Communitygithub.com

prathameshp107/video-editing

Prepare source-linked cutaway clips for any long or short video, with timecodes, rights, clear names, format-aware framing, and a contact sheet.

video-editing 是什么?

video-editing is a Claude Code agent skill that prepare source-linked cutaway clips for any long or short video, with timecodes, rights, clear names, format-aware framing, and a contact sheet.

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/prathameshp107/video-editing/tree/HEAD/.agents/skills/broll-curator

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

B-roll curator

Use for a Reel, Short, long video, vlog, product video, or other footage edit when supporting shots need to be selected or stored. Establish the video's subject and delivery canvas first. Inspect each candidate visually; a name or one midpoint frame can hide unusable motion or a misleading shot. Favor footage that advances the story or covers a specific edit point.

For a new project, fill templates/BROLL_MANIFEST.csv with source path, in-point, duration, output name, category, usage note, rights, and any source URL. Then run python scripts/curate_broll.py --manifest <csv> --output <folder> --profile wide|vertical|square|portrait-feed --mode fit|crop. This trims raw video or animates a still into a clean MP4, writes catalog.csv, and makes a contact sheet. Source paths in the CSV are relative to that CSV. Use rotation=none|cw|ccw|180 only after inspecting a clip with incorrect orientation; auto follows normal metadata. Use fit to keep the whole shot or crop only when the subject survives the crop. Preserve source audio when useful; the helper adds no title or music.

Keep source media untouched. If third-party footage is used, verify its current license and record its exact URL, creator, and attribution requirement. Label photo-derived motion honestly. Review the contact sheet and play the start and end of uncertain clips; check that no person, menu, sign, or important action was cut off. Report format, count, rights, and any unusable shots. Preparing a pack does not insert clips into the final edit.

Individual skills in this repo

This repo contains 13 individual skills — each has its own dedicated page.

prathameshp107/video-editing

Inventory and classify footage, photos, audio, and factual evidence before a footage-based video edit; record required shots and source-backed labels in this repository.

prathameshp107/video-editing

Measure and finish the mixed audio of a Reel, Short, long video, or audio-only deliverable with local FFmpeg and an encoded-output check.

prathameshp107/video-editing

Compare multiple frames from videos or photos across cameras, lighting, and output formats, then review a deliberate color adjustment.

prathameshp107/video-editing

Audit the picture and audio at edit boundaries in a rendered video, catching clipped speech, sudden sound changes, black frames, awkward dissolves, and visible jump cuts.

prathameshp107/video-editing

Reframe a selected source range for wide YouTube, vertical Reels or Shorts, square, or portrait-feed delivery with fit or intentional crop.

prathameshp107/video-editing

Design and add short motion graphics inside an existing video, such as titles, maps, labels, lower thirds, photo moves, and transitions, using Remotion or HyperFrames where appropriate.

prathameshp107/video-editing

Prepare source-backed cover art, title or caption, credits, and optional long-form chapters for YouTube videos, Shorts, Instagram Reels, or other delivery formats.

prathameshp107/video-editing

Review a finished video export for story coverage, readable text, framing, motion graphics, audio, and technical integrity before delivery.

prathameshp107/video-editing

Build a coherent travel, food, visit, or topic-driven video from inventoried footage, choosing story beats, clip order, pacing, still-photo placement, and an edit decision list.

prathameshp107/video-editing

Turn explicit creator feedback on pacing, framing, titles, transitions, and audio into a reusable style note without overgeneralizing one-off corrections.

prathameshp107/video-editing

Match narration or dialogue to indexed footage and audit a video timeline for off-topic shots using local, free tools. Use for footage searches and voiceover-to-picture alignment; do not treat filename similarity as visual proof.

prathameshp107/video-editing

Plan and quality-check footage-based travel, food, or visit vlogs in this repository, including source inventory, story structure, required-shot coverage, portrait framing, photos, titles, audio, and export review.

prathameshp107/video-editing

Generate narration locally in a consented speaker's voice using the bundled Chatterbox TTS model. Works with any language supported by the installed checkpoint. Audio finishing and soundtrack mixing are separate steps.

相关技能