
seedance-meme-comedy
A short skit where every beat is laid down to serve one punchline. The joke has to land on something visible, and the absurdity only works when the camera and the physics stay dead serious. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Twist-ending comedy skit; 中文触发词: 反转结尾搞笑短片, 搞笑, 反转, 梗, 沙雕), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
- Installs
- 62
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/learnprompt/awesome-seedance --skill seedance-meme-comedy- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads seedance-meme-comedy automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Twist-ending comedy skit · 反转结尾搞笑短片
A short skit where every beat is laid down to serve one punchline. The joke has to land on something visible, and the absurdity only works when the camera and the physics stay dead serious.
This Skill carries one prompt structure distilled from 40 human-verified Seedance cases on goodcase.ai. It is a sibling of seedance-prompt-library (all templates in one Skill); install this one when you only want this kind of clip. Do not invent structure from general video-generation knowledge: follow the structure below and ground the draft in one anchor case from references/cases.md.
Use when
- Meme clips, prank and revenge skits, absurd scale gags, family comedy — anything whose payload is one laugh at the end.
- 中文:玩梗片、整蛊和复仇小剧场、荒诞比例梗、家庭喜剧,任何有效载荷就是结尾那一下笑的片子。
Workflow
- Collect inputs. Ask only for what is missing: subject or product, setting, duration, aspect ratio, whether reference images / audio exist, and which language the final prompt should be in.
- Pick one anchor case. Read
references/cases.md, choose the case closest to the request, and name it in the reply. One anchor, never an average of several. - Fill the structure block by block. Every block below must be present in the final prompt; an empty block is where prompts go vague.
- Opening line: duration, look (ultra-realistic or photorealistic absurd), the genre named as comedy, and whether there are reference images
- Character cards: appearance plus a personality written as an emotional arc, such as playful then shocked and embarrassed
- Location: an ordinary low-budget real place, described plainly
- Timecoded beats with headings, running from hook to punchline
- Spoken lines written into the beat where they are said, one sentence each
- Bystander reactions and the closing expression as their own beat
- Negative list: no gore, no teleportation, no duplicated people, no subtitles or on-screen text
- Apply the guidance and check the pitfalls (next two sections) before returning anything.
- Return the finished prompt as one copy-pasteable block, the anchor case link, and a three-line checklist of what to verify in the generated video.
Guidance (from the cases)
- Fix where the laugh lands first, then work backwards. The duck wizard case names its sections
Hook,The Spell,Countdown,Twist,Reaction,Punchlineand puts the payoff in the 26–30 second slot. - Make the twist a visible object. The whole FIVE MORE MINUTES skit pays off on a close-up of
one black sneaker and one grey sneaker. - Keep the camera and the physics straight-faced. The hotel pool case says outright that
The humor comes from the impossible scale and the dead-serious realism, and shoots itRecorded like a viral smartphone clip. - Give the bystanders their own beat. The subway skit has one passenger laugh first and then the whole carriage; the Turkish ice cream vendor
raises his hands in playful defeat. - Write the safety edges of any violence into the body text. The subway skit breaks the glass
with no injury or goreand bansregenerating glassandteleportationin the negative list.
Pitfalls
- Describing the joke with adjectives like funny or hilarious. The model has nothing to act on; replace them with one concrete action or object.
- Firing the twist with no pause before it. FIVE MORE MINUTES holds
one silent secondon the two of them before they both start laughing. - Asking the model to render end text. The duck wizard case closes on
Never rush a spellplus emoji, which comes out garbled — leave a clean tail frame and add the text in post. - Letting a character's mood flip without a written trigger. The subway skit spells out the man's arc as
playful, then shocked and embarrassedand gives each stage its own on-screen cause.
Language
Reply in the user's language. The prompt itself can stay in English when that is what the user's Seedance workflow expects; ask if unclear. The Chinese version of this structure follows.
