菜单
Process videos with FFmpeg — improve quality, auto-contrast, downsample, denoise, or crop using the video_ffmpeg_process tool.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Label video behavior segments from frame-grid images with a defined behavior list, model-ready JSON, resumable outputs, and no_behavior handling for sparse labels.
Use Annolid GUI tools for robust automation across web, PDF, video, and chat controls.
Infer the assay or paradigm from video context, task text, tracked entities, and experimental cues such as social interaction, open field, courtship, resident-intruder, and novel object recognition.
Choose assay-specific features and measurable objectives for behavior analysis, including distances, zones, speed, contact, orientation, and object interaction.
Segment behavior timelines from tracks, pose, contact, speed, and proximity signals into typed intervals with stable labels and rationales.
Keep behavior analysis aligned with assay objectives, controls, reproducibility, and measurable outputs instead of ad hoc summaries.
| name | Video FFmpeg Processing |
| description | Process videos with FFmpeg — improve quality, auto-contrast, downsample, denoise, or crop using the video_ffmpeg_process tool. |
| requires | {"any_bins":["ffmpeg"]} |
Use the video_ffmpeg_process tool to process video files with FFmpeg.
Use video_info first to inspect the source video (resolution, FPS, duration).
video_ffmpeg_processRequired: path — the input video file.
Presets — use action to apply common operations:
| Action | What it does |
|---|---|
improve_quality | Denoise + auto-contrast (good default for noisy lab videos) |
auto_contrast | Brightness/contrast/saturation enhancement only |
downsample | Halve resolution and FPS (reduce file size) |
denoise | Temporal + spatial denoising (hqdn3d) |
crop | Crop to a region (requires crop object) |
custom | Only explicit parameters are applied |
Fine-grained parameters — override any preset default:
scale_factor: spatial scale (0–1], e.g. 0.25 for quarter resolutiontarget_fps: output frame rateauto_contrast: booleancontrast_strength: 0–3 (higher = more contrast/saturation)denoise: booleancrop: {x, y, width, height} in pixels| User request | Recommended parameters |
|---|---|
| "improve the quality of this video" | action=improve_quality |
| "make the video brighter" | action=auto_contrast, contrast_strength=1.5 |
| "enhance contrast" | action=auto_contrast |
| "reduce file size" / "compress this video" | action=downsample |
| "downsample to 15 fps" | action=custom, target_fps=15 |
| "downsample spatially and temporally" | action=downsample |
| "half the resolution" | action=custom, scale_factor=0.5 |
| "denoise this recording" | action=denoise |
| "remove noise from the video" | action=denoise |
| "crop to region x=100 y=50 w=640 h=480" | action=crop, crop={x:100, y:50, width:640, height:480} |
| "clean up and shrink" | action=improve_quality, scale_factor=0.5 |
video_info to inspect the source video.video_ffmpeg_process with the appropriate action/params.output_path and key settings from the result to the user.error and suggest the user check FFmpeg availability.action=downsample + scale_factor=0.25 gives quarter resolution at half FPS.action=improve_quality with contrast_strength=2.0.overwrite=true only when the user explicitly says to replace the existing file.