本文へ移動
cccskills
無料GitHub で公開

create-kinetic-typography

Render a deterministic text-only video ad from approved copy, font, colors, timing and CTA. Use when a brand needs an animated message without product photography or a creator.

インストール方法を見る

含まれるファイル(4)

  • SKILL.md2.2 KB
  • scripts/config.example.json394 B
  • scripts/render.py5.1 KB
  • skill.meta.json263 B

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。

Kinetic typography

Render approved text as a silent video using the bundled renderer. No generation service is required. Review the complete copy and motion before delivery.

Inputs

The configuration contains an even canvas size, frame rate, local font file or automatic system font, background/text/accent colors, text beats and a final CTA. Each beat has text, duration in seconds and an animation: punch, typewriter or rise. The renderer's help describes its arguments. The example configuration is a neutral layout sample; replace every creative value with the approved brief.

Workflow

  1. Lock supported copy, CTA and brand styling. Ask only for unresolved creative choices.
  2. Write the configuration. Hold every beat for 1.5–10 seconds and allow at least three seconds for the CTA. Long copy is wrapped; excessive lines or an oversized word are rejected. Split copy into more beats instead of shrinking it.
  3. Render the video and optional contact sheet with the bundled renderer. It uses Pillow and ffmpeg and makes no paid calls.
  4. Inspect the full video and sheet: readable holds, safe text, intact letters, correct colors/font and complete ending. Review motion as well as held frames.
  5. If audio is requested, use a supplied cleared track or separately approved generation. Its cost and final audio check are additional to this silent format.

Output and checks

The output is an H.264 video, a render manifest and an optional contact sheet. Text stays in the central safe region. Verify dimensions, duration, beginning, animation settles and final CTA. A rendered manifest establishes media production; final creative acceptance requires viewing.

Failure modes

Missing fonts fail clearly; an explicitly supplied font is never substituted. Short or crowded beats fail before rendering. Provide shorter copy or more beats. This complete-video renderer supports three motions; the canonical overlay workflow also describes other effects, which are not promised by this command.

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

Research supported advertising promises from a specific buyer's context, current product facts, customer language and observed ads. Turn them into static, video or copy ideas; match video ideas to actual recipes and save a product-scoped angle bank for write-video-ad-script. Product-led discovery can use verified facts without reviews. Reference persistence and reach are observations, not proof of performance.

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。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift recommendations and scenario modeling.

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。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

For paid lead-gen and participant-recruitment ads, replaces vanity CPA with true CAC per qualified lead by joining ad-platform data with downstream funnel events, surfaces tracking gaps, and classifies every creative into Scale / Keep / Investigate / Cut.

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。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

The intake stage of a Meta ad harness. Researches the brand first, states what it assumes, and asks only what it cannot infer and what would change money, claims or legal exposure if guessed wrong — at most four questions a turn, in plain business language. Writes the brand's stable facts (ads/brand.md), the campaign brief, and a log of what was asked vs assumed. Use it when someone wants to run Meta ads and the brand's ad facts are not yet recorded.

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。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

Analyze the message match between your ads and landing pages. Checks if the promise in the ad copy carries through to the landing page headline, body, and CTA. Flags disconnects that kill conversion rates. Works with Google, Meta, and LinkedIn ads.

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。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

Turn a brand's facts, a campaign brief and the product into a one-minute Meta ad strategy with its reasoning — goal, audience, objective and placements, budget split, how many ads and how different they must be (generate 3x so the user can choose), the test frame, the success metric, and safety rules for the user to accept. Decides what launch-meta-ad-campaign then executes, and re-reads the strategy after a deep check to show which assumption changed. Use it after intake and before any creative is generated or any campaign is built.

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。

gooseworks-ai/goose-skills1,2452026年10月13日 更新

gooseworks-ai のスキルをすべて見る

このスキルの問題を報告する