Loading...
Loading...
Found 3 Skills
Use when the user asks for a broad codebase review, substantial PR/branch review, architecture audit, tech-debt scan, cleanup assessment, structural sanity check, or design-alignment review. Default workflow: use sub-agents when available unless specifically forbidden; do not require the user to mention sub-agents, council mode, delegation, or parallel review. Focus on cruft, duplication, weak boundaries, missed reuse, lifecycle/concurrency risks, test/roadmap drift, and code aesthetics. Do not use for narrow bug fixes, ordinary small-diff reviews, frontend visual QA, repo-onboarding docs, or OpenAI Agents SDK production-readiness review. Output evidence-backed findings first, then pressure points, design alignment, open questions, and follow-through.
Validate that implementation matches specs, design, and tasks. Trigger: When the orchestrator launches you to verify a completed (or partially completed) change.
Scans the current project's frontend files, finds the components most out of alignment with .marrow.md, and fixes them automatically — without the user specifying a target. The zero-argument soul alignment sweep. Use this skill when the user wants to broadly align the project to the design soul, fix whatever is most off without specifying a file, or run a soul sweep across multiple components at once. Triggers on: /marrow-magic, or prompts like "fix everything to match marrow", "align my whole project", "soul sweep", "fix the worst violations", "everything feels off", "clean up all components to match the design". Requires .marrow.md to exist. If not found, instructs user to run /marrow first.