codex-image-gen
>-
供给资产档案
设计与创意生产
Design assets, images, video, audio, multimodal media, presentation, and creative production skills.
场景
设计与创意
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
适配 Agent
Claude Code + OpenAI Agents + CLI
适用于 Codex、Claude Code、Cursor、CLI 或自定义 Agent。
安装
就绪
npx skills add shipshitdev/skills --skill codex-image-gen
维护状态
新鲜
距上次推送 2 天
风险
需审查
Permission surface may require sandboxing
GitHub 质量
33
62/100 质量 · 73/100 信任
覆盖标签
审查说明
Permission surface may require sandboxing · Low GitHub adoption signal
Agent 采用评分卡
一眼查看信任、审计与安装准备度
这些分数综合公开仓库元数据、OpenAgentSkill 审查信号、维护新鲜度与安装准备度。它用于候选筛选,不替代人工审查。
质量
有潜力有用的候选项,但采用前应与替代方案比较。
信任
仅限沙盒有用但信任信号不足或混杂的候选项。在结果闭环证明任务匹配前,请保持在隔离工作区内使用。
审计
需审查对安装准备度、安全元数据、维护情况与采用风险的机器可读审查。
OpenAgentSkill 信任评分 v5
安装前需人工审查
仅在沙盒中运行,并在用于真实工作前比较接近的替代方案。
Stars
33 个 GitHub Stars
仓库活跃度
33 个 Star,3 个 Fork
维护状态
距上次推送 2 天
许可证
MIT
安装
npx skills add shipshitdev/skills --skill codex-image-gen
安装安全性
标准软件包或运行时安装路径
权限范围
shell or command execution, filesystem or document access
Agent 结果
暂未有 Agent 结果数据
文档
Usable metadata, review docs
风险摘要
生产前审查
- Low GitHub adoption signal
- Quality score needs review
- Permission surface needs review: shell or command execution, filesystem or document access
- GitHub adoption: 33 GitHub stars
安装准备度
安装路径可用
- 安装路径可用
- 仓库证据可用
- 已声明许可证
- 暂无 Agent 验证结果证据
Agent 可读元数据
这个 Skill 的机器可读决策数据。
使用此区块或内嵌 JSON 判断 Agent 是否应安装该 Skill、选择替代方案,或先请求人工审查。
适用任务
- 设计与创意 工作流
- Claude Code 团队
- builders willing to evaluate younger projects
- Inspect visual requirements
适用 Agent
安装决策
- 命令
- npx skills add shipshitdev/skills --skill codex-image-gen
- 策略
- 审查
- 人工审查
- 是
信任与风险
- 信任
- 65/100
- 审计
- 77/100
- 风险级别
- 需审查
结果闭环
- 端点
- /api/agent/outcome
- 事件 ID
- resolve
- 结果
- 5
不适用场景
- 需要厂商支持 SLA 的团队
- production agents without a repository review
- Low GitHub adoption signal
- 暂未有 OpenAgentSkill 使用反馈数据
- 高风险权限提示:Shell 或命令执行
替代 Skill
Frontend Design
171.1K Stars
npx skills add anthropics/skills --skill frontend-design
替代 Skill
Taste Skill: Anti-Slop Frontend
79.4K Stars
npx skills add Leonxlnx/taste-skill --skill design-taste-frontend
替代 Skill
Canvas Design
171.1K Stars
npx skills add anthropics/skills --skill canvas-design
替代 Skill
Anthropic Brand Guidelines
171.1K Stars
npx skills add anthropics/skills --skill brand-guidelines
Agent 安全 v2
45/100 · 避免自动安装
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
高
Shell 或命令执行
Skill 元数据引用了终端、CLI、Shell、子进程或命令执行工作流。
中
网络访问
Skill 可能访问远程页面、API、仓库或外部服务。
中
文件系统访问
Skill 可能读取或写入项目文件、文档、生成产物或本地工作区状态。
中
数据库访问
Skill 可能检查 Schema、查询数据库或处理持久化存储。
- 高风险权限提示:Shell 或命令执行
- Permission surface may require sandboxing
安装目标
在你的 Agent 工作流中安装此 Skill
通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。
OpenAgentSkill CLI
Resolve policy, run the source installer safely, and report a verified install receipt.
