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

AI Video Generation

by 0xsline in 0xsline/OpenChatCut

Submits AI video generation jobs to Fal.ai, Seedance, Kling, MiniMax Hailuo, xAI Grok Imagine or OFox for text-to-video, image-to-video, transitions and clip extension.

AGPL-3.0Auto-check passedMedia & Creative

Install AI Video Generation

skills CLI
$ npx skills add 0xsline/OpenChatCut --skill video-gen -a claude-code

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

GitHub CLI
$ gh skill install 0xsline/OpenChatCut video-gen --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/0xsline/OpenChatCut.git skills-src && mkdir -p .claude/skills && cp -r skills-src/src/agent/skills/video-gen .claude/skills/video-gen && 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-gen
GitHub stars
2.2k
Token cost
~4.3k tokens
SKILL.md length
2,170 words
Files
7 (incl. references)
Skills in repo
31
Repo updated
First seen
Licence
AGPL-3.0

At a glance

Submits AI video generation jobs to Fal.ai, Seedance, Kling, MiniMax Hailuo, xAI Grok Imagine or OFox for text-to-video, image-to-video, transitions and clip extension.

  • Works in 4 steps: Align scope with the user → Write the prompt → Submit one, wait, confirm → …
  • Generating a short clip from a text prompt
  • SKILL.md covers When to Use, Models, Model Selection and Tool Params, plus 6 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Each call submits one video generation job and returns a jobId. Waiting and status checks belong to a separate track_progress tool, and the skill does not place the finished clip on the timeline. It covers text-to-video, image-to-video, first and last frame transitions, reference-guided generation, multi-shot storyboards and generatively editing or extending an existing clip, which means new generated footage rather than timeline trimming.

Six model routes are described, each with a reference file the agent must read before generating: Fal.ai with an explicit model name, Seedance 2.0 (the default when configured), Kling, MiniMax Hailuo, xAI Grok Imagine and the OFox gateway. Limits differ. Hailuo clips are 6s or 10s, Grok Imagine does text-to-video only for 1–15s, and Seedance runs 2–15s. The agent only calls a vendor whose key is configured and never invents parameters a reference forbids.

When your agent uses it

  • Generating a short clip from a text prompt
  • Animating a still image into a video clip
  • Building a transition between a first and a last frame
  • Extending or regenerating part of an existing clip with AI

Example prompts

  • “Generate a 6-second clip of waves rolling onto a rocky beach at sunrise with Hailuo.”
  • “Animate the product photo ./shots/mug.png into a slow camera push-in video.”
  • “Make a clip that transitions from ./frames/day.png as the first frame to ./frames/night.png as the last.”

Requirements

  • An API key configured for at least one supported video vendor

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Align scope with the user
  2. Write the prompt
  3. Submit one, wait, confirm
  4. Iterate

What it can do on your machine

Read from SKILL.md and the folder at commit 2e6f4a2. 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 (its code samples are typescript).

    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

AI Video Generation loads about 4.3k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 78 tokens; SKILL.md has 2,170 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~4.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~14k

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 0xsline/OpenChatCut at commit 2e6f4a2, republished under its AGPL-3.0 licence (© 0xsline). 2,170 words, ~4,291 tokens.

Download SKILL.mdSave it as .claude/skills/video-gen/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
video-gen
description
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.
user-invocable
true

Video Gen

Submits one video generation job per call and returns a jobId. Job management (wait / status) belongs to track_progress; this skill does not place videos on the timeline automatically.

When to Use

Any time the user wants to generate a video clip — text-to-video, image-to-video, first-last-frame transition, reference-based generation, multi-shot storyboard, or generatively editing / extending an existing video (producing new generated footage based on a source clip; not timeline trimming).

