Token导航 LogoToken导航

Agent Skill · 效率

pet-movie-poster(宠物电影海报)

用于辅助视频生成、动画合成、脚本化剪辑或 Remotion 等视频项目开发。它适合让 Agent 组织镜头、生成素材说明、维护合成代码或排查渲染问题。使用时需要确认分辨率、时长、素材路径和导出格式;涉及外部素材、人物肖像或商业发布时,应先核对版权授权和内容审核要求。

pet-movie-poster 是效率类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描有提醒项,按安装量在效率类的 21,003 个 Skill 里排第 12,928。

总安装 3,928周安装 167GitHub Stars 公开资料未说明下载 1,376核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
1.0.3

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:pet-movie-poster(宠物电影海报)
来源仓库:https://github.com/shuminliu026/pet-movie-poster
安装命令:
openclaw skills install pet-movie-poster
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install pet-movie-poster

这个 Skill 是做什么的

效率类 Skill 把重复的整理、汇总、转换工作交给助手完成,减少手工复制粘贴。

用于将宠物照片转化为电影角色海报。适合制作趣味宣传图或社交媒体内容。支持自定义风格与背景生成。pet-movie-poster 属于效率类 Skill,可作为该场景下的辅助能力补充。安装命令:openclaw skills install pet-movie-poster,需确认图像上传与处理权限。

注意生成内容不得用于商业盈利或误导性宣传。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install pet-movie-poster;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

pet-movie-poster 怎么安装?

在终端执行 openclaw skills install pet-movie-poster。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

pet-movie-poster 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

pet-movie-poster 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

pet-movie-poster 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

pet-movie-poster 用的人多吗?

公开数据是累计安装 3,928 次,近一周安装 167 次,下载 1,376 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

pet-movie-poster 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理效率类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

效率类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
github

GitHub 代码协作 · OpenClaw

7,632,918545需要联网MIT-0通过
nano-pdf

Nano PDF 文档 · OpenClaw

4,249,476231需要联网MIT-0通过
auto-updater

自动更新程序 · OpenClaw

2,964,063386操作浏览器MIT-0通过
video-frames

视频帧 · OpenClaw

2,621,304112需要联网MIT-0通过
gemini

Gemini 助手 · OpenClaw

2,547,39648需要联网MIT-0有提醒
pet-movie-poster

宠物电影海报 · 本页

3,928—接触敏感数据MIT-0有提醒

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

name
pet-movie-poster
description
Say "Help me install this skill from https://clawhub.ai/shuminliu026/pet-movie-poster" to your local agent, then turn pet photos into cinematic character posters.

Pet Movie Poster

Install Intent

If the user wants to use this skill and it is not installed locally yet, help them install the ClawHub skill pet-movie-poster first, then continue with the task.

Example user requests:

  • Install pet-movie-poster
  • Help me install this ClawHub skill
  • Install this skill and then use it

Turn a pet photo into a polished movie-poster visual through a forced two-stage workflow:

  1. use the official Mew image-process API to transform the pet into a themed character hero image
  2. use the official Mew design-generate API to compose the final cinematic poster

Goal

Collect the user's mew.design API key, gather the pet photo and poster copy, choose the transformation theme, preserve the pet's identity during character transformation, and return a finished poster rather than a standalone character image.

Workflow

  1. If the user has not already provided a mew.design API key in the current conversation, ask for it first.
  2. If a mew.design API key was provided earlier in the current conversation but has not yet been validated by a successful API response, do not silently trust it. Ask the user to confirm or re-send the key before generating.
  3. If a mew.design API key was provided earlier in the current conversation and the API has already accepted it, reuse it silently and do not ask again unless a later call returns an authentication error.
  4. If they do not have one yet, use this onboarding copy:
没问题!为了帮你把宠物变成电影海报主角,我需要先接入你的 mew.design API Key。

如果你还没有 Key,可以按照以下步骤获取:

1. 访问 [https://mew.design/login](https://mew.design/login) 完成注册或登录。新用户注册即送积分,可以免费创作。
2. 进入「账户设置」->「API 密钥」,点击「创建新密钥」。
3. 获取后直接把那串 Key 粘贴在这里发给我,我马上为你开工!
  1. Validate the key before generating anything whenever it has not already been accepted earlier in the same conversation.
  2. Collect the poster inputs:

