layer-video-fixes — Claude Code skill for video repair
The layer-video-fixes Claude Code skill repairs specific defects in Layer video clips instead of generating them again. It handles requests to extend a shot, replace a subject, change lighting, or improve image quality.
MIT 1,100 installs ★ 10 updated 2026-09-30
npx skills add layerai/skills --skill layer-video-fixes -a claude-codeWhat layer-video-fixes does
The skill routes a clip to a Layer repair use case, such as extending or inserting footage, swapping an object or character, transferring motion, relighting, interpolation, upscaling, denoising, deblurring, or converting SDR to HDR. It uses list_base_models to find a model and get_base_model to read that model’s accepted input slots.
The original file_id remains the master source. Independent fixes start from it, while upscaling comes last because chained edits compound detail loss. Set keep_audio: true to carry sound through a repair. Inserts, extensions, and interpolation can change clip length. The skill estimates the cost before execution and waits for approval above 20 CUs.
What it helps with
- extend a shot whose action ends too early
- replace an incorrect object or character in a clip
- smooth motion or create a slow-motion segment
- reduce grain or motion blur in footage
- convert an SDR master to HDR
Example prompts for the agent
- Extend the clip with
file_idabc123; the action ends too soon. - Replace the object in the clip with
file_idabc123while keeping the motion and scene. - Remove noise from the clip with
file_idabc123and preserve its audio.
How to install layer-video-fixes
1Skills CLI (Vercel)
npx skills add layerai/skills --skill layer-video-fixes -a claude-code2Manually: put the files in place
~/.claude/skills/layer-video-fixes/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/layer-video-fixes/
1Skills CLI (Vercel)
npx skills add layerai/skills --skill layer-video-fixes -a codex2Manually: put the files in place
.agents/skills/layer-video-fixes/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add layerai/skills --skill layer-video-fixes -a cursor2Manually: put the files in place
.cursor/skills/layer-video-fixes/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install layerai/skills plugins/layer/skills/layer-video-fixes2Manually: put the files in place
.github/skills/layer-video-fixes/SKILL.md1Skills CLI (Vercel)
npx skills add layerai/skills --skill layer-video-fixes -a gemini-cli2Platform CLI
gemini skills install https://github.com/layerai/skills --path plugins/layer/skills/layer-video-fixesManually: put the files in place
.devin/skills/layer-video-fixes/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add layerai/skills --skill layer-video-fixes -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about layer-video-fixes
How do I install layer-video-fixes in Claude Code?
Run npx skills add layerai/skills --skill layer-video-fixes -a claude-code. The skill file is at ~/.claude/skills/layer-video-fixes/SKILL.md.
What does layer-video-fixes do?
It selects a Layer workflow for a specific video repair, such as extending a clip, replacing an object, adjusting lighting, or increasing resolution. The skill reads the chosen model’s input schema before using it.
How does the skill handle several video fixes?
It applies independent fixes to the original file_id to limit cumulative detail loss. Upscaling comes after the other edits.
Source text
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