中文:反转结尾搞笑短片
所有节拍都为一个笑点服务的短剧。笑点得落在一个看得见的东西上,荒诞设定要配一本正经的相机和物理才立得住。
结构:
- 开场一句:时长、画风(ultra-realistic 或 photorealistic absurd)、片种写明是 comedy、有没有参考图
- 角色卡:外貌加一句性格,性格写成情绪弧,比如 playful, then shocked and embarrassed
- 场景:一个普通的、便宜的真实地方,平铺直叙写
- 带小标题的时间码分段,从 hook 一路推到 punchline
- 台词写进它被说出的那一拍,每句一句话
- 旁人反应和收尾表情单独占一拍
- 负面清单:禁血腥、禁瞬移、禁复制人、禁字幕和上屏文字
要点:
- 先钉死笑点落在哪一秒,再往回铺。女巫变鸭那条直接把段落命名成
Hook、The Spell、Countdown、Twist、Reaction、Punchline,兑现放在 26–30 秒那一槽。 - 反转得是一个看得见的东西。FIVE MORE MINUTES 整条片子押在脚部特写
one black sneaker and one grey sneaker上。 - 相机和物理要一本正经。酒店泳池那条自己写明
The humor comes from the impossible scale and the dead-serious realism,镜头是Recorded like a viral smartphone clip。 - 旁人的反应单独给一拍。地铁那条先让一个乘客笑,再让全车笑;土耳其冰淇淋那条让摊主
raises his hands in playful defeat。 - 暴力桥段的安全边界写进正文。地铁那条玻璃碎了但
with no injury or gore,负面清单里又禁掉regenerating glass和teleportation。
常见坑:
- 用 funny、hilarious 这类形容词描述笑点。模型没东西可演,要换成一个具体动作或物件。
- 反转前不留停顿就直接炸。FIVE MORE MINUTES 在两个人笑出来之前先停了
one silent second。 - 让模型画结尾文字。女巫变鸭那条收在
Never rush a spell加表情符号,生成出来大概率是乱码,应该留干净收尾画面,文字后期加。 - 角色情绪没有写明触发就翻转。地铁那条把男生的弧线写成
playful, then shocked and embarrassed,每一段都在画面里给了起因。
Copy-ready lead-in / 可复制引导语
For users who would rather paste into a chat model than run this Skill, hand them this line above the structure:
I want a short comedy clip with a twist ending. [Setup: a man quietly stuffing food into his bag at a buffet.] [Twist: he opens the bag at home and the restaurant owner's cat climbs out.] Using the prompt template below, rewrite it into one ready-to-use Seedance video prompt for me:
我要做一条有反转的搞笑短片,【设定是一个人在自助餐厅偷偷往包里塞食物】,【反转是他回家打开包,钻出来一只餐厅老板的猫】。请根据下面这个提示语模板,帮我改写成一条可以直接用的 Seedance 视频提示语:
Notes
references/cases.mdis generated fromdata/in LearnPrompt/awesome-seedance and refreshed daily; do not hand-edit an installed copy.- Prompts in the reference file belong to their creators (linked on every card). Transfer the structure; do not present a close copy as original work.
- For the full library across every model, install the
goodcaseSkill from LearnPrompt/goodcase-lite.
FAQ
What does the seedance-meme-comedy skill do?
A short skit where every beat is laid down to serve one punchline. The joke has to land on something visible, and the absurdity only works when the camera and the physics stay dead serious. Use when the user wants a Seedance 2.5 / 2.0 video prompt for this kind of clip (Twist-ending comedy skit; 中文触发词: 反转结尾搞笑短片, 搞笑, 反转, 梗, 沙雕), or asks how published cases of this type were prompted. Read references/cases.md before drafting.
How do I install seedance-meme-comedy?
Run npx skills add https://github.com/learnprompt/awesome-seedance --skill seedance-meme-comedy in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/seedance-meme-comedy/ (personal) or .claude/skills/seedance-meme-comedy/ (project).
Which AI agents can use seedance-meme-comedy?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is seedance-meme-comedy safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains seedance-meme-comedy?
It is published by learnprompt in learnprompt/awesome-seedance. It has 62 recorded installs.
More from learnprompt/awesome-seedance
seedance-prompt-library
learnprompt/awesome-seedance
Open the skill to read its SKILL.md instructions.
seedance-storyboard-grid-to-video
learnprompt/awesome-seedance
Open the skill to read its SKILL.md instructions.
seedance-production-workflow
learnprompt/awesome-seedance
Open the skill to read its SKILL.md instructions.
seedance-3d-cartoon
learnprompt/awesome-seedance
Open the skill to read its SKILL.md instructions.
seedance-epic-fantasy-scifi
learnprompt/awesome-seedance
Open the skill to read its SKILL.md instructions.
seedance-fashion-lookbook
learnprompt/awesome-seedance
Open the skill to read its SKILL.md instructions.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available