Models

ModelReferenceStrengths
fal + falModelreferences/fal.mdExplicit Fal catalog; see tool schema for per-model limits
seedance2references/seedance2.mdDefault when configured. Multimodal refs, first/last, edit/extend/bridge, 2–15s, 480p/720p/1080p/4k, audio/seed/camera/watermark/last-frame/task controls.
klingreferences/kling.mdTechnical camera/performance; Omni multi-shot; images ≤7 (≤4 with one feature refVideos); std/pro; 3–15s.
hailuoreferences/hailuo.mdMiniMax 海螺. T2V / I2V / first+last; 6s or 10s; 512P (Hailuo-02), 720p→768P, 1080P (6s); no multi-ref / multi-shot.
grok-imagine-videoreferences/grok-imagine-video.mdxAI Grok Imagine. Text-to-video only; 1–15s; 480p/720p/1080p; audio track included.
ofoxreferences/ofox.mdOFox multi-model gateway (Seedance/Wan and more behind one key). Text/image-to-video, first+last frame, up to 9 image refs; 2–30s with per-model API limits; 480p/720p/1080p per model.

IMPORTANT: Before generating, READ the chosen model's reference for capabilities, input channels, modes, prompt structure, and model-specific behavior. Never invent params the reference forbids.

Model Selection

Respect configured vendors from the capabilities prompt (only call a model whose key is on).

  1. User named a vendor ("用海螺", "MiniMax", "Kling", "Seedance") → that model, if configured.
  2. If Fal.ai is selected or requested, use model: "fal" and the requested falModel or saved Fal default from capabilities. Ask if no Fal model is selected. Read the Fal catalog constraints in the tool schema; the native-provider limits below do not apply.
  3. Else default seedance2 when Seedance is configured.
  4. Else if only Kling is on → kling. Else if only MiniMax is on → hailuo. Else if only xAI is on → grok-imagine-video. Else if only OFox is on → ofox.
  5. Switch away from default when:
    • Need multi-shot customize / intelligence → kling (confirm if not user-named).
    • Need rich multi-modal refs (video/audio refs, edit/extend) → seedance2.
    • Need a short single beat and only MiniMax is available, or user wants Hailuo → hailuo with duration 6 or 10.

If the required model is not configured, say so and offer: another configured video vendor, upload, or Motion Graphic — do not pretend the API exists.

Briefly tell the user what you will generate before submitting.

Tool Params

ParamValuesDefault
modelseedance2, kling, hailuo, grok-imagine-video, ofox, falseedance2 when available
durationSecondsmodel-specificseedance/kling ~5; hailuo 6 or 10 (1080p → 6 only); grok 1–15; ofox 2–30 (per-model API limits)
ratiosee model docs16:9 (seedance/kling/grok/ofox); ignored on hailuo
resolution480p, 512p, 720p, 1080p, 4kprovider-specific; hailuo adds 512p for Hailuo-02; grok: 480p/720p/1080p
refVideoModefeature, basekling only, with refVideos
promptOptimizer / fastPretreatmentbooleanhailuo only
generateAudio, seed, cameraFixed, watermarkcontrolsseedance only
returnLastFrame, executionExpiresAfter, prioritycontrolsseedance only; requested last frame becomes another image asset
namedescriptive asset namerequired for good pool UX
firstFrameproject image asset refoptional
lastFrameproject image asset refseedance / kling / hailuo (requires firstFrame; not with multi-ref on seedance)
refImages / refVideos / refAudiosasset refsseedance full; kling: images + 1 feature video (no audio); hailuo: none (frames / S2V subject)
mode / shotType / multiPromptsKling multi-shotkling only

Model-specific params — see the model's reference.

Input Resolution

firstFrame / lastFrame / refImages / refVideos / refAudios all take a project asset reference. Prefer a full UUID or short prefix from read_project; asset://<id> and same-project asset URLs returned by read_project are also accepted. Per-slot type: frame slots and refImages → image; refVideos → video; refAudios → audio.

External URLs and base64 are not accepted. If the source is a public URL, download it into the project first (download_media for video/audio, submit_image for images) and pass the resulting asset id.

Workflow

Four-step loop. For each new generation, restart from Step 1 if the user's intent has shifted.

Step 1 — Align scope with the user

Before writing any prompt, align on three dimensions:

  1. Duration & segments — total length, how many shots, and whether they live in one clip or several.

    If the user has already stated a direction ("做一段", "in one video", "分别生成", "split into N shots", etc.), follow it — don't second-guess.

