How do I install the Ltx Fidelity Debugging skill?

Run npx skillmds@latest add numman-ali/ltx-fidelity-debugging in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Ltx Fidelity Debugging safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ltx Fidelity Debugging?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ltx Fidelity Debugging free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ltx Fidelity Debugging?

numman-ali (@numman-ali) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ltx Fidelity Debugging by numman-ali

Name: Ltx Fidelity Debugging
Author: numman-ali

Ltx Fidelity Debugging

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.

numman-ali ad194c0 2 files · 2.4 KB Updated Sep 17, 2026

File contents

LTX Fidelity Debugging

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:

real-weight local smoke runs
stage-local visual debugging
safe iteration on the 22B AV path
deciding whether the next suspect is prompt/stage 1, x2/stage 2, or decode/export

Do not use this skill for the common implementation path. The default repo loop still lives in AGENTS.md, MEMORY.md, and scripts/dev.py.

Default workflow

Read docs/research/10-ltx-fidelity-debug-playbook.md.
Use scripts/ltx_debug_smoke.py with a fixed seed and real converted artifacts.
Start with the named profile ladder: safe-smoke, then visual-gate, then coherence.
Keep clean lifecycle on unless you are disproving the lifecycle itself.
Use detached tmux execution for long real-weight smokes.
Inspect stage1, post_x2, and final snapshots before deciding what to fix next.
Review frame_0001, frame_mid, and frame_last before promoting a rung.
Downgrade the claim if the result is ambiguous.

What to load

docs/research/10-ltx-fidelity-debug-playbook.md
docs/research/07-ltx-integration-seams.md
docs/research/09-open-questions-and-validation-plan.md
MEMORY.md

Load these code paths only when you need the implementation seam:

packages/families/ltx/src/ltx/_prompt_encoding_backend.py
packages/families/ltx/src/ltx/_generation_backend.py
scripts/ltx_debug_smoke.py

Rules

Start at the smallest truthful rung, not the highest resolution.
Use real converted artifacts for visual conclusions.
Change one major variable at a time.
Trust stage-local evidence over the final clip when localizing a bug.
Generic quadruped output does not count as dog success.

---name: ltx-fidelity-debuggingdescription: 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.---# LTX Fidelity DebuggingUse 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:- real-weight local smoke runs- stage-local visual debugging- safe iteration on the `22B` AV path- deciding whether the next suspect is prompt/stage 1, x2/stage 2, or decode/exportDo not use this skill for the common implementation path. The default repo loop still lives in `AGENTS.md`, `MEMORY.md`, and `scripts/dev.py`.## Default workflow1. Read `docs/research/10-ltx-fidelity-debug-playbook.md`.2. Use `scripts/ltx_debug_smoke.py` with a fixed seed and real converted artifacts.3. Start with the named profile ladder: `safe-smoke`, then `visual-gate`, then `coherence`.4. Keep clean lifecycle on unless you are disproving the lifecycle itself.5. Use detached `tmux` execution for long real-weight smokes.6. Inspect `stage1`, `post_x2`, and `final` snapshots before deciding what to fix next.7. Review `frame_0001`, `frame_mid`, and `frame_last` before promoting a rung.8. Downgrade the claim if the result is ambiguous.## What to load- `docs/research/10-ltx-fidelity-debug-playbook.md`- `docs/research/07-ltx-integration-seams.md`- `docs/research/09-open-questions-and-validation-plan.md`- `MEMORY.md`Load these code paths only when you need the implementation seam:- `packages/families/ltx/src/ltx/_prompt_encoding_backend.py`- `packages/families/ltx/src/ltx/_generation_backend.py`- `scripts/ltx_debug_smoke.py`## Rules- Start at the smallest truthful rung, not the highest resolution.- Use real converted artifacts for visual conclusions.- Change one major variable at a time.- Trust stage-local evidence over the final clip when localizing a bug.- Generic quadruped output does not count as dog success.

Frequently asked questions