Communitygithub.com

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.

video-editing とは?

video-editing is a Claude Code agent skill that 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.

対応~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/prathameshp107/video-editing/tree/HEAD/.agents/skills/vlog-editor

お気に入りのAIに質問する

このエージェントスキルを事前に読み込んだ状態で新しいチャットを開きます。

ドキュメント

Vlog editor

Use this for a visit, travel, or food vlog under projects/. Read its BRIEF.md, SHOT_LOG.csv, STORYBOARD.md, and EDIT_DECISIONS.csv if present. Inventory new media before editing; filenames alone are not enough to understand what a shot shows. Load the local asset-plan skill for new media, watch for video evidence or a reference style, story-editor for the cut structure, broll-curator for a reusable cutaway pack, motion-overlay for graphics, audio-finisher for the mixed soundtrack, color-match for inconsistent shots, cut-audit for edit boundaries, render-review for the final export, platform-package for upload assets, format-repurposer for another canvas, and style-memory when the creator gives corrections. Load only the relevant focused skills for the current task.

Build the story from what was actually filmed. For a visit vlog, establish how the creator traveled there, what changed on arrival, what the place looks and feels like, and the main experience. An engaging hook can precede the journey. Give required photos and videos a purposeful place in the sequence. Do not force a standard structure on footage that tells its story differently.

Treat must_use=yes in the shot log and direct user requests as coverage requirements. Run scripts/check_edit_plan.py before export. Record any deliberately omitted source with a reason in the shot log.

Use stills with gentle motion when it helps, especially for detailed product, food, or location photos; preserve readable text and natural framing. Use a few motivated transitions rather than adding one at every cut. Do not stretch portrait footage to fill 16:9. Label subjects, prices, and factual claims only when source material or the creator supports the claim.

Choose the editing implementation from TOOLING.md. If using Remotion or HyperFrames, load the installed framework skill and follow its setup and preview/render process. This skill covers editorial decisions and review; it does not replace framework documentation.

Check STYLE_DEFAULTS.md and the project's STYLE.md for the creator's recorded typography, transition, and framing preferences before choosing graphic styles or effects.

Before delivery, inspect representative frames in the final render, listen to the mix, and run scripts/verify_export.py. Give the user the final video and the editable project when available. Keep all referenced media with that project.

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

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

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

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.

関連スキル