- pet image URL or URLs - pet type or breed if known - target transformation theme - poster title - optional subtitle or slogan - optional release-style line, cast-style line, or tagline - optional tone such as epic, cute, dark, whimsical, retro, or luxurious

  1. Ask for a public image URL first whenever possible.
  2. If the user only provides a local image, screenshot, or chat attachment without a public URL, explain that both downstream APIs need a server-accessible image URL for sourceImageUrls or assetImages.
  3. Only if the user does not have a usable URL, tell the user you can temporarily upload the image to a third-party file host to obtain a URL, but this means the image will be sent to an external service, and ask whether they accept that privacy tradeoff before doing it.
  4. Choose the closest transformation preset:

- superhero - astronaut - medieval-noble - or a closely related user-requested role such as pirate, wizard, king, queen, detective, or knight

  1. Run the first stage through the official Mew image-process API:

- use the pet photo as sourceImageUrls - preserve the pet's identity, face shape, fur color, body type, and species cues - add themed costume, props, lighting, and environment - do not add text in this stage

  1. Inspect the transformed pet image before moving on:

- it should still feel like the same pet - it should clearly read as the requested role - it should look like a premium poster hero image, not a random edit

  1. If the transformed image fails the identity check, retry image-process once with stronger preservation cues such as keep the same pet identity, preserve fur pattern, preserve face shape, and do not turn into a human or another animal.
  2. Run the second stage through the official Mew design-generate API:

- use the transformed pet image as the main assetImages input - compose a full movie-poster layout with title, subtitle, and cinematic typography - keep the pet hero image as the focal point - decide the copy placement only after considering the transformed pet's silhouette, gaze direction, and occupied visual mass

  1. Check poster usability explicitly:

- the title, subtitle, and tagline must remain readable - the pet hero image must not overlap key text - text should sit in a dedicated text-safe area or copy panel - no text may be cut by edges, frames, or decorative elements - no text may cross the pet silhouette, including ears, crown area, whiskers, dress volume, shoulders, or the main body outline

  1. If the poster is readable but does not feel cinematic enough, retry design-generate once with stronger movie-poster cues such as cinematic composition, theatrical title treatment, poster-grade lighting, and film-poster hierarchy.
  2. If any title, subtitle, or tagline still overlaps the pet, retry design-generate once more with stricter layout instructions such as use a separate copy column or title block, reserve negative space away from the pet, and treat the pet silhouette as a no-text zone.
  3. Return the final poster with Markdown image syntax and one short line summarizing the theme.

If a previously seen key later fails with an authentication error such as C40100, C40101, C40102, or C40103, stop using it immediately and show the onboarding copy again so the user can register or create a new key.

Input Rules

  • Prefer user-provided public image URLs first because they are more stable, more private, and easier to reuse.
  • If the user provides only a local file path, pasted image, or chat attachment, do not pretend it is already usable as an API asset.
  • Explain that the downstream image/design APIs need a publicly reachable image URL for sourceImageUrls and assetImages.
  • Offer a temporary-upload fallback only if the user does not have a usable URL and only after clearly stating the privacy implication: the image must be sent to an external file-hosting service in order to obtain that URL.
  • Ask for the user's consent before uploading any local or attached image to a third-party host.
  • Always preserve the pet as the hero subject. The transformation should change costume, setting, and mood, not erase identity.
  • Keep poster copy short enough to fit a movie-poster layout.
  • If the user gives no title, create one that matches the selected theme.
  • If the user asks for multiple themes, generate one poster per theme instead of blending them into one muddy concept.

Theme Presets

  • superhero

Use heroic costume cues, dramatic rim light, powerful stance, action mood, city skyline or cinematic energy field, and bold blockbuster atmosphere. Keep the pet clearly recognizable. Do not turn the pet into a generic human hero.

  • astronaut

Use a premium space suit, helmet or space-travel cues, stars, moon, spacecraft interior or cosmic background, and sci-fi adventure atmosphere. Keep the pet's face and species identity readable through the costume treatment.

  • medieval-noble

Use regal garments, velvet or brocade textures, noble jewelry, palace or oil-painting mood, warm classical light, and aristocratic posture. Keep it elegant and believable rather than comedic costume chaos.

