New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Video Editor

by jtydhr88 in jtydhr88/ComfyTV

Conversation-driven video editing on the ComfyTV canvas — rough cuts, silence removal, pacing passes, montages, trims, concat assemblies, speed changes, color grades, and subtitle burns over footage…

MITAuto-check passedMedia & Creative

Install Video Editor

skills CLI
$ npx skills add jtydhr88/ComfyTV --skill video-editor -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jtydhr88/ComfyTV video-editor --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jtydhr88/ComfyTV.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/video-editor .claude/skills/video-editor && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
video-editor
GitHub stars
1.1k
Token cost
~1.8k tokens
SKILL.md length
905 words
Files
4 (incl. references, assets)
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Conversation-driven video editing on the ComfyTV canvas — rough cuts, silence removal, pacing passes, montages, trims, concat assemblies, speed changes, color grades, and subtitle burns over footage…

  • Works in 8 steps: Strategy confirmation before execution.… → Never cut mid-speech. Snap every cut… → Pad every cut edge 30–200ms into the… → …
  • The user explicitly invokes $video-editor
  • SKILL.md covers Purpose, Core principle: read the…, Hard rules and Tool map, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Video Editor is an agent skill from jtydhr88/ComfyTV. Conversation-driven video editing on the ComfyTV canvas — rough cuts, silence removal, pacing passes, montages, trims, concat assemblies, speed changes, color grades, and subtitle burns over footage the user already has. Use when the user explicitly invokes $video-editor or asks to edit footage, cut out dead air or filler, tighten pacing, assemble clips into a sequence, grade a video, or burn subtitles. Reads the video through composite timeline views instead of frame-dumping; always confirms the cut strategy in…

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files and assets (for example `agents/openai.yaml` and `references/cut-craft.md`).

It sits in Media & Creative, covering Video production and Transcription. The repository describes itself as: ComfyTV — the canvas-based app that truly belongs to ComfyUI. The licence is MIT.

When your agent uses it

  • The user explicitly invokes $video-editor
  • Asks to edit footage
  • Cut out dead air
  • Assemble clips into a sequence

Example prompts

  • “/video-editor”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Strategy confirmation before execution. Describe the plan in plain
  2. Never cut mid-speech. Snap every cut edge to a silence gap from
  3. Pad every cut edge 30–200ms into the silence. Tighter for montage
  4. Subtitles burn LAST. SubtitleStage goes after every concat, speed,
  5. Preview cheap before rendering expensive. Iterate looks with
  6. Self-eval before presenting. After the final render, run
  7. Don't re-run what didn't change. Stages keep their outputs; Director
  8. The canvas is the project file. Keep the graph tidy (arrange_canvas)

What it can do on your machine

Read from SKILL.md and the folder at commit acde8fc. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Video Editor loads about 1.8k tokens when it runs, and up to ~2.9k if it reads all its reference files. Until then it costs about 143 tokens; SKILL.md has 905 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~143
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jtydhr88/ComfyTV at commit acde8fc, republished under its MIT licence (© jtydhr88). 905 words, ~1,779 tokens.

Download SKILL.mdSave it as .claude/skills/video-editor/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
video-editor
description
Conversation-driven video editing on the ComfyTV canvas — rough cuts, silence removal, pacing passes, montages, trims, concat assemblies, speed changes, color grades, and subtitle burns over footage the user already has. Use when the user explicitly invokes $video-editor or asks to edit footage, cut out dead air or filler, tighten pacing, assemble clips into a sequence, grade a video, or burn subtitles. Reads the video through composite timeline views instead of frame-dumping; always confirms the cut strategy in plain English before touching anything.

Video Editor

Purpose

Edit existing footage by conversation. The material is the user's — takes, renders, downloads, generated clips. The job is editorial: what to keep, where to cut, how to pace, how it should look. Everything is built as stages on the user's canvas, so every decision stays visible and adjustable after you leave.

Invoke with $video-editor or infer from an editing request. Do not widen the task into generating new footage unless asked — generation is the Director stage's job, editing is yours.

Core principle: read the video, don't watch it

Never scan a video by pulling frames one by one. Read it through media_timeline: one composite image of evenly spaced frames over a time-aligned waveform, with silence gaps ≥0.35s shaded AND returned as data (silences). The silence spans are your cut candidates before you have looked at a single frame.

  • media_probe first — duration, fps, resolution, has_audio.
  • media_timeline over the whole clip for the first read; again over narrow ranges (±1.5s) at decision points — ambiguous pauses, boundary checks.
  • media_frame + view_image only when you need one frame at full attention.
  • Audio is primary, visuals follow: cut candidates come from silence gaps and speech boundaries; drill into visuals only to confirm.

If a transcript helps (dialogue-heavy footage) and a speech-to-text workflow is available, add a ComfyTV.SubtitleGenStage, run it, and read the SRT it returns. Convert its cues to {text, start, end} objects and pass them as words to media_timeline to get a labeled timeline. SRT cues are phrase-level, not word-level — pad cuts more generously when relying on them.