    Otherwise, surface the two paths and let the user pick:

    • Multi-shot within one clip (see model ref) — single inference, subject / lighting / style physically consistent across sub-shots; fits a coherent narrative within the per-clip duration cap.
    • Multiple clips — each clip is independently controllable and re-rollable, but identity and style continuity have to be carried by anchors; fits durations beyond the cap or hard scene breaks.

    Offer the trade-off; do not pick for the user.

  2. Content — what each clip depicts. Summarize back what you understood, segment by segment. When content is vague (e.g. "generate a video of a girl dancing"), the user typically hasn't specified one or more of:

    • Subject: who / what is the main subject (appearance, outfit, defining features)?
    • Action: what are they doing? (For talking / emotional shots, what micro-expression?)
    • Scene: where — setting, time of day, environmental details?
    • Lighting / color mood: what atmosphere?
    • Camera: any shot-size / angle / movement preference?
    • Style: visual style or reference (cinematic / anime / documentary / ...).

    Focus on the items that matter for this specific request and can't be safely inferred — don't turn this into a blank-filling exercise. Summarize the understood parts back to the user before proceeding.

  3. Consistency anchors — only when multiple shots reuse a character, object, or scene: identify which anchor (reference image or video) to pin across shots. For sourcing rules, see §Visual consistency across shots below.

For each dimension, check the user's words:

  • Clear — proceed.
  • Ambiguous or missing — ASK the user. Do not guess, do not default to your own interpretation. A round-trip confirmation is cheaper than a wasted generation.
What NOT to do
  • Do not "tell then submit" — announcing "I'll make this as 2 clips" and immediately submitting is not alignment, it's a unilateral decision with announcement.
  • Do not default to splitting a single-video request into multiple clips. A single clip can carry multiple sub-shots (see model ref), with subject / lighting / style physically consistent across them. Surface the trade-off, then let the user choose.
  • Do not skip the ask because you think the answer is obvious.
Hard overrides (user's explicit word wins)
  • "one clip / single clip / 一条 / 一个镜头 / in 1 clip" → never split, even if the description is objectively long.
  • "N shots / N 段 / N 个镜头" → generate exactly N.
  • "use this image / 用这张图" → use as reference, don't substitute.
Step 2 — Write the prompt

See the chosen model's reference for prompt structure and param combinations (e.g., Seedance's 8-element structure and modes; Kling's prompt tips). Before submitting, check:

  • name is a descriptive asset name — descriptive enough for the user (and you in later turns) to recognize this asset in the project library. Avoid vague names like "Untitled" or "clip 1".
  • Param combination matches the user's intent — see the Modes section in the model's reference.
  • Generated video audio is not a tool parameter (provider-side). Hailuo has no ratio/multi-ref; do not invent those params.
  • On validation failure, read the error and fix the inputs — do not blindly retry the same invalid arguments.
Step 3 — Submit one, wait, confirm

Submit one generation job at a time. Unless the user explicitly asked for multiple clips in parallel, do not submit the next clip until the current one completes and the user has reviewed it. Parallel submission hides problems: if the first shot has drift or wrong framing, the user would rather redo it once than have several misaligned shots to discard.

  • submit_video.ratio controls the generated asset only; it does not change the project timeline canvas. If the user requested a final output aspect ratio (for example "9:16 vertical" or "16:9 landscape"), set the timeline canvas to the same ratio with manage_timelines action=update (e.g. ratio:"9:16") before placing the completed asset. If the user asked for no black bars / full-bleed, pass fit:"cover" when setting the canvas or updating/adding the visual item.
  • Do not use this skill for job management — use the track_progress tool for status/wait.
  • After submitting, end your turn (tell the user the job was created) unless a follow-up task is already queued.
  • When the job finishes, surface the result to the user for review before proceeding to the next shot.
  • Model-specific failure handling — see the model's reference.
Show full SKILL.md (812 more words)Show less
Step 4 — Iterate

When the user wants a next clip, a revision, or a continuation:

  • If it's the next shot in a multi-shot sequence — reuse the established anchor (see §Visual consistency across shots below for principles, model ref for flag-level details).
  • If the user's feedback is ambiguous ("it doesn't feel right") — ask what specifically to change before regenerating.
  • If the same text-prompt adjustment has failed twice — stop adjusting text. Switch to reference images, or switch to edit mode where the model supports it (see model ref).
  • Each new generation restarts the loop at Step 1 — realign if scope shifted.

Visual consistency across shots

Text alone cannot reliably maintain visual identity across shots; visual references constrain output far more precisely than words.

Anchors: the cornerstone of consistency

An anchor is a reference image or video pinned across every shot that shares the same character, object, or style. Any multi-shot sequence with recurring visual elements needs an anchor — don't try to reproduce them from text.

Sourcing an anchor

Have reference awareness. When the user's request involves a recurring character / object / scene, think about what anchor to use before writing prompts:

  • Check the project first. What has the user already provided or approved? Uploaded images, previously generated and approved shots, or earlier project assets can all serve as anchors.
  • Match the user's intent. If the user pointed to a specific asset ("use this photo", "像上一段那样"), use that. If they described a character only in words, no anchor exists yet and one must be established.
  • When in doubt, ask the user. Don't guess which asset to pin, and don't silently generate a new anchor when the user may already have one in mind.

When no existing asset fits and one must be generated, propose it to the user first — it shapes every downstream shot. Model-specific paths — see the chosen model's ref.

Using the anchor
  • Pass the anchor in every shot that shares the character / object / style. The specific flag(s) to use depend on the model — see the model's ref.
  • Describe the anchor by appearance in the prompt, not by name: "The BLACK RACING CAR with chrome exhaust" constrains far more than "Fleetmaster". When role confusion is likely, add explicit negations: "The motorcycle does NOT transform."
  • Refer to the anchor with @Image1 / @Video1 in the prompt — not vague phrases like "the same car as before".
  • When a shot depends on a previous generation, wait for the previous job to complete (via track_progress with action=wait) to obtain its assetId, then pass it as the anchor reference. Do not submit dependent shots in parallel.
Multi-character projects

When a project has multiple named characters with distinct attributes (e.g. Faz with fire energy, Kev with ice energy), treat each character as a separate anchor — one reference asset per character. In every prompt:

  • Name the active character and attach their distinctive attributes ("Kev has blue ice electric energy").
  • Add explicit negations for the others to prevent attribute leakage ("NOT red fire energy, NOT Faz's look").
  • Pin the correct character's anchor (model-specific flag — see model ref). Do not reuse another character's anchor by accident.

Missing either explicit attribution or negation causes cross-character attribute mixing.

Multiple characters in the same frame. For shots where multiple characters appear together (especially facing the camera), the model is prone to face-swap or body-clipping. Add strong positional + outfit anchors to each character and prefer a fixed camera for that shot:

  • "the character on the LEFT wears a grey-blue tactical jacket, short beard, silver earring"
  • "the character on the RIGHT wears a red cape with gold trim, long braided hair"
  • "fixed camera, medium shot, both characters clearly separated"

Positional words (left / right / foreground / background) + distinctive outfit colors give the model enough signal to keep the characters apart.

Escalate when text adjustments fail

If a visual-identity issue (wrong character, drift, color mismatch) persists after two text-prompt adjustments on the same shot, stop adjusting text. Text is not a substitute for an anchor. Escalate to:

  • Adding or switching the anchor.
  • Edit mode where the model supports it (see model ref for how to invoke).

Do not submit a third text-only retry on the same consistency issue.

When to skip anchoring

Simple, one-off, or exploratory requests do not need anchors — generate directly.

Run

ts
// Text-to-video (seedance2 default)
submit_video({
  model: "seedance2",
  prompt: "A cat walks across a sunny windowsill",
  name: "Cat on windowsill",
});

// Image-to-video with seedance2 — pass the project asset id directly; the server resolves the asset's media URL
submit_video({
  model: "seedance2",
  prompt: "The scene comes to life, gentle breeze rustles the curtains",
  firstFrame: "abc12345",
  name: "Living room animation",
});

// Kling text-to-video — only after Model Selection check
submit_video({
  model: "kling",
  prompt: "A sports car drifts around a wet corner",
  name: "Car drift shot",
});

// MiniMax Hailuo — 6s or 10s; optional firstFrame / lastFrame (with first)
submit_video({
  model: "hailuo",
  prompt: "A ceramic cup steams on a wooden table, soft morning light [Push in]",
  durationSeconds: 6,
  resolution: "720p",
  name: "Coffee steam morning",
});

After submission, call the track_progress tool: action=status jobIds=<jobId> to poll, action=wait jobIds=<jobId> to block until terminal.

