layer-video-fixes — скилл для Claude Code: правка видео
Скилл layer-video-fixes для Claude Code исправляет отдельные дефекты видео на Layer без повторной генерации клипа. Он продлевает ролик, заменяет объект или персонажа, меняет свет и улучшает качество изображения.
MIT 1 100 установок ★ 10 обновлён 2026-09-30
npx skills add layerai/skills --skill layer-video-fixes -a claude-codeЧто делает layer-video-fixes
Скилл подбирает сценарий Layer под конкретный дефект: продление или вставку фрагмента, замену объекта или персонажа, перенос движения, коррекцию света, интерполяцию, апскейл, шумоподавление, повышение резкости и конвертацию SDR в HDR. Для выбора модели используются list_base_models и get_base_model; входные слоты нужно брать из схемы выбранной модели.
Исходный file_id служит мастер-копией. Независимые исправления выполняются от неё, а апскейл идёт последним: последовательные правки накапливают потерю деталей. Для звука используется keep_audio: true; длительность ролика может измениться после вставки, продления или интерполяции. Перед запуском скилл предлагает оценить стоимость, а расходы выше 20 CUs требуют подтверждения.
Какие задачи решает
- продлить клип, в котором обрезалось действие
- заменить неверный предмет или персонажа в кадре
- сгладить движение или сделать замедленный фрагмент
- убрать шум, размытие или нехватку разрешения
- перевести видео из SDR в HDR
Примеры запросов агенту
- Продли клип с
file_idabc123: действие обрывается в конце. - Замени предмет в кадре на
file_idabc123, сохранив движение и остальную сцену. - Убери шум в клипе с
file_idabc123и оставь исходный звук.
Как установить layer-video-fixes
1Через Skills CLI (Vercel)
npx skills add layerai/skills --skill layer-video-fixes -a claude-code2Вручную: положить файлы
~/.claude/skills/layer-video-fixes/SKILL.mdПапка скилла целиком; для одного проекта — .claude/skills/layer-video-fixes/
1Через Skills CLI (Vercel)
npx skills add layerai/skills --skill layer-video-fixes -a codex2Вручную: положить файлы
.agents/skills/layer-video-fixes/SKILL.mdДля всех проектов — ~/.agents/skills/
1Через Skills CLI (Vercel)
npx skills add layerai/skills --skill layer-video-fixes -a cursor2Вручную: положить файлы
.cursor/skills/layer-video-fixes/SKILL.mdCursor читает и .agents/skills/, и .claude/skills/
1GitHub CLI
gh skill install layerai/skills plugins/layer/skills/layer-video-fixes2Вручную: положить файлы
.github/skills/layer-video-fixes/SKILL.md1Через Skills CLI (Vercel)
npx skills add layerai/skills --skill layer-video-fixes -a gemini-cli2Командой платформы
gemini skills install https://github.com/layerai/skills --path plugins/layer/skills/layer-video-fixesВручную: положить файлы
.devin/skills/layer-video-fixes/SKILL.mdСтарый путь .windsurf/skills/ тоже читается
Через Skills CLI (Vercel)
npx skills add layerai/skills --skill layer-video-fixes -a opencodeClaude.ai
Упакуйте папку в zip и загрузите в Settings → Capabilities → Skills
По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов
Вопросы о layer-video-fixes
Как установить layer-video-fixes в Claude Code?
Выполни npx skills add layerai/skills --skill layer-video-fixes -a claude-code. Файл скилла находится по пути ~/.claude/skills/layer-video-fixes/SKILL.md.
Что делает layer-video-fixes?
Скилл исправляет отдельные дефекты видео через сценарии Layer: например, продлевает клип, меняет объект, корректирует свет или увеличивает разрешение. Он выбирает модель под нужный тип правки.
Как скилл сохраняет исходное видео при нескольких правках?
Независимые исправления выполняются от исходного file_id, чтобы не накапливать потерю деталей. Апскейл выполняется после остальных правок.
Исходный текст
SKILL.md · MIT
---
name: layer-video-fixes
description: "Use when a generated or supplied clip on Layer is nearly right and should be repaired, not rerolled: extending it, inserting into it, swapping an object or a character, transferring motion, relighting, smoothing motion or making slow motion, upscaling, denoising, deblurring, or converting to HDR. Keywords: fix video, extend clip, swap character, motion transfer, relight, interpolation, slow motion, frame rate, upscale video, denoise, deblur, HDR."
license: MIT
---
# Layer Video Fixes
## Overview
A clip that is 90 percent right is worth more than a fresh roll. Rerolling throws away the motion,
the timing and the performance that already work, and buys a new set of problems. Layer exposes a
use case for most single defects, so the job is to name the defect, pick the use case that fixes only
that, and leave everything else as it was.
Generating a clip from scratch is `layer-video`; cutting finished clips together is
`layer-video-timeline`. The loop, the spend gate and polling are in the `layer` skill.
If a sibling skill named here is missing from your available skills, ask the user to install it
(`npx skills add layerai/skills --skill <name>`); unattended, proceed from tool schemas and flag the
gap.
