video-director
Canonical entrypoint for every AI chat request that asks to make, generate, plan, or edit a video, including promotional films, ads, short videos, product videos, reference-image videos, image-to-video, first/last-frame transitions, storyboard/keyframes, character talking-head videos, 宣传片, 广告片, 短视频, 视频, 口播视频, 分镜图, 图片转视频, and 商品宣传片. Do not invoke cosyvoice-ssml or tts-director as the first response to a video request. This skill must draft a script and shot table, generate storyboard contact-sheet preview images through image.generate, ask the user to confirm the script plus storyboard together
npx skills add Jamailar/Beav --skill video-director --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Directs video requests by drafting a concise script and shot table, then generating storyboard contact-sheet preview images, and awaiting user confirmation before any video generation. It serves as the canonical entrypoint for requests to make, generate, plan, or edit videos, including promotional films, ads, short videos, product videos, and related formats. It must not invoke cosyvoice-ssml or tts-director as the first response. It drafts a script and shot table, generates storyboard preview images via image.generate, asks the user to confirm the script plus storyboard together, and only then calls video generation.
How it works
- plan_draft: Clarify the intended video mode and assets, then draft a concise but detailed video script and shot table.
- storyboard_preview: Immediately after the shot table exists, generate storyboard contact-sheet preview image(s) with Operate(resource="image", operation="generate", input={ ... }).
- user_review: Show the script, storyboard preview image(s), and explicit video specs; ask the user to confirm or revise.
- production_prep: After confirmation, decide whether this should be a <=15s single upstream clip, a long video_sequence, or a manual editor/workflow. Do not use a project pack unless explicitly requested.
- tts_if_needed: If the task is a character talking-head / 口播 video, complete the TTS-first workflow as described.
- video_generate: After confirmation and any required TTS, call Operate(resource="video", operation="generate", input={ ... }).
When to use it
Activate before any video generation when the user asks for promotional or reference-image videos (e.g., 宣传片, 广告片, 短视频, 视频, 口播视频, 分镜图, 图片转视频). Do not start from cosyvoice-ssml; load this skill and follow its staged workflow.
What it can touch
The skill uses the tool workflow to generate images for storyboards and, after user confirmation, to generate video. It explicitly invokes Operate with resource="image" for storyboard previews and eventually resource="video" for generation. It also manipulates script and shot-table data internally for review by the user.
Caveats
- Must not invoke cosyvoice-ssml or tts-director as the first response to a video request.
- Video generation is performed only after the user confirms the script and storyboard.
- A storyboard preview is mandatory after the script is written and before video generation.
- A video project pack is not created by default unless explicitly requested by the user.
# Video Director Use this skill before calling `Operate(resource="video", operation="generate", input={ ... })` for video work. For AI chat, this skill is the single entrypoint for video generation. If the user says "做一个口播视频", "生成一个视频", "产品宣传片", "广告片", "数字人视频", or any similar video request, invoke `video-director` first. Do not start from `cosyvoice-ssml`; that skill is an internal digital-human TTS substep and must not drive the video workflow. If this skill was loaded because the user attached an image and asked for a promotional film / 宣传片 / 视频, treat the attached image as a product or visual reference for the video workflow. Do not generate a replacement product image as an "analysis" step. ## Default Workflow Treat the workflow as a gated state machine. Do not skip or reorder states: 1. `plan_draft`: Clarify the intended video mode from the user's goal and assets, then draft a concise but detailed video script and shot table. 2. `storyboard_preview`: Immediately after the shot table exists, generate storyboard contact-sheet preview image(s) with `Operate(resource="image", operation="generate", input={ ... })`. The storyboard image is a preview of the planned shots, not a stand
- Default Workflow
- Asset-Library Character Talking-Head Rule
- Video Project Pack Rule
- Hard Rules
- Mode Selection
- Production Strategy
- Storyboard-First Rule
- Core Environment Reference Image
- Storyboard Contact-Sheet Preview
- Prompt Consistency Rules For Keyframe Images
- Keyframe Generation Order
- Script Format
- Prompt Discipline
- Tool Usage
What does the video-director skill do?
Canonical entrypoint for every AI chat request that asks to make, generate, plan, or edit a video, including promotional films, ads, short videos, product videos, reference-image videos, image-to-video, first/last-frame transitions, storyboard/keyframes, character talking-head videos, 宣传片, 广告片, 短视频, 视频, 口播视频, 分镜图, 图片转视频, and 商品宣传片. Do not invoke cosyvoice-ssml or tts-director as the first response to a video request. This skill must draft a script and shot table, generate storyboard contact-sheet preview images through image.generate, ask the user to confirm the script plus storyboard together
How do I install it?
Run `npx skills add Jamailar/Beav --skill video-director --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From Jamailar/Beav, a repository with 1,349 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.