Config Mode

For complex multimodal jobs, build the full args object up front and pass it in a single call:

ts
submit_video({
  model: "seedance2",
  prompt: "...",
  name: "...",
  firstFrame: "abc12345",
  refImages: ["def67890", "ghi24680"],
  refVideos: ["abc99999"],
  refAudios: ["jkl55555"],
  durationSeconds: 8,
  ratio: "9:16",
});

Rules

  • Always provide --name with a descriptive asset name.
  • Default to submit-only. End your turn after submitting unless a follow-up task is queued.
  • Do not call this skill with --job, --wait, or --timeout — job management belongs to track_progress.
  • Before submitting, briefly tell the user model + duration + what will be generated.
  • Place completed assets with edit_item only after the user wants them on the timeline (pool-first contract).

© 0xsline, AGPL-3.0. 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 6 other files (references) in src/agent/skills/video-gen of 0xsline/OpenChatCut.

  • SKILL.md
  • references/fal.md
  • references/grok-imagine-video.md
  • references/hailuo.md
  • references/kling.md
  • references/ofox.md
  • references/seedance2.md

Open the folder on GitHubat commit 2e6f4a2

Compare with similar skills

AI Video Generation 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.

AI Video Generation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AI Video Generation this skill0xsline/OpenChatCut2.2k—~4.3kAutomated safety check: PassAGPL-3.0
Video-to-Sprite Animation Generator0x0funky/agent-sprite-forge4.4k—~3.8kAutomated safety check: PassMIT
VideoNexus-JPF/note-companion8703 repos~3.6kAutomated safety check: PassMIT
AI Video Gencalesthio/OpenMontage66k—~3kAutomated safety check: PassAGPL-3.0
AI Video Gencalesthio/OpenMontage66k—~2.8kAutomated safety check: PassAGPL-3.0
Atlas Cloudcalesthio/OpenMontage66k—~1.2kAutomated safety check: PassAGPL-3.0

Similar skills

  • Video-to-Sprite Animation Generator

    0x0funky/agent-sprite-forge

    Turns one approved master still into a full set of animated action clips for a character, one image-to-video take per action, then packages them for a game engine.

    4.4k GitHub stars~3.8k tokensUpdated 4 days ago
    Media & CreativeAuto-check passed

  • Video

    Nexus-JPF/note-companion

    When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks.

    870 GitHub starsUsed in 3 repos~3.6k tokens
    Media & CreativeAuto-check passed

  • AI Video Gen

    calesthio/OpenMontage

    Generate AI videos from text prompts using multiple provider gateways.

    66k GitHub stars~3k tokensUpdated 7 days ago
    Media & CreativeAuto-check passed

  • AI Video Gen

    calesthio/OpenMontage

    Generate AI videos from text prompts using multiple provider gateways.

    66k GitHub stars~2.8k tokensUpdated 7 days ago
    Media & CreativeAuto-check passed

  • Atlas Cloud

    calesthio/OpenMontage

    Generate or edit images and videos through the Atlas Cloud gateway.

    66k GitHub stars~1.2k tokensUpdated 7 days ago
    Media & CreativeAuto-check passed

  • Seedance 2 0

    calesthio/OpenMontage

    Generate cinematic clips with ByteDance Seedance 2.0 — the preferred premium video model in OpenMontage when a paid gateway is configured.

    66k GitHub stars~4.4k tokensUpdated 7 days ago
    Media & CreativeAuto-check: notes

More from 0xsline/OpenChatCut

All 31 skills in this repo

  • OpenChatCut Video Editing

    0xsline/OpenChatCut

    Connects an MCP-capable agent to the local OpenChatCut video editor to inspect and edit projects through draft edit sessions, with manual approval by default.