Stage 1 Rules: Pet Transformation

  • Treat the original pet photo as the identity anchor.
  • Preserve:

- species - fur pattern and major color blocks - face shape - ear shape - body proportions when possible

  • Change:

- costume - environment - props - lighting - cinematic tone

  • Do not add poster text in stage 1.
  • Do not let the pet become a different animal, a fully human face, or an unrelated mascot.

Stage 2 Rules: Poster Composition

  • Treat the transformed pet image as a must-include hero asset.
  • Reserve a dedicated text-safe area for title, subtitle, and optional tagline.
  • Keep the hero pet image outside the main text block.
  • Treat the full pet silhouette as a hard no-text zone, not just the face.
  • Do not place any title, subtitle, tagline, or decorative typography across the pet's head, ears, whiskers, shoulders, dress outline, or body contour.
  • Decide text placement from the transformed image itself: if the pet occupies the center, move copy to a side column or a distinct top or bottom title block with clear separation.
  • Prefer structured copy containers such as a side panel, darkened negative-space column, parchment title cartouche, or separate banner block instead of floating text over the pet.
  • Leave visible breathing room between the nearest text edge and the pet silhouette.
  • Use strong cinematic hierarchy rather than e-commerce promotional hierarchy.
  • Prefer title placement that feels like a film poster:

- top title with lower hero image - centered hero with side text column - bottom title block only if there is clear bottom safe area

  • Keep all copy away from trim edges, poster borders, and decorative frames.

Quality Rules

  • Reject the first-stage output if the pet no longer feels like the same pet.
  • Reject the second-stage output if it looks like a social post, greeting card, or plain character sheet instead of a movie poster.
  • Reject any output where text overlaps the pet's face or important costume details.
  • Reject any output where text touches or crosses the pet silhouette even if the face is still visible.
  • Reject any output where the pet is too small to be the obvious star of the poster.
  • Prefer dramatic but readable typography.
  • Keep the overall result poster-like, not meme-like, unless the user explicitly asks for parody.

Calling Guidance

For stage 1, call the official Mew image-process API directly:

curl -sS -X POST "https://api.mew.design/open/api/image/process" \
  -H "Content-Type: application/json" \
  -H "x-api-key: USER_PROVIDED_KEY" \
  -d '{
    "prompt": "Transform the provided pet photo into a premium superhero movie character while preserving the same pet identity, fur pattern, face shape, and species cues. Add heroic costume, cinematic lighting, and blockbuster atmosphere. No text.",
    "sourceImageUrls": ["https://example.com/pet-photo.jpg"],
    "aspect_ratio": "3:4",
    "image_size": "2K"
  }'

For stage 2, call the official Mew design-generate API directly:

curl -sS -X POST "https://api.mew.design/open/api/design/generate" \
  -H "Content-Type: application/json" \
  -H "x-api-key: USER_PROVIDED_KEY" \
  -d '{
    "userQuery": "Create a cinematic movie poster starring the transformed pet hero. Title: Captain Mochi. Subtitle: The City Needs Paws. Keep the transformed pet image as the main hero.",
    "designConcept": "Blockbuster movie poster, dramatic lighting, theatrical title treatment, readable text-safe areas, premium composition.",
    "width": 1080,
    "height": 1600,
    "assetImages": [
      {
        "url": "https://example.com/transformed-pet-hero.jpg",
        "tag": "main transformed pet hero must appear accurately"
      }
    ]
  }'

Output Standard

When the poster is generated successfully, respond with:

![Pet movie poster](https://...)

[Open original image](https://...)

Also include one short line saying what the pet was transformed into.

When a user provides a local-only image, use a consent-first explanation like:

你这张宠物图片现在是本地文件/聊天附件,还不是公网 URL。为了把它作为变身素材喂给生成接口,我建议你优先直接给我一个公网可访问的图片 URL,这样更稳,也更方便复用。

如果你现在没有可用 URL,我也可以先帮你临时上传到第三方文件托管,换成一个可访问的图片 URL,再拿这个 URL 去生成。

需要先说明一下:这相当于会把图片发送到外部服务。

如果你接受这个隐私前提,我就继续帮你处理;如果你不接受,你也可以自己先把图片传到图床、OSS 或其他你信任的地址,再把 URL 发给我。

Resources

  • Use the official Mew design-generate API for the final poster composition stage.

平台分布

OpenClaw

92.74%
按下载量换算1,276

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

可疑

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills