メニュー
Generate short-form video clips via a 5-stage human-in-the-loop pipeline: concept, keyframes, video generation, and delivery.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Embed C2PA (Content Authenticity Initiative) provenance manifests into SocialForge AI-generated assets — images, video, audio. Use when: preparing AI-generated social posts for EU markets to comply with EU AI Act Article 50 (applicable 2 Aug 2026); making AI generation disclosure machine-readable; signing already-generated assets retroactively; auto-signing newly generated assets when c2pa_auto_sign is enabled in brand profile.
Adapt post copy per platform — character limits, hashtags, CTAs, tone, and compliance checking.
Set up and manage brand profiles. Use when: configuring a new brand, updating brand config, or switching brands.
Core creative engine. Generates images and video using 4 modes with brand assets, AI compositing, and platform resizing.
Run the complete end-to-end production pipeline — parse, match, compose, copy, preview, review, finalize.
Index brand photo library using AI vision. Use when: setting up assets, adding new photos, or refreshing the index.
| name | generate-video |
| description | Generate short-form video clips via a 5-stage human-in-the-loop pipeline: concept, keyframes, video generation, and delivery. |
| argument-hint | [--post <id>] [--script-only] [--thumbnail] |
| effort | high |
| user-invocable | true |
Generate video production assets through a 5-stage human-in-the-loop pipeline. Each stage requires user approval before advancing.
Asset-heavy skill. Grep before Read the asset catalog (${CLAUDE_PLUGIN_DATA}/<brand>/assets/index.json) — never list the asset directory. Reference generated images / videos by path, not by loading metadata. Brand profile loads once per session.
/socialforge:setup:
/socialforge:switch-brand if needed)/socialforge:parse-calendar) with video posts identifiedClaude generates 2-3 video concept ideas based on the post brief, brand voice, and platform requirements. Each concept includes:
The user picks one concept (or requests refinements) before proceeding.
Generate 2 first-frame options based on the chosen concept. These set the opening visual and establish the look and feel.
Generate 2 last-frame options that complete the visual narrative arc, matching the approved first frame.
Using the approved first and last frames, generate 2 video versions via WaveSpeed's Kling v3.0 Pro image-to-video endpoint (3-15 seconds).
After the user picks the final video, post-processing runs before saving:
Save all final assets to {post_folder}/ -- keyframes in keyframes/, video versions in versions/, platform-resized final videos in final/:
| Asset | Format | Always Generated |
|---|---|---|
| Script | Markdown | Yes |
| Storyboard | Markdown + keyframe images | Yes |
| Thumbnail | PNG/WebP (via compose-creative) | Yes |
| First frame | PNG | Yes (Stage 2) |
| Last frame | PNG | Yes (Stage 3) |
| AI Video Clip | MP4 via WaveSpeed / Kling v3.0 Pro (image-to-video, 3-15 seconds) | If pipeline completed |
| SRT subtitles | .srt | If video generated |
| Type | Duration | AI Generation | Production Notes |
|---|---|---|---|
| hero_video | 30-90s | Partial — AI generates 3-15s hero clip; full version needs filming | Script + storyboard + AI teaser clip |
| mini_case_study | 30-60s | Yes — AI animation from keyframes | Full pipeline supported |
| short_reel | 15-30s | Yes — ideal for AI generation | Full pipeline supported |
| story | 15s | Yes — image-to-video animation | Full pipeline supported |
| talking_head | 30-120s | No — needs filming | Script + storyboard only (use --script-only) |
--script-only skips Stages 2-4 and generates script + storyboard only--thumbnail generates a video thumbnail via compose-creative (independent of the pipeline){post_folder}/ -- keyframes in keyframes/, video versions in versions/, final video in final/