// 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.
Comprehensively 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.
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.
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.
| name | ltx-fidelity-debugging |
| description | 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. |
Use this skill for the narrow slice where the real LTX-2.3 path runs but the output is still visually wrong, ambiguous, or not strong enough to promote into repo truth.
This skill is for:
22B AV pathDo not use this skill for the common implementation path. The default repo loop still lives in AGENTS.md, MEMORY.md, and scripts/dev.py.
docs/research/10-ltx-fidelity-debug-playbook.md.scripts/ltx_debug_smoke.py with a fixed seed and real converted artifacts.safe-smoke, then visual-gate, then coherence.tmux execution for long real-weight smokes.stage1, post_x2, and final snapshots before deciding what to fix next.frame_0001, frame_mid, and frame_last before promoting a rung.docs/research/10-ltx-fidelity-debug-playbook.mddocs/research/07-ltx-integration-seams.mddocs/research/09-open-questions-and-validation-plan.mdMEMORY.mdLoad these code paths only when you need the implementation seam:
packages/families/ltx/src/ltx/_prompt_encoding_backend.pypackages/families/ltx/src/ltx/_generation_backend.pyscripts/ltx_debug_smoke.py