Claude commands

Stage changes, generate conventional commit message, commit, and push to current branch. One-shot git add-commit-push.

Run a computer use task on the desktop via Claude's vision and action API

Evaluate and upgrade test suites with TDD/BDD rigor.

Analyze skill execution metrics and identify unstable or underperforming skills.

View recent skill executions with full context and error details.

Audit shell scripts for correctness, safety, and portability.

Expert-level Rust audits for safety and correctness.

Analyze code quality across 6 dimensions (duplication, algorithms, clean code, architecture, errors, style) and apply fixes.

Static-analysis hot-spot review for time and space complexity.

Intensive mathematical analysis for numerical stability and correctness.

Audit Makefiles for best practices and portability.

Active security hardening of the existing codebase, with a report and concrete proposals to apply.

Run a detailed review that picks its dimensions from what the codebase and diff contain.

Systematic bug detection with language-specific expertise.

Principal-level architecture assessment against ADRs and design patterns.

Evaluate public API surfaces against guidelines and exemplars.

Profile Python code for performance bottlenecks using cProfile, memory_profiler, or py-spy.

Analyze Python async code for correctness, patterns, and potential issues.

Analyze Python test suites for quality, coverage, and improvement opportunities.

Provision the oracle ML inference daemon

Reorganize GitHub issue labels into type, priority, and effort groups.

Create a new GitHub issue with formatted description, labels, and optional reference links

Analyze if issues (GitHub/GitLab) can be closed based on commits

View and manage skill execution memories stored by memory-palace.