## Quick reference
Each route is `list_base_models` with `filter.use_case` set as below; take the first result.
| Symptom | `use_case` |
| ----------------------------------------------- | ---------------------- |
| Clip ends too soon, action is cut off | `video_extend` |
| A moment is missing in the middle | `insert_video` |
| One element is wrong (colour, prop, background) | `video_editing` |
| The wrong object is in shot | `video_object_swap` |
| The wrong character, or an off-model one | `video_character_swap` |
| Right performance, wrong subject | `motion_transfer` |
| Lighting fights the scene it is cut into | `relight_video` |
| Motion stutters, or the shot needs slow motion | `video_interpolation` |
| Too small for delivery | `upscaling` |
| Grain or compression noise | `denoise_video` |
| Soft or motion-blurred | `deblur_video` |
| Standard range master needed as HDR | `sdr_to_hdr_video` |
## Read the model before the first call
These models disagree about inputs more than generation models do. The schema does not fix which
guidance slot a repair model reads the source clip from (`init_video` or `reference_video`), nor
where a replacement subject goes (`reference_image`, `face`, or an `element_*` type). Call
`get_base_model` on the chosen model and use the slots it lists; never assume one because another
model took it. When a fix needs two inputs at once, narrow the search with
`filter.guidance_file_types`, for example `["init_video", "reference_image"]`, which keeps only
models that accept both.
Guidance files are `{file_id, type}` objects in `guidance_files`. A clip from an earlier run already
has a `file_id`; pass it directly. Upload only footage that is local, with `request_file_upload_url`.
## Repair from the original
Every pass through a model costs detail. Three fixes chained on each other look worse than three
fixes each made from the source, and the losses compound in faces and fine texture first. Keep the
original `file_id` as the master, apply each fix to the master where the fixes are independent, and
chain only when a later fix genuinely needs the earlier result (upscale last, after the content is
settled, since an upscale of a clip you then edit is wasted).
To fix only part of a clip (slow motion on the last two seconds), cut that span out first with a
`render_video_timeline` edit (`start_from_in_seconds` and `duration_in_frames`, `layer-video-timeline`),
then repair the cut file.
## Sound, length and frame rate
- **Sound.** Set `keep_audio: true` to carry the source's audio through a fix. Without it, assume
the output may be silent, and check before delivering.
- **Length.** Extensions, inserts and interpolation change a clip's duration, and some swaps do too.
Report the new length to the user, especially when the clip sits in an edit cut to music. An
interpolated slow-motion shot is longer by design; a swap that came back shorter is a defect.
- **Frame rate.** `fps` is honoured only by the models that take it (`get_base_model` says so). Ask
for interpolation to reach a target rate rather than generating at one the model ignores.
- **Size.** For a reframe, pass both `width` and `height`. With either one missing and a source
attached, the output geometry is taken from the source file.
For an upscale, `upscale_ratio` sets the factor (2.0, 4.0). `creativity` and `resemblance` trade
invented detail against fidelity; keep resemblance high on footage with faces or text.
## Pricing
The forge guide prices a video edit by its source's length and an upscale by its source's
dimensions. An estimate without the source attached prices a different run, so pass
`estimate_forge_price` exactly the inputs `execute_forge` will get. Several fixes on clips of
different lengths are several estimates, never the first one multiplied. Sum the job and ask before
spending above 20 CUs.
## Worked example
"The hero's 6-second clip is perfect except the sword turned into a staff halfway through. Also make
it 4K for the trailer."
1. The clip is a previous run's output, so it has a `file_id`. Keep it as the master.
2. Defect one is a wrong object: `list_base_models` with `filter.use_case: "video_object_swap"`.
Take the first result and call `get_base_model` for its source slot and replacement slot.
3. Defect two is size: `list_base_models` with `filter.use_case: "upscaling"` and
`filter.modality: "video"`; `get_base_model` for its slot and ratio limits.
4. Price both before running either: `estimate_forge_price` for the swap with the master attached in
its listed slot, the approved sword still as the replacement, `keep_audio: true`, and a prompt
naming only the change: "Replace the staff in the hero's right hand with the approved longsword.
Keep the motion, the timing and everything else unchanged." Then estimate the upscale with
`upscale_ratio: 2.0` against a 6-second source. Present the total; above 20 CUs wait for a yes.
5. `execute_forge` the swap; poll `get_forge_run` at `poll_interval_seconds`. Check the length is
still 6 seconds and the sword holds across every frame.
6. Upscale the swap's output (`file_id` from step 5), the one fix that must come last. Poll, then
report both `file_id` values and any change in length.
## Common mistakes
- Rerolling a clip whose only defect a single use case could fix.
- Assuming the source slot instead of reading it from `get_base_model`.
- Chaining independent fixes off each other instead of each off the master.
- Upscaling first, then editing the upscaled clip.
- Losing the soundtrack by leaving `keep_audio` unset.
- Delivering a fixed clip without saying its length changed.
- Pricing several fixes from one estimate when their sources differ in length or size.
- Prompting a repair with a full scene description instead of only the change.
© layerai · MIT · layerai/skills