Hard rules

  1. Strategy confirmation before execution. Describe the plan in plain English — what gets cut, kept, reordered, graded — and wait for the user's OK before building or running anything.
  2. Never cut mid-speech. Snap every cut edge to a silence gap from media_timeline. Gaps ≥400ms are the cleanest; 150–400ms need a visual check; below 150ms is unsafe.
  3. Pad every cut edge 30–200ms into the silence. Tighter for montage energy, looser for cinematic pacing.
  4. Subtitles burn LAST. SubtitleStage goes after every concat, speed, and FX stage in the chain — anything composited after it will cover the captions.
  5. Preview cheap before rendering expensive. Iterate looks with fx_preview (one FX stage, ~1.2s window) until the frame is right, THEN set the stage and render. Render one boundary clip to verify a doubtful cut before building the whole chain.
  6. Self-eval before presenting. After the final render, run media_timeline on the RENDERED output at every cut boundary (±1.5s): look for visual jumps, waveform spikes (audio pops), and captions hidden by later compositing. Fix and re-render at most 3 times, then flag what remains instead of looping.
  7. Don't re-run what didn't change. Stages keep their outputs; Director clips re-render only when edited. Re-running an unchanged chain wastes the user's GPU time.
  8. The canvas is the project file. Keep the graph tidy (arrange_canvas) and show the user what you built (canvas_focus). Never leave orphaned stages behind.
Show full SKILL.md (413 more words)Show less

Tool map

Reading:

  • media_probe — metadata; always first.
  • media_timeline — filmstrip + waveform + silence data; the primary read.
  • media_frame + view_image — one frame, actually looked at.
  • media_waveform — audio-only files.
  • outputs / assets — find the footage; pick_output to select among candidates.

Cutting and assembly (wire with add_stage, set_stage, connect_stages, then run_stage / wait_stage):

  • ComfyTV.VideoClipStage — keep one range (start_s, end_s). One kept segment = one clip stage.
  • ComfyTV.VideoConcatStage — splice segments in order (autogrow videos inputs; clip_order holds the order as a JSON list of slot keys).
  • ComfyTV.VideoSplitStage — one cut point, two outputs.
  • ComfyTV.VideoSpeedStage — speed ramps; ComfyTV.VideoCropStage — reframe; ComfyTV.VideoVolumeStage — gain and audio fades.
  • ComfyTV.SubtitleGenStage — speech-to-text workflow → SRT text out.
  • ComfyTV.SubtitleStage — burn SRT/VTT (subs widget or wired text input).

Look development:

  • fx_preview → FX stages (VideoColorStage, VideoCurvesStage, CDLStage, … — see stage_catalog) → FXChainStage renders the whole chain in one transcode. Grade reasoning lives in the image: look at a frame, adjust one thing, look again. Test skin tones before going aggressive.

Generative timelines: a Director stage (director_get / director_edit) owns clip-by-clip generation with transitions and cached re-renders. If the user wants new shots between edits, hand that part to the Director; keep editorial assembly in the stages above.

The process

  1. Inventory. media_probe + full-range media_timeline on every source. Note lengths, silence patterns, visual character. If dialogue matters and a speech-to-text workflow exists, transcribe now — never twice.
  2. Converse. Say what you see in plain English. Ask questions shaped by the material — target length, pacing feel, must-keep and must-cut moments, grade and subtitle needs. No fixed checklist; the right questions differ every time.
  3. Propose strategy. 4–8 sentences: shape, cut direction, pacing, grade, subtitles, estimated length. Wait for confirmation (hard rule 1).
  4. Execute. Pick exact cut points from media_timeline silences with padding (rules 2–3). Build clip stages → concat → speed/FX → subtitles last. Run and wait.
  5. Self-eval (rule 6), then present with canvas_focus on the result.
  6. Iterate. Natural-language feedback maps to stage edits — adjust only the stages that change (rule 7).

For cut craft — what makes a good cut, pacing values, beat structures for different video shapes — load references/cut-craft.md.

Taste

Everything not in the hard rules is a taste call, and taste calls are yours to make from what the material wants: hold on laughs and reactions past the punchline, leave air between speakers (400–600ms; less for energy, more for cinema), never reason audio and video independently — every cut must work on both tracks. Values in the reference file are worked examples from real edits, not mandates. Invent freely when the material calls for something the tools support.

© jtydhr88, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (references, assets) in skills/video-editor of jtydhr88/ComfyTV.

  • SKILL.md
  • agents/openai.yaml
  • assets/icon.svg
  • references/cut-craft.md

Open the folder on GitHubat commit acde8fc

Compare with similar skills

Video Editor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Video Editor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Video Editor this skilljtydhr88/ComfyTV1.1k—~1.8kAutomated safety check: PassMIT
Video Understandcalesthio/OpenMontage66k—~841Automated safety check: PassAGPL-3.0
Capcut Editrenezander030/capcut-cli847—~1.4kAutomated safety check: PassMIT
Yt Dlp DownloaderMapleShaw/yt-dlp-downloader-skill2091 repos~1.5kAutomated safety check: PassNone
Karaoke CaptionsAI-Builder-Club/skills1.3k—~850Automated safety check: PassNone
Paper Collage Explainer Generatortl2012tl/comfyUI-llama-TE2414 repos~5.2kAutomated safety check: PassNone

Similar skills

  • Video Understand

    calesthio/OpenMontage

    Understand video content locally using ffmpeg frame extraction and Whisper transcription.

