THE SKILL MARKETPLACE

AI VIDEO EDITING SKILL

Editing for YouTube: edit in your channel’s style

Editing for YouTube is a bundle of instructions and tools for editing YouTube videos with Codex or Claude on Windows. It helps analyze footage and prepare speech, inserts and animation; you approve the plan and sample.

Codex + ClaudeWindows 10 / 11v4.1.0
  • Analysis and structure before rendering
  • A 60–90-second sample before the full edit
  • Your branding and lasting editing rules
Example result ↓
Current version · v4.1.014 motion templates, breath attenuation and more accurate screencast editsVersion and updates ↓

See before deciding

See what you can create

First: a 55-second showcase of version 4.1.0, with Russian on-screen text. The author’s project used 7.6 hours of source footage to produce a 19:36 video with 81 graphics layers. These are results from one project, not a promise for every video. The other visual examples were made with 4.0.0.

Skills by Paul Wise · Spec Skills. Demo videos supplied by the author.

Your style and your material

The skill keeps your lasting instructions in your workspace. Its rules preserve the faces of the video’s creators; you review the final edit and rights to music and materials.

How to start

01 /

Connect the bundle

Choose Codex or Claude and configure your channel, tools and branding.

02 /

Approve the analysis

The AI reviews footage and proposes an opening, structure and inserts.

03 /

Review a sample

Review 60–90 seconds, then approve the full video.

Who it is for

For reviews, screencasts, news and talking-head videos. You approve the plan and review the footage. Some local models need a compatible GPU.

What the skill includes now

The essentials are visible. Expand the complete capability list.

01 /

Transcription and speech editing

Whisper word timestamps with two-model checks; synchronize a separate microphone with the camera and check drift.

02 /

Titles, graphics and animation

Remotion chapter cards, news cards, name/role lower thirds, counters, word-timed lists, charts, quotes, transitions and HUD panels.

03 /

Delivery and verification

YouTube H.264/BT.709 export with faststart; checks for black/frozen frames, audio gaps and levels.

All capabilities · v4.1.0

Footage review and plan

Inventory files, duration, audio tracks and creator footage. Propose openings, structure, chapters, inserts, graphics and effects. Agree on the plan before rendering, then review a 60–90-second sample.

Transcription and speech editing

Whisper word timestamps with two-model checks; synchronize a separate microphone with the camera and check drift. Find repetitions, false starts, slips and failed takes, prepare listening clips, shorten pauses naturally without speeding speech and check that unique ideas survive the edit.

Sound and music

Basic filtering and light noise reduction, smooth audio joins, loudness normalization and peak checks. Duck music under speech and use your music/SFX folders. Optional Demucs separates voice/background; DeepFilterNet handles stronger noise.

Framing and inserts

Face tracking, smooth zooms and framing changes. Phrase-based visual plans, own-footage search and Pexels/Pixabay material with source/license records. Check shake, repetition and scene drift; blur unrelated logos and private data.

Titles, graphics and animation

Remotion chapter cards, news cards, name/role lower thirds, counters, word-timed lists, charts, quotes, transitions and HUD panels. Speech-synced kinetic titles. Shine, glow, electricity, glitch, typewriter, decode, scanner, drawn lines and particles; image pans, zooms, detail highlights, before/after comparisons, grids and parallax.

Local model and AI imagery

Optional Qwen3‑VL‑4B describes sampled frames and indexes B-roll for content search; ask questions about images. Optional tools make object masks and depth maps, support parallax and titles behind the creator, and generate FLUX illustrations through ComfyUI. Surface-tracked text needs a suitable tool and license; commercial CoTracker use requires separate permission.

Separate Video Story format

A large canvas with smooth camera moves between ideas, a route and an overview. Paper style: sketch-to-color, drawn diagrams, charts and labels. Technology style: blueprint grid, laser engraving, layered reveals, LED text and pulses. Elements follow spoken words; approve the storyboard and sample chapter first.

Video formats and dubbing

Rules for screencasts, gadget reviews, news and talking heads. On request, Shorts from strong passages with vertical 9:16 framing. Optional Chatterbox supports creator-voice dubbing, phrase timing and back-transcription checks.

Personal setup

Configure the channel, formats, colors, font and signature; review sample graphics and a test edit. Lasting revisions go into a personal rules file. Preserve creators’ faces. Change the primary chat language independently of the video language. Includes Codex/Claude packages, Windows installer, documentation and license table.

