跳到正文
cccskills
免费在 GitHub 公开

Meme Video

Turn an approved meme idea, image, or short source into a concise humorous video draft with a clear hook, caption plan, and platform variants.

中文简介正在准备中。当前显示原文说明。

实测评分 未实测

查看安装方法

包含的文件(1)

  • SKILL.md3.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Meme Video

Mission

Create a short humorous video draft from a supplied meme concept, image, character, product, or short source. Make the joke legible through setup, escalation, payoff, caption timing, and a deliberate end frame. Do not promise virality, reuse copyrighted material without permission, or turn a real person into a joke without authorization.

Required inputs

  • joke premise, reference meme, source clip, or image;
  • audience, tone, language, platform, duration, ratio, and caption style;
  • characters/products/brands that must remain recognizable;
  • text, punchline, CTA, and facts that are approved versus proposed;
  • rights/consent for source media, likeness, music, and brands; and
  • variant count, budget, reviewer, and definition of done.

If the user gives only “make it funny,” propose two or three distinct joke structures and ask them to select one before rendering. Do not invent a defamatory allegation or present a generated depiction as a real event.

Build the meme beat sheet

Keep the visual and text timing explicit:

BeatTimeVisualSpoken/on-screen textPayoff
Hookopeningrecognizable setupshort premiseviewer understands context
Escalationmiddleaction/reactionminimal supporting texttension or surprise
Punchlineendreveal/reaction/loopapproved punchlineclear comedic turn

Keep captions short, high contrast, and readable without sound. Preserve the original image or product when it is the joke's anchor; use an image-led path instead of asking a text-only model to recreate an exact mark.

Execute

  1. Freeze the selected joke, wording, source roles, and rights state.
  2. Use the adjacent image agent or an available image capability for a still meme frame only when needed. Review text, likeness, product, and brand fidelity before animating.
  3. Choose T2V, I2V, or edit from MODELS.md and inspect the live schema. Resolve fields through muapi-video-tools.md.
  4. Generate a small set of controlled variants: change timing, reaction, camera, or caption treatment one variable at a time.
  5. Poll jobs and review the full clip for joke clarity, visual drift, caption timing, audio, crop, and unintended offensive or misleading implications. Use video QA.
  6. Return the strongest draft and rejected/failed branches. Do not publish or label an editorial score as audience performance.

Output contract

Return joke premise, beat sheet, source/rights state, variant matrix, model/endpoint, prediction IDs, output URLs, caption status, QA findings, and next iteration. Save permitted artifacts under .video/ using reports-and-receipts.md.

Meme generation is draft-only. Do not target a private person for harassment, create deceptive political content, or use a minor's likeness.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

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

中文简介正在准备中。当前显示原文说明。

SamurAIGPT/open-ai-video-agent82026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.

中文简介正在准备中。当前显示原文说明。

SamurAIGPT/open-ai-video-agent82026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.

中文简介正在准备中。当前显示原文说明。

SamurAIGPT/open-ai-video-agent82026年8月28日 更新

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

中文简介正在准备中。当前显示原文说明。

SamurAIGPT/open-ai-video-agent82026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.

中文简介正在准备中。当前显示原文说明。

SamurAIGPT/open-ai-video-agent82026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.

中文简介正在准备中。当前显示原文说明。

SamurAIGPT/open-ai-video-agent82026年8月28日 更新

查看 SamurAIGPT 的全部技能

报告此技能的问题