Communitygithub.com

FilippTrigub/abra

>- Video enhancement pipeline. Use this skill when the user wants to sharpen, colour grade, warm, or normalise the audio of videos — including presets for natural, cinematic, or vivid looks.

abra 是什麼?

abra is a Claude Code agent skill that >- Video enhancement pipeline. Use this skill when the user wants to sharpen, colour grade, warm, or normalise the audio of videos — including presets for natural, cinematic, or vivid looks.

相容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/FilippTrigub/abra/tree/HEAD/skills/video-enhancer

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

video-enhancer — Video Enhancement Pipeline

Sharpens, colour-grades, and normalises audio for a batch of videos. No captions — for captioning use the video-captioner skill.

Pipeline

input video → unsharp + eq + colorbalance (ffmpeg) → -14 LUFS audio normalisation → output

Presets

PresetSharpnessSaturationWarmth
naturalsubtle+10%none
cinematicstrong+35%warm (red boost, blue reduce)
vividstrong+40%none

If the user has not specified a preset, ask them which look they want before running. Describe the options briefly: natural for a clean, understated result; cinematic for a warm, punchy Instagram-ready grade; vivid for maximum colour intensity.

How to run

Install dependencies (first run only):

cd "$SKILL_DIR" && uv sync

Then process videos:

cd "$SKILL_DIR" && uv run python scripts/enhance.py \
  --input <path/to/input> \
  --output <path/to/output> \
  --preset natural|cinematic|vivid

Common invocations

# Cinematic grade
uv run python scripts/enhance.py --input ./input --output ./output --preset cinematic

# Natural grade
uv run python scripts/enhance.py --input ./input --output ./output --preset natural

# Vivid grade
uv run python scripts/enhance.py --input ./input --output ./output --preset vivid

After running

Report back to the user:

  • How many videos were processed successfully and how many failed.
  • The full path to the output directory.
  • If any videos failed, name them explicitly.

Edge cases

  • If ffmpeg is not installed: tell the user to install it (sudo pacman -S ffmpeg on Arch/CachyOS, brew install ffmpeg on macOS, sudo apt install ffmpeg on Ubuntu)
  • If uv is not installed: direct to https://docs.astral.sh/uv/getting-started/installation/
  • If the input directory is empty: report clearly rather than silently exiting
  • If an unknown preset is given: list the valid options (natural, cinematic, vivid)
  • Audio normalisation may print a warning about dynamic mode for short clips — this is expected and not an error

Individual skills in this repo

This repo contains 7 individual skills — each has its own dedicated page.

FilippTrigub/abra

>- Animate a still image into a short video clip using fal.ai's LTX-2.3 Fast image-to-video model in the cloud. No GPU required - runs entirely on fal.ai serverless infrastructure.

FilippTrigub/abra

>- Auto-describe and caption images using a local vision-language model. Writes a JSON sidecar per image containing a one-sentence description, a suggested Instagram caption with hashtags, and detected content tags.

FilippTrigub/abra

>- Animated caption pipeline. Use this skill when the user wants to burn word-by-word animated captions into videos — using Whisper for transcription and pycaps for rendering. Supports default minimalist style or a futuristic CSS theme with alternating gold/magenta glowing words.

FilippTrigub/abra

>- Cut videos into segments, rearrange them, and produce an output video with a specific cuts-per-second rate. Uses MoviePy for video manipulation. Prioritizes audio transcription for timestamped cutting, falls back to adaptive scene detection.

FilippTrigub/abra

>- Edit a region of a video using a text prompt via Wan2.1-VACE inpainting. Supports two modes: background (auto-segment via rembg) or region (rectangle defined by fractions). Requires a CUDA GPU with at least 8 GB free VRAM.

FilippTrigub/abra

Generate videos from text or images using Higgsfield's multi-model cloud platform. Supports kling, seedance, dop, and dop-preview models. Uses a small preset layer for common creative styles. Auto-detects text-to-video or image-to-video based on input. No GPU required.

FilippTrigub/abra

>- Remove the background from every frame of a video using AI (BiRefNet-general via rembg). Outputs transparent-background video or composites onto a solid colour or image. Requires a CUDA GPU with at least 3 GB free VRAM.

相關技能