Delivery and verification

YouTube H.264/BT.709 export with faststart; checks for black/frozen frames, audio gaps and levels. Transcript-derived chapters, three titles and three real-footage thumbnails. Timecoded revisions and rebuilding changed parts. After publication, compare retention with the edit and formulate a testable hypothesis.

4.1.0 additions: graphics, speech and synchronization

14 additional Remotion compositions: word-timed kinetic titles, a glowing counter, shine/glitch callouts, A/B matchups, three alternatives, round scoreboards, stamps, measurement and verdict tables, dialogue bubbles and end screens. Android/ADB diagrams also ship with demonstration content to adapt to your project. Audio: new breath.py attenuates quiet breaths and clicks between words in a separate WAV, protecting speech boundaries. An optional energy guard is available. Very short recordings and phase-opposed stereo are handled correctly. For intrusive noise, the skill first proposes an approved DeepFilterNet before/after sample. Fewer unnecessary speech cuts: repetition checks account for lists, alternatives and differing before/after numbers. A nonadjacent repeated single word does not automatically trigger removal. Long words and uncertain cuts become listening candidates. Screencasts and cameras: gentle pushes normally up to 110%, focus on the readable window and overlays clear of important text. Silent screen recordings require event-based alignment and drift checks. Zoom windows correctly follow video offsets relative to the microphone. Animation stays word-timed after pause removal by mapping source timestamps to the edit. Parallel jobs use isolated temporary names; push caches include FPS, and detected render failures prevent an output being marked complete. Local insert search retains optional Qwen3-VL-4B frame descriptions, a B-roll text index, readable tables, query search and people/no-people filters. Searching a completed index does not load the model.

Optional AI components require approval for installation and use. Capabilities depend on the host application’s tools, your computer and licenses.

For Codex

A video-editing skill for Codex on your computer, with instructions for working with files and tools in the Codex environment.

For Claude

The same editing rules, with separate instructions for computer access and tools in the Claude environment.

One bundle · Codex + Claude

39.99 € · Euro payments with Stripe are not available yet. Submit a request to be notified; no payment will be taken.

Request payment in euros →
Portrait of Paul Wise, creator of Spec Skills

Paul Wise

20 years in IT, from computers and websites to YouTube and AI skills.

About the author and his projects ↗

Page updated:

COMMUNITY / SPEC SKILLS

Reviews and ratings

Reviews submitted on Spec Skills are moderated. No account is needed; an on-site rating alone does not verify a purchase.

Digiseller reviews are published automatically after purchase verification and synced hourly. Positive feedback is shown as 5 stars and negative feedback as 1 star. Reviews on the two platforms count separately.

Published reviews

5.0 / 5 · 1

Digiseller buyer ★★★★★

Digiseller · verified purchase

Супер, работает круто, я раньше столько времени тратил на монтаж видео и делал хуже, а теперь все просто и быстро, спасибо Павлу и Клоду.

Added to Spec Skills · Original text

Write a review

Write a review

Do not include personal or confidential details. No email required. Reviews are stored on this site; contact support to request removal. Spam protection uses a temporary IP hash; your IP is not stored with the review.

PROMPTS / 3

Example prompts

Start by adapting the skill to your channel.

01 /

Set up your editing style

Establish your style, tools and materials for a first sample edit.

Download TXT ↓

02 /

Starter prompt for your first video

Fill in the fields in < >. The AI first reviews your footage and proposes a plan; the sample and full edit follow your approval.

Download TXT ↓

03 /

Short prompt for future videos

For a configured skill: analysis and suggestions → your approval → a 60–90 second sample.

Download TXT ↓

Frequently asked questions

When can I buy and download it?

39.99 €. Euro payments with Stripe are not available yet. Submit a request to be notified; no payment will be taken.

Is it a standalone video editor?

It is a pair of AI skills and a toolkit. You need Codex or Claude with skill support and appropriate access to your computer.

Can it adapt to my channel?

Yes. First-time setup covers your channel, branding, software and materials, and proposes sample graphics and a test edit.

What language are the materials in?

This page is assigned the English archive; the Russian page uses Russian. Change and save the primary chat language independently of the spoken-video language.

Will the skill ask for a rating?

After successful installation and initial setup, the skill invites you once to leave an honest rating and comment. No account is needed; reviews appear only after moderation. Declining does not affect the skill.

What does the local model do, and does it need internet?

Optional Qwen3‑VL‑4B analyzes sampled frames on your PC and creates a B-roll text index for finding inserts. Models and tools must first be downloaded using internet access. Local components do not make the whole workflow offline: data processing by the main AI assistant depends on its application and settings.

