// Commit staged changes, push branch, and create a PR with full pre-flight verification.
| name | commit-push-pr |
| description | Commit staged changes, push branch, and create a PR with full pre-flight verification. |
Streamlined commit → push → PR workflow. Run the full verification sequence first, then ship.
Confirm we are NOT on master: git rev-parse --abbrev-ref HEAD
Run build + test verification:
DOTNET_SYSTEM_GLOBALIZATION_INVARIANT=1 dotnet build Frank.sln
DOTNET_SYSTEM_GLOBALIZATION_INVARIANT=1 dotnet test Frank.sln --filter "FullyQualifiedName!~Sample"
DOTNET_SYSTEM_GLOBALIZATION_INVARIANT=1 dotnet test test/Frank.Tests/
dotnet fantomas --check src/
If any step fails, fix it before proceeding.
git status — review changesgit diff --staged and git diff — review what's going ingit log --oneline master..HEAD — review commit historygit push -u origin HEADgh pr create:
Closes #XX if there's a related issueBreak an issue into tasks so small and precise that each has exactly one correct implementation. Refuses to launch execution until the plan contains actual code shapes, verified file paths, and scope locks. Use before any implementation session.
Use when implementing a milestone with multiple issues. Thesis-first approach: write failing E2E tests before issues, expert-review acceptance criteria before implementation, use dedicated terminal sessions (not subagents), and verify E2E yourself before merging. Includes review cycle that creates follow-up issues when expert review surfaces new gaps.
Use when the user wants to find, catalog, or address technical debt. Also use when starting a cleanup sprint, looking for code quality improvements, or asking "what needs cleaning up?"
Babysit open PRs — auto-rebase, fix CI, address review comments. Use with /loop 5m /babysit for hands-free PR management.
Run Holzmann "Power of Ten" discipline review on changed code. Checks nesting depth, loop bounds, function size, preconditions, mutable state, side effect surfacing, and indirection depth. Use after writing code, before committing, or as part of PR review. Outputs a weighted letter grade (A-F) with stoplight color.
Use when completing a feature, before creating a PR, or when the user asks "what do my experts think?" Dispatches the expert panel as parallel subagents for structured code review from multiple perspectives.