$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install shipshitdev-codex-image-genAgent 解析计划
让 Agent 在安装前验证匹配度。
Resolve API 返回首选 Skill、替代方案、安全策略、审计说明、安装目标和可直接执行的提示词,无需抓取此页面。
打开 JSON
/api/agent/resolve?task=Use%20codex-image-gen%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve 文本
/api/agent/resolve?task=Use%20codex-image-gen%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
安装交接
/api/skills/shipshitdev-codex-image-gen/install
Agent 应检查
- 从 Resolve API 检查任务匹配与替代方案。
- 检查审计评分、信任评分和安全策略警告。
- 检查 Codex、Claude Code、Cursor 或 CLI 的安装目标兼容性。
复制提示词
Task: Use codex-image-gen in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20codex-image-gen%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/shipshitdev-codex-image-gen/install
Install command: npx skills add shipshitdev/skills --skill codex-image-gen
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent 交接
把安装路径交给 Agent,而不是再给一个目录页。
通过公开安装端点获取命令、安全清单、目标提示词和该 Skill 的规范链接。
安装交接
/api/skills/shipshitdev-codex-image-gen/install
LLM 文本格式
/api/skills/shipshitdev-codex-image-gen/install?format=text
寻找替代方案
/api/skills/search?q=codex-image-gen&limit=3
Agent 提示词
Use codex-image-gen for this task. Review https://www.openagentskill.com/api/skills/shipshitdev-codex-image-gen/install, then install with: npx skills add shipshitdev/skills --skill codex-image-genRegistry 元数据
用于自动选择 Skill 的 Agent 可读档案。
本页通过 Registry API 提供相同的决策、信任、审计、场景和安装信号,让 Agent 无需抓取界面即可排序。
Agent 决策面板
Fallback candidate for Design and creative
先用此 Skill 做原型验证,并保留备选方案。
栈中角色
备选候选
主要匹配
设计与创意
信任标签
先做原型验证
安装路径
命令已就绪
适用场景
- 设计与创意 工作流
- Claude Code 团队
- builders willing to evaluate younger projects
证据
- 仓库近期活跃
- 已提供安装命令或 GitHub 仓库
- 62/100 质量档案
先审查
- Low GitHub adoption signal
- 暂未有 OpenAgentSkill 使用反馈数据
实施路径
- 1在沙盒 Agent 中安装它,并端到端完成一次设计与创意任务。
- 2Compare output quality, latency, and failure behavior against at least one alternative.
- 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.
信任档案
仅限沙盒
有用但信任信号不足或混杂的候选项。在结果闭环证明任务匹配前,请保持在隔离工作区内使用。
GitHub 采用度
检查33 个 GitHub Stars
Star/Fork 活跃度
检查33 个 Star,3 个 Fork; 当前元数据中没有议题活跃度信息
近期维护
通过距上次推送 2 天
许可证清晰度
通过MIT
积极信号
- AI 审查已通过
- 安装路径可用
- 仓库证据可用
- 近期维护的仓库
- 安装命令未发现明显高风险模式
- 结果闭环已就绪,但需要首次真实 Agent 运行
安装前审查
- Low GitHub adoption signal
- Quality score needs review
- Permission surface needs review: shell or command execution, filesystem or document access
- GitHub adoption: 33 GitHub stars
- Stars/forks activity: 33 stars, 3 forks; issue activity unavailable in current metadata
- Permission surface: shell or command execution, filesystem or document access
- 暂未有真实 Agent 结果报告
- 无人值守安装前需要人工审查
建议操作
仅在沙盒中运行,并在用于真实工作前比较接近的替代方案。
质量档案
有潜力 适用于 Agent 工作流的候选
有用的候选项,但采用前应与替代方案比较。
工作流匹配
在这些场景使用此 Skill
Create assets
Design and creative
I need my agent to produce design assets, UI directions, presentations, or creative media workflows.
Operate web apps
Browser automation
I need my agent to control a browser, fill forms, and verify web app workflows.
Operate local tools
Local desktop
I need my agent to operate local files and desktop apps in a repeatable workflow.
工作流匹配
加入完整工作流
Design, build, test, and ship interfaces
Frontend and UI
A practical workflow for agents that turn product briefs or Figma designs into polished frontend code, review the result, test it in a browser, and prepare a safe deployment.