    2.2k GitHub starsUsed in 1 repo~655 tokens
    Auto-check passed

  • Video Shader Generator

    0xsline/OpenChatCut

    Generates WebGL shaders for video effects, transitions, masks and color grades in the OpenChatCut editor, trying built-in catalog effects such as zoom before making anything new.

    2.2k GitHub starsUsed in 1 repo~3.2k tokens
    Auto-check passed

  • AI Image Generation

    0xsline/OpenChatCut

    Generates still images through the submit_image tool, choosing among Fal.ai, gpt-image-2, nano-banana, MiniMax image-01 and Grok Imagine by configured keys.

    2.2k GitHub stars~1.3k tokensUpdated 3 days ago
    Auto-check passed

  • Livestream to Clips

    0xsline/OpenChatCut

    Cuts a livestream recording into evidence-backed, platform-ready clips by combining transcript, visual, audio and genre-specific signals.

    2.2k GitHub stars~2.7k tokensUpdated 3 days ago
    Auto-check passed

  • Music Generation

    0xsline/OpenChatCut

    Generates instrumentals, songs, soundtracks and covers through Mureka, MiniMax, Atlas Cloud or Sonilo using the `submit_music` tool.

    2.2k GitHub stars~1.1k tokensUpdated 3 days ago
    Auto-check passed

  • Video Voiceover And SFX Generator

    0xsline/OpenChatCut

    Generates text-to-speech narration and custom sound effects for a video timeline, keeping existing voiceover in sync after visual retiming edits.

    2.2k GitHub stars~4.4k tokensUpdated 3 days ago
    Auto-check passed

Works with

Categories

Questions about AI Video Generation

What does AI Video Generation do?

Submits AI video generation jobs to Fal.ai, Seedance, Kling, MiniMax Hailuo, xAI Grok Imagine or OFox for text-to-video, image-to-video, transitions and clip extension. Each call submits one video generation job and returns a jobId. Waiting and status checks belong to a separate track_progress tool, and the skill does not place the finished clip on the timeline.

When should I use AI Video Generation?

AI Video Generation fits situations like: generating a short clip from a text prompt; animating a still image into a video clip; building a transition between a first and a last frame; extending or regenerating part of an existing clip with AI.

How do I install AI Video Generation in Claude Code?

Run `npx skills add 0xsline/OpenChatCut --skill video-gen -a claude-code`. Or copy the skill folder (src/agent/skills/video-gen in 0xsline/OpenChatCut) into .claude/skills/video-gen in your project. Claude Code loads it when a task matches its description.

How do I install AI Video Generation in Codex?

Run `npx skills add 0xsline/OpenChatCut --skill video-gen -a codex`. Or copy the skill folder (src/agent/skills/video-gen in 0xsline/OpenChatCut) into .agents/skills/video-gen in your project. Codex loads it when a task matches its description.

Can I use AI Video Generation 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 0xsline/OpenChatCut --skill video-gen -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-gen, .gemini/skills/video-gen, .github/skills/video-gen and .opencode/skills/video-gen in your project.

What does AI Video Generation need to run?

SKILL.md names no scripts, command-line tools or credentials: AI Video Generation is instructions for the agent only. Our summary lists: An API key configured for at least one supported video vendor.

Does AI Video Generation 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 AI Video Generation 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 AI Video Generation use?

AI Video Generation is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does AI Video Generation use?

About 4.3k tokens (SKILL.md is roughly 17k 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 9.8k tokens, read only when the agent opens those files.

What are the alternatives to AI Video Generation?

Skills that share tags, products or a category with AI Video Generation: Video-to-Sprite Animation Generator (0x0funky/agent-sprite-forge, 4.4k stars), Video (Nexus-JPF/note-companion, 870 stars), AI Video Gen (calesthio/OpenMontage, 66k stars) and AI Video Gen (calesthio/OpenMontage, 66k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Video Generation?

0xsline (a GitHub user) maintains it in 0xsline/OpenChatCut, which has 2,235 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on October 7, 2026.

Source: 0xsline/OpenChatCut on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.