本文へ移動
cccskills
無料GitHub で公開

Social Video

Turn brand context and a social brief into platform-aware copy, storyboard, reference frames, and video drafts without publishing them.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md3.3 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Social Video

Mission

Create a social-first video package from a brand brief. Read the available brand system, audience, and messaging context; produce an honest hook and storyboard; then create platform-specific video drafts with explicit assumptions. This skill does not publish, promise virality, or invent brand facts.

Collect brand and platform context

Look for approved project files such as brand-identity.md, ICP.md, messaging.md, a campaign brief, or .video/project.md. If a file is absent, continue with what is available and record the gap.

Collect:

  • platform, audience, language, target ratio, duration, captions, and CTA;
  • brand tone, palette, product/visual invariants, approved words, and claims;
  • hook, offer, proof source, disclosure, creator/talent, and music policy;
  • reference assets and rights/consent state; and
  • variant count, budget, reviewer, and definition of done.

Do not treat a generic platform “best practice” as a current platform rule. Ask for or verify the rule set when compliance matters.

Build the package

  1. Write the social post draft: hook, body, CTA, accessibility text, and clearly labeled claims. Keep performance predictions as hypotheses.
  2. Convert it into a compact storyboard with time ranges, visual beat, spoken words, on-screen text, camera direction, audio, and transition.
  3. Create an image/reference frame through the adjacent image agent or an available image capability when product, character, or brand fidelity needs an anchor. Obtain review before animating expensive dependent shots.
  4. Turn the storyboard into a technical director brief using Cinematic Direction principles. Use MODELS.md and live schema discovery; do not assume all platforms or model families share the same duration/ratio enum.
  5. Upload local references, submit one or a small number of variants, retain prediction IDs, and poll with media.check_result.
  6. Generate captions only after selecting a candidate. Proofread claims, names, numbers, timing, contrast, and safe areas with video QA.

Change one meaningful variable per variant—opening visual, hook, pacing, proof, presenter, or CTA layout. Keep the product and approved claims fixed unless the experiment explicitly changes them.

Output contract

Return brand inputs and missing files, post copy, storyboard, director brief, platform assumptions, model/endpoint, prediction IDs, output URLs, variant matrix, caption status, QA findings, and disclosure/rights gaps. Save permitted plans and receipts under .video/ using reports-and-receipts.md.

Social drafts are not publication-ready by default. Do not connect accounts, schedule posts, or claim engagement results from this skill.

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Plan draft video-ad variations from supplied performance evidence, preserving the distinction between observed data and creative hypotheses.

日本語の概要は準備中です。原文の説明を表示しています。

SamurAIGPT/open-ai-video-agent72026年8月28日 更新

Create authorized presenter, avatar, and UGC-style video drafts with explicit voice, likeness, consent, and synthetic-media handling.

日本語の概要は準備中です。原文の説明を表示しています。

SamurAIGPT/open-ai-video-agent72026年8月28日 更新

Analyze a script or existing edit, identify visual gaps, and generate supplemental B-roll coverage with clear parent and factual-status labels.

日本語の概要は準備中です。原文の説明を表示しています。

SamurAIGPT/open-ai-video-agent72026年8月28日 更新

Build a consented continuity system for an authorized person, fictional character, product, or world across video shots.

日本語の概要は準備中です。原文の説明を表示しています。

SamurAIGPT/open-ai-video-agent72026年8月28日 更新

Translate creative intent into coherent cinematography, framing, camera, lens, lighting, motion, and sound direction for a video shot.

日本語の概要は準備中です。原文の説明を表示しています。

SamurAIGPT/open-ai-video-agent72026年8月28日 更新

Create a non-explicit romantic scene from authorized adult references with clear consent, identity boundaries, and synthetic-media labeling.

日本語の概要は準備中です。原文の説明を表示しています。

SamurAIGPT/open-ai-video-agent72026年8月28日 更新

SamurAIGPT のスキルをすべて見る

このスキルの問題を報告する