    66k GitHub stars~841 tokensUpdated 6 days ago
    Media & CreativeAuto-check passed

  • Capcut Edit

    renezander030/capcut-cli

    Edit CapCut / JianYing video projects — read and write subtitles, timing, speed, volume, templates, animations (fade/ken-burns), and cut long-form to shorts.

    847 GitHub stars~1.4k tokensUpdated today
    Media & CreativeAuto-check passed

  • Yt Dlp Downloader

    MapleShaw/yt-dlp-downloader-skill

    Download videos from YouTube, Bilibili, Twitter, and thousands of other sites using yt-dlp.

    209 GitHub starsUsed in 1 repo~1.5k tokens
    Media & CreativeAuto-check passed

  • Karaoke Captions

    AI-Builder-Club/skills

    Generate TikTok/Shorts-style karaoke captions using MLX Whisper, ASS subtitles, and FFmpeg libass.

    1.3k GitHub stars~850 tokensUpdated 24 days ago
    Media & CreativeAuto-check passed

  • Paper Collage Explainer Generator

    tl2012tl/comfyUI-llama-TE

    For creators, educators, and social-video editors who need a tactile paper-collage language for narration, knowledge points, opinions, or abstract topics.

    241 GitHub starsUsed in 4 repos~5.2k tokens
    Media & CreativeAuto-check passed

  • Short Form Edit

    nateherkai/hyperframes-student-kit

    Turn talking-head footage into a finished reel, YouTube Short, or short advertisement with curiosity-led openings, earned payoffs, story-driven cuts, transcript-synced motion graphics, moving…

    1.2k GitHub stars~5.3k tokensUpdated 11 days ago
    Media & CreativeAuto-check passed

More from jtydhr88/ComfyTV

  • H3 Cinematic Director

    jtydhr88/ComfyTV

    Convert approved scripts, shot briefs, storyboards, keyframes, character sheets, scene assets, prop sheets, and sound briefs into director-level storyboards and production-ready MiniMax H3 prompts.

    1.1k GitHub stars~2.7k tokensUpdated 2 days ago
    Auto-check passed

  • Brainstorm

    jtydhr88/ComfyTV

    Pre-production ideation on the canvas. An agent skill from jtydhr88/ComfyTV.

    1.1k GitHub stars~631 tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Video Editor

What does Video Editor do?

Conversation-driven video editing on the ComfyTV canvas — rough cuts, silence removal, pacing passes, montages, trims, concat assemblies, speed changes, color grades, and subtitle burns over footage…. Video Editor is an agent skill from jtydhr88/ComfyTV. Conversation-driven video editing on the ComfyTV canvas — rough cuts, silence removal, pacing passes, montages, trims, concat assemblies, speed changes, color grades, and subtitle burns over footage the user already has.

When should I use Video Editor?

Video Editor fits situations like: the user explicitly invokes $video-editor; asks to edit footage; cut out dead air; assemble clips into a sequence.

How do I install Video Editor in Claude Code?

Run `npx skills add jtydhr88/ComfyTV --skill video-editor -a claude-code`. Or copy the skill folder (skills/video-editor in jtydhr88/ComfyTV) into .claude/skills/video-editor in your project. Claude Code loads it when a task matches its description.

How do I install Video Editor in Codex?

Run `npx skills add jtydhr88/ComfyTV --skill video-editor -a codex`. Or copy the skill folder (skills/video-editor in jtydhr88/ComfyTV) into .agents/skills/video-editor in your project. Codex loads it when a task matches its description.

Can I use Video Editor in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jtydhr88/ComfyTV --skill video-editor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/video-editor, .gemini/skills/video-editor, .github/skills/video-editor and .opencode/skills/video-editor in your project.

What does Video Editor need to run?

SKILL.md names no scripts, command-line tools or credentials: Video Editor is instructions for the agent only.

Does Video Editor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Video Editor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Video Editor use?

Video Editor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Video Editor use?

About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.1k tokens, read only when the agent opens those files.

What are the alternatives to Video Editor?

Skills that share tags, products or a category with Video Editor: Video Understand (calesthio/OpenMontage, 66k stars), Capcut Edit (renezander030/capcut-cli, 847 stars), Yt Dlp Downloader (MapleShaw/yt-dlp-downloader-skill, 209 stars) and Karaoke Captions (AI-Builder-Club/skills, 1.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Video Editor?

jtydhr88 (a GitHub user) maintains it in jtydhr88/ComfyTV, which has 1,066 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 7, 2026.

Source: jtydhr88/ComfyTV on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.