Get a brutally honest review of your project from the perspective of a principal AI engineer. Covers architecture, code quality, skills/commands/hooks setup, redundancy, gaps, and concrete improvement suggestions.
Generate architecture documentation — from a quick Mermaid diagram to full system overview with data flow, component relationships, and architecture decision records (ADRs).
Explain a git diff or branch comparison in plain language. Describes the intent behind changes, not just what files were modified. Useful for MR reviews and catching up.
Explain code functionality — from high-level overview to line-by-line analysis. Useful for onboarding, knowledge transfer, and understanding unfamiliar code.
Test LLM prompts against sample inputs. Shows outputs, checks for regressions when prompts change, and compares different prompt versions side-by-side.
Refactor internals without changing public API. Fixes structural problems (long functions, duplication, poor naming) while keeping the external interface identical.
Check if focused repositories are up to date with the remote. Fetches latest changes and warns about repos that are behind or have uncommitted changes.
Show available skills, agents, and commands — and recommend which to use based on the current repo and task. Helps new users discover what capabilities are available.
Runs before the agent uses a tool for Bash, Bash, Edit, Write, Edit, Write, Read and Bash tool calls, executing commit-size-guard.sh, branch-guard.sh and skill-suggest.sh via bash with --include (4 commands). From Benkapner/claude-code-basecamp.
Use when the user asks to design, plan, or explore approaches before implementing — creating features, building components, or adding functionality that would benefit from design exploration first.