Skip to content
mcp/skillhub

Agent Skill

Video Gen skill

video-gen0xsline/OpenChatCutsrc/agent/skills/video-gen/SKILL.md

AI video generation via Fal.ai, Seedance 2.0, Kling, MiniMax Hailuo, xAI Grok Imagine, and OFox. Use when the user wants to generate a video clip — text-to-video, image-to-video, first/last-frame transitions, reference-guided generation, multi-shot, or generatively editing / extending an existing clip.

2.6kAGPL-3.0

always on

78 tokname + description

once used

4,066 tokSKILL.md body

bundled files

638 KB

repo stars

2.6kGitHub

Install the Video Gen skill

Skills CLI (Claude Code, Codex, Cursor and others)

npx skills add https://github.com/0xsline/OpenChatCut --skill video-gen

Claude Code, by hand (all projects)

git clone --depth 1 https://github.com/0xsline/OpenChatCut.git /tmp/OpenChatCut
mkdir -p ~/.claude/skills
cp -R /tmp/OpenChatCut/src/agent/skills/video-gen ~/.claude/skills/video-gen

For one project only, copy the folder into .claude/skills/ in that project instead. The agent picks it up when a task matches its description.

What it costs your context

Agent Skills load in three steps. Tokens counted with the o200k tokenizer; your model's count will differ a little.

WhenWhat loadsCost
Every sessionName and description78 tok
When the agent uses itThe SKILL.md instructions4,066 tok
Only if opened6 bundled files (38 KB)varies

Until it is used, video-gen costs about 17× less than the median MCP server we measured (1,363 tokens on every turn). Installing all 31 skills from 0xsline/OpenChatCut would load 2,031 tokens of descriptions. Skills vs MCP study

Checks

Our checks found nothing to flag: it follows the Agent Skills specification's naming and size guidelines and doesn't pipe downloads into a shell.

Checked 2026-10-22 · method

What's inside

The headings of its SKILL.md. Read the full file on GitHub.

  • Video Gen
  • When to Use
  • Models
  • Model Selection
  • Tool Params
  • Input Resolution
  • Workflow
  • Step 1 — Align scope with the user
  • Step 2 — Write the prompt
  • Step 3 — Submit one, wait, confirm
  • Step 4 — Iterate
  • Visual consistency across shots
  • Anchors: the cornerstone of consistency
  • Sourcing an anchor
  • Establishing a new anchor (with user consent)
  • Using the anchor
  • Multi-character projects
  • Escalate when text adjustments fail
  • When to skip anchoring
  • Run
  • Config Mode
  • Rules

More skills from 0xsline/OpenChatCut

All skills in this repo
  1. ai-cinematic-short-film0xsline/OpenChatCut

    Plan AI short films with story, shots, prompts, and continuity.

    2.6k20 tok idle · 517 in use
  2. asset-import0xsline/OpenChatCut

    Use when acquiring or importing media into a OpenChatCut project asset library for video editing or creation, including local/attached videos, user-provided paths, public media URLs, web video/audio/image assets, upload fallback decisions, and deciding between import_media, download_media, or manual user action.

    2.6k62 tok idle · 746 in use
  3. batch-montage-variants0xsline/OpenChatCut

    Turn one pool of existing project media into a batch of distinct, publishable montage cuts instead of a single hero edit. Use for batch montage, one-source-many-outputs, 一源多出, 批量混剪, 批量出片, 矩阵号, 多账号分发, variant batches, deduped cuts, 去重变体, 防搬运, or when the user asks for N different versions of the same footage.

    2.6k101 tok idle · 1,053 in use
  4. beat-sync-montage0xsline/OpenChatCut

    Plan and build a finished beat-synced montage where cut placement serves the content, not just the metronome. Use for 卡点混剪, 卡点剪辑, 踩点视频, beat-sync montage, rhythm edit, 节奏剪辑, 音乐驱动剪辑, or when the user wants cuts that land on the beat.

    2.6k81 tok idle · 1,032 in use
  5. create-motion-graphics0xsline/OpenChatCut

    Use whenever the agent needs to add, create, hand-author, patch, or place Motion Graphic JSX assets in a OpenChatCut project. This is the direct-authoring path: use create_motion_graphic_from_code / edit_asset / edit_item, not motion-graphic-gen or submit_motion_graphic. Covers project/timeline intake, project visual language, editable properties, asset binding, inline JSX authoring, existing asset updates, timeline placement, and verification.

    2.6k97 tok idle · 5,976 in use
  6. ecommerce-product-montage0xsline/OpenChatCut

    Assemble product footage, UGC, and b-roll into a conversion-oriented montage with a hook → pain → demo → proof → CTA rhythm. Use for 带货混剪, 产品混剪, 商品短视频, 种草视频, ecommerce montage, product reel, UGC cutdown, or when the user wants selling footage cut into a short that converts.

    2.6k81 tok idle · 987 in use
  7. explainer-video0xsline/OpenChatCut

    Create finished explainer videos from a topic, script, outline, voiceover, product logic, data, technical concept, course material, or reference assets. Use when the user wants narration, motion graphics, stock footage, generated visuals, or mixed visuals to explain an idea.

    2.6k59 tok idle · 2,183 in use
  8. export0xsline/OpenChatCut

    Use when a OpenChatCut video editing or creation workflow needs export, render, download, share, final delivery, subtitle-file export, render choice, local-only asset handling, or export fallback explanation.

    2.6k42 tok idle · 1,934 in use