Agent Skills › CodingFeng101/CanvasAnvil › poster-skill

poster-skill

GitHub

用于根据结构化需求生成最终海报图像的技能，支持单张海报、活动宣传及发布视觉素材。流程涵盖字段收集、提示词生成、调用配置好的AI图像提供商进行绘制，并导出为PNG等本地图片文件及元数据。

skill/poster-skill/SKILL.md CodingFeng101/CanvasAnvil

Trigger Scenarios

需要生成单张最终海报图像制作活动或发布会宣传视觉图将结构化需求转换为直接可用的本地图片文件

Install

npx skills add CodingFeng101/CanvasAnvil --skill poster-skill -g -y

More Options

Non-standard path

npx skills add https://github.com/CodingFeng101/CanvasAnvil/tree/main/skill/poster-skill -g -y

Use without installing

npx skills use CodingFeng101/CanvasAnvil@poster-skill

指定 Agent (Claude Code)

npx skills add CodingFeng101/CanvasAnvil --skill poster-skill -a claude-code -g -y

安装 repo 全部 skill

npx skills add CodingFeng101/CanvasAnvil --all -g -y

预览 repo 内 skill

npx skills add CodingFeng101/CanvasAnvil --list

SKILL.md

Frontmatter

{
    "name": "poster-skill",
    "description": "Generate final poster images from structured requirements. Use for single-poster tasks, campaign posters, event posters, launch visuals, and other single-frame promotional graphics that should export directly to local image files."
}

Poster Skill

Trigger

Use when the task requires one final poster image.

First-Use Reminder

On the first use of this skill in a conversation, remind the user that image generation is configurable and tell them which model vendors are supported in config/image-provider.json.

Supported vendors:

openai
aliyun
tencent
bytedance
zhipu
google
xai
bfl
adobe

Order

Confirm the task is a poster task.
Collect required fields.
Ask follow-up questions for missing required fields.
Read the required references.
Produce the final poster prompt.
Generate the image through the configured provider.
Export or bundle artifacts when requested.

Required Fields

theme
size or aspect_ratio
style_direction
color_direction
primary_copy
reference_image_status

Do not guess missing required fields.

Required References

references/poster-fields.md
references/prompt-rules.md
references/image-provider-config.md
references/output-contract.md

Prompt Contract

Produce one final poster prompt.
Keep the output specific to one frame.
Include composition, focal area, typography intent, and color direction.
Keep provided copy explicit.
Do not invent unsupported claims, pricing, or brand facts.
Treat reference images as visual guidance only.
Do not treat reference images as factual sources for copy, branding, pricing, dates, or claims.

Provider Contract

Use the configured image provider for image generation.
Require config/image-provider.json before image generation.
Do not ask the user to paste API keys into chat.
Stop and tell the user to fill config/image-provider.json when provider, apiKey, or model is missing.
Pass a reference image only when reference_image_status is positive and a usable reference image URL is available.