// Use this skill when working on MLXR runtime debugging, log triage, validation discipline, benchmark-backed claims, or deciding whether runtime behavior is strong enough to count as evidence rather than a one-off run.
| name | validation |
| description | Use this skill when working on MLXR runtime debugging, log triage, validation discipline, benchmark-backed claims, or deciding whether runtime behavior is strong enough to count as evidence rather than a one-off run. |
Use this skill for the narrow slice that sits beyond the normal dev loop:
Do not use this skill for the common implementation path. The default loop still lives in AGENTS.md, MEMORY.md, and docs/dev-harness.md.
For real LTX-2.3 fidelity bring-up and stage-local smoke debugging, use the dedicated ltx-fidelity-debugging skill instead of stretching this generic validation overlay.
uv run python scripts/dev.py verifyuv run python scripts/dev.py logs --tail 120scripts/gemini_describe_video.py as an automated semantic cross-check and keep the parsed XML review with the receipt.docs/benchmark-matrix.mddocs/research/09-open-questions-and-validation-plan.mddocs/technical-design.mddocs/research/05-optimization-playbook.mddocs/research/07-ltx-integration-seams.mdComprehensively reviews SwiftUI code for best practices on modern APIs, maintainability, and performance. Use when reading, writing, or reviewing SwiftUI projects.
Use this skill when bringing up a new model family, re-basing an existing family onto the current platform contract, or deciding what belongs in core workflow orchestration versus family or host code.
Design static and light-motion media assets such as posters, slides, cards, flyers, invitations, social graphics, thumbnails, hero images, banners, certificates, README art, and short promo reels. Use when Codex needs to turn text, images, icons, or video into polished layout-driven visuals, especially through a reproducible Python, Pillow, SVG, or ffmpeg workflow.
Use this skill when debugging real LTX-2.3 output quality, running safe manual smoke tests, interpreting stage snapshots, or deciding whether a result is specific enough to count as a clear dog or other visually coherent subject.