Automates targeted asset correction and updates related AI generation prompts.
Install
mkdir -p .claude/skills/creator-fix-asset && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13000" && unzip -o skill.zip -d .claude/skills/creator-fix-asset && rm skill.zipInstalls to .claude/skills/creator-fix-asset
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Creator根据修改意见定向修正指定资产文件。修改视觉描述时同步更新图像提示词。Key capabilities
- →Correct specified asset files based on modification feedback
- →Synchronize image prompt words when visual descriptions are modified
- →Read local files in the current workspace
- →Create or overwrite local files in the current workspace
- →Perform directed modifications to local files
- →Search for files by pattern or content
How it works
The skill corrects specified asset files based on feedback and updates image prompt words, operating through a Codex adapter layer that maps to local file and shell tools.
Inputs & outputs
When to use creator-fix-asset
- →Fix asset based on feedback
- →Update generation prompts
- →Refine asset files
- →Correct visual errors
About this skill
Codex 适配器
这是生成的 Codex 适配层。源 skill 仍是唯一事实来源，位置为 skills/creator-fix-asset/SKILL.md。
不要手动编辑这个适配层。只有在确实需要改变 Claude 行为时才修改源 skill，然后运行 python3 .codex/build-codex-skills.py 重新生成适配层。
运行时映射
Codex 运行时映射
本仓库保持 skills/ 下的 Claude Code skill 不变。Codex 加载 .codex/skills/ 下生成的适配层；每个适配层会应用本映射，然后执行原始源 skill。
文件和 Shell 工具
- Claude
Read表示读取当前工作区中的本地文件。 - Claude
Write表示在当前工作区创建或覆盖本地文件。 - Claude
Edit表示对本地文件进行定向修改。 - Claude
Glob表示按模式查找文件。 - Claude
Grep表示搜索文件内容，优先使用rg。 - Claude
Bash表示在 skill 必要时执行本地 shell 命令。
Skill 调用
使用 Skill tool 调用 <skill-name> skill表示调用或执行名为<skill-name>的 Codex 适配层 skill。- 如果不能直接调用 skill，则读取
skills/<skill-name>/SKILL.md，并带着原始参数执行其中的说明。 - 传递参数时保留源 skill 的
$ARGUMENTS约定。
Agent 调用
- Claude
Agent表示在可用时委托给 Codex sub-agent。 - 如果存在匹配的角色，则使用
agents/<role>.md中的角色意图。 - 如果当前环境不支持自定义角色注入，则在当前 Codex 会话中执行委托任务，并遵循对应角色提示词。
定时任务和自动化
- Claude
CronCreate、CronList和CronDelete不是 Codex 中的字面工具名。 - 对于
/auto-video，优先使用 Codex automation 能力。 - 如果当前环境没有 Codex automation 能力，则使用手动或外部周期性调用
/check-video <target> --auto。 - 不得绕过
check-video或creator-video-dreamina中的安全规则。
模型提示
- Claude
model: opus和model: sonnet在 Codex 中仅作为提示信息。 - 在 Codex 中，除非用户明确要求切换模型，否则使用当前活动模型。
工具白名单
- 源 skill 中的 Claude
allowed-tools元数据在 Codex 中仅作为提示信息。 - 如果某个 Claude 工具名在 Codex 中不可用，不要仅因为工具名不同而失败，应按本映射执行。
执行源 Skill
- 读取
skills/creator-fix-asset/SKILL.md，并使用用户的原始参数执行该 skill 的说明。 - 将
skills/creator-fix-asset/视为源 skill 目录。当源 skill 引用rules.md或config-template.md等同级文件时，相对该目录解析。 - 将
scripts/、agents/、story/、assets/和config.md等仓库根路径视为相对当前工作区根目录的路径。 - 执行本适配层时，不要复制或修改源 skill 说明。
When not to use it
- →When the task involves manual editing of the Codex adapter layer
- →When the task involves bypassing safety rules in check-video or creator-video-dreamina
Limitations
- →Do not manually edit the Codex adapter layer
- →Do not bypass safety rules in check-video or creator-video-dreamina
- →Do not copy or modify source skill instructions when executing the adapter layer
How it compares
This skill uses a generated Codex adapter layer to execute instructions from a source skill, ensuring that changes are applied consistently through a defined mapping rather than direct manual intervention.
Compared to similar skills
creator-fix-asset side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| creator-fix-asset (this skill) | 0 | 3mo | No flags | Intermediate |
| nano-banana-pro-prompts-recommend-skill | 13 | 2mo | Review | Beginner |
| baoyu-cover-image | 10 | 2mo | No flags | Beginner |
| nano-image-generator | 1 | 6mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by wddxh
View all by wddxh →You might also like
nano-banana-pro-prompts-recommend-skill
YouMind-OpenLab
Recommend suitable prompts from 6000+ Nano Banana Pro image generation prompts based on user needs. Use this skill when users want to: - Generate images with AI (Nano Banana Pro model) - Find inspiration for image generation prompts - Get prompt recommendations for specific use cases (portraits, landscapes, product photos, etc.) - Create illustrations for articles, videos, podcasts, or other content - Translate and understand prompt techniques
baoyu-cover-image
JimLiu
Generates article cover images with 5 dimensions (type, palette, rendering, text, mood) combining 9 color palettes and 6 rendering styles. Supports cinematic (2.35:1), widescreen (16:9), and square (1:1) aspects. Use when user asks to "generate cover image", "create article cover", or "make cover".
nano-image-generator
solidSpoon
Generate images using Nano Banana Pro (Gemini 3 Pro Preview). Use when creating app icons, logos, UI graphics, marketing banners, social media images, illustrations, diagrams, or any visual assets. Triggers include phrases like 'generate an image', 'create a graphic', 'make an icon', 'design a logo', 'create a banner', or any request needing visual content.
isometric-asset-sheets
amilich
Generate sprite sheet images for the isometric city game using the GenerateImage tool. Use when creating new game assets, sprite sheets, vehicle sprites, building sprites, or any visual assets for the isometric city builder. Ensures consistent format, sizing, and isometric projections.
image
Script-Java
When the user wants to create, generate, edit, or optimize images for marketing — blog heroes, social graphics, product mockups, profile banners, listing visuals, or brand assets. Also use when the user mentions 'AI image generation,' 'generate an image,' 'create a graphic,' 'product mockup,' 'hero
generate
tahatms12
You are a visual producer. Your job is to generate AI images and videos from a shot deck, using the right models, prompts, and settings for each shot.