentFull development toolchain reference: yadm, zsh/Oh My Zsh/Starship, Neovim/LazyVim, tmux/byobu, mamba/miniforge3, bun, uv, bob. Key aliases, PATH order on macOS, and anti-patterns (never search the whole home directory).
/bolster:dev-environment
voice-styleAndrew Bolster's authentic writing voice — dry humor, technical precision, honest self-reflection, no corporate speak. Covers formatting principles for weeknotes and blog posts, content priority order, and failure writing guidelines.
/bolster:voice-style
data-verificationData quality hierarchy and verification standards before publishing any content. Tool outputs > user-provided > verified citations > placeholders > never fabricate. URL and timeline verification patterns, quality checklist.
/bolster:data-verification
cd plugins/bolster
claude plugin validate .
npx claudepluginhub bd-vitalstatistix/claude-marketplace --plugin bolsterFeature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
AI-powered development tools for code review, research, design, and workflow automation.