Do editing and animation require a graphics card?

A GPU is not required for basic editing. Some optional frame-analysis, illustration and dubbing models need a compatible NVIDIA GPU and enough VRAM. The installer checks the environment; components are chosen with the user.

Are there extra tool costs?

The bundle price excludes AI-application subscriptions and any third-party tool licenses. Remotion has specific commercial-team terms; CoTracker has a non-commercial license. Review the license table and terms before use.

Start with your own footage

Editing for YouTube · v4.1.0 · 39.99 €

Request payment in euros →
Version and updates

Version history

The two latest versions are shown first. Expand earlier changes below. Downloads use only the current version.

v4.1.0

  • 14 additional Remotion compositions: word-timed kinetic titles, a glowing counter, shine/glitch callouts, A/B matchups, three alternatives, round scoreboards, stamps, measurement and verdict tables, dialogue bubbles and end screens. Android/ADB diagrams also ship with demonstration content to adapt to your project.
  • Audio: new breath.py attenuates quiet breaths and clicks between words in a separate WAV, protecting speech boundaries. An optional energy guard is available. Very short recordings and phase-opposed stereo are handled correctly. For intrusive noise, the skill first proposes an approved DeepFilterNet before/after sample.
  • Fewer unnecessary speech cuts: repetition checks account for lists, alternatives and differing before/after numbers. A nonadjacent repeated single word does not automatically trigger removal. Long words and uncertain cuts become listening candidates.
  • Screencasts and cameras: gentle pushes normally up to 110%, focus on the readable window and overlays clear of important text. Silent screen recordings require event-based alignment and drift checks. Zoom windows correctly follow video offsets relative to the microphone.
  • Animation stays word-timed after pause removal by mapping source timestamps to the edit. Parallel jobs use isolated temporary names; push caches include FPS, and detected render failures prevent an output being marked complete.
  • Local insert search retains optional Qwen3-VL-4B frame descriptions, a B-roll text index, readable tables, query search and people/no-people filters. Searching a completed index does not load the model.

v4.0.0

  • Video stories: a separate Video Story skill builds explainers on a large canvas. The camera moves smoothly between ideas, zooms into details and reveals the whole layout. The storyboard is approved before rendering.
  • Two animation styles: paper uses pencil sketches, color reveals and drawn diagrams/charts; technology uses a blueprint grid, laser engraving, layer-by-layer image reveals, LED headings and pulses along circuit traces.
  • Titles and infographics: expanded HUD panels, counters, lists and comparisons. Large kinetic titles can follow the creator’s spoken words, while effect suggestions highlight numbers, conclusions and other meaningful speech moments.
  • Speech and content checks: expanded checks for repetitions, slips and failed takes, listening clips for review and coverage checks that preserve unique ideas. Questionable edits can be reviewed before the final cut.
  • Local frame-analysis model: Qwen3‑VL‑4B describes sampled frames and creates a text index of your B-roll library, helping you find relevant inserts by content and ask questions about images. After download it runs on your PC; this optional component needs a compatible NVIDIA GPU and enough VRAM.
  • Optional local AI tools: voice/background separation and noise cleanup, object cutouts, depth maps for 3D-like parallax, illustration generation through FLUX/ComfyUI and Chatterbox dubbing with back-transcription checks. Installation and use require approval; availability depends on your PC and the selected tools’ licenses.
  • Installation matched to your computer: the installer checks the environment and offers suitable optional components. The workflow includes plan approval and a sample edit before the full video; video stories begin with a chapter for review.
Earlier versions (1)

v3.2.0

  • Added Codex/Claude packages, Windows installer and editing tools.
  • Creator/brand setup, test edit and persistent editing rules.
What you need

Windows 10/11 64-bit, at least 8 GB RAM (16 GB recommended), around 10 GB of free space plus project files. All optional AI components may require around 70 GB. A GPU is optional for basic editing; some components require NVIDIA and sufficient VRAM.

The Windows installer places tools in your workspace. In its normal mode, if Python or Node.js is missing, it offers installation with your consent. Internet access is needed to obtain tools and models.

Tool licensing

Remotion is free for individuals and teams of up to three, including commercial videos. Larger commercial teams generally need a paid license; exceptions and special rules for joint projects apply. Check the current Remotion terms and other tools’ licenses. CoTracker is non-commercial; commercial tracking requires another tool or separate permission.

Check Remotion terms ↗ ↗