From orchestrate
Reviews code against project rules and reference files, flagging violations in correctness, security, reliability, architecture, dead code, complexity, and conventions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/orchestrate:reviewingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Review code against curated project rules and flag all violations found — not just things introduced by recent changes.
Review code against curated project rules and flag all violations found — not just things introduced by recent changes.
references/general.mdCLAUDE.md or AGENTS.md at repo root, plus stack-specific files relevant to the scope.references/<dir>.md exists for a top-level directory in scope, load it.Produce a report grouped by category. For each issue: file, location, what's wrong, why, and suggested fix.
npx claudepluginhub haowjy/orchestrate --plugin orchestrateStructured code review that composes validation checklists from relevant atoms based on code changes. Produces severity-ordered report with specific locations and fixes. Activated when user asks for code review.
Performs comprehensive code reviews with automated fixes for Python, TypeScript, JavaScript, Go, Rust projects. Analyzes quality, security, performance, architecture, tests; applies safe fixes and generates reports.
Performs a structured 5-pass code review across correctness, security, performance, readability, and consistency. Invoke via /review on files, directories, or git diffs.