Operate and verify web apps
Browser QA agent
A workflow for agents that navigate products, fill forms, take screenshots, and verify real user flows across web applications.
Turn skills into distribution
Content growth agent
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
替代方案短名单
安装前对比
可能适合该任务的相近 Skill。
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
Taste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
Canvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
Anthropic Brand Guidelines
Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
概览
--- name: codex-image-gen description: >- Generate raster images (icons, illustrations, textures, app icons) from a text prompt by driving the Codex CLI's image tool, then extracting the finished PNG from the Codex session rollout. Use when an agent needs a real generated image and has no native image-generation tool. Requires the `codex` CLI, logged in. license: MIT compatibility: Requires the `codex` CLI (logged in) plus `python3` and `base64`; `sips` is optional for post-processing on macOS. metadata: version: "1.0.0" tags: "codex, image-generation, gpt-image, cli, assets, app-icon" when_to_use: "generate an image, make an icon, create an app icon, render an illustration or texture, agent needs an image but has no image tool, codex image generation" ---
# Codex Image Gen
Generate a real raster image from a text prompt when the running agent has no native image generator. The mechanism is non-obvious: the headless `codex exec` path genuinely calls the image tool, but it never writes the PNG to disk — only the Codex desktop app has the plumbing that polls the async job and saves it. The finished image is still recoverable, because its full base64 PNG is recorded in the session rollout JSONL. Run the prompt, read the session id Codex prints, open the matching rollout, and decode the largest `result` string to a PNG.
## When this is the right tool
- The agent needs a generated raster image (icon, illustration, texture, app icon, placeholder art) and has no built-in image-generation tool. - A `codex` CLI is installed and logged in, and shelling out to it is allowed. - A vector result is **not** required — this produces a PNG, not an SVG.
If a native image tool exists, prefer it. If the deliverable is a logo or crisp vector, prefer a vector workflow.
## Why the naive approach fails
Running `codex exec "draw a ..."` and then watching `~/.codex/generated_images/` produces nothing: that folder is written by the desktop app's async-job poller, not by `codex exec`. People conclude CLI image generation is impossible. It is not — the completed image lives in the session rollout as the `result` field of the image-generation response item. This skill reads it from there.
## Pipeline
### 1. Write the prompt to a file
Avoid shell-escaping pain by putting the prompt in a file. Be explicit — the model has no other context:
- Subject and style ("flat vector mark", "glossy 3D glass icon", "hand-drawn"). - Composition: full-bleed vs. padded, centered, single object vs. scene. - Palette and background (solid color, transparent intent, gradient). - `NO text, NO letters, NO words` unless you specifically want type. - Target aspect ratio and rough size.
```bash cat > /tmp/img-prompt.txt <<'PROMPT' A single app icon: a glossy translucent envelope on a soft blue-to-violet gradient, Liquid Glass style, centered with even padding, no text, no letters, 1:1 square, high detail. PROMPT ```
### 2. Run `codex exec` and capture stdout
```bash codex exec -s read-only "$(cat /tmp/img-prompt.txt)" 2>&1 | tee /tmp/codex-run.log ```
Run it in the **foreground**. `exec` returns once the turn completes; in practice the `result` is already written to the rollout by then.
### 3. Parse the session id
Codex prints a `session id: <uuid>` line. Pull it from the captured log:
```bash SESSION_ID=$(grep -oE 'session id: [0-9a-f-]{36}' /tmp/codex-run.log | awk '{print $3}') echo "session: $SESSION_ID" ```
### 4. Extract the PNG from the rollout
The rollout lives at `~/.codex/sessions/YYYY/MM/DD/rollout-*<session-id>*.jsonl`. Walk it, find the largest `result` string (the base64 image), and decode it. Use the bundled helper:
```bash python3 scripts/extract-codex-image.py "$SESSION_ID" /tmp/out.png ```
### 5. Assert success
Confirm the file exists and is a real PNG before using it:
```bash test -s /tmp/out.png && file /tmp/out.png # expect: PNG image data, 1254 x 1254 ```
If extraction finds no base64 `result`, the turn did not actually generate an image (e.g. the model answered in text). Re-run step 2 with a more explicit "generate an image" instruction.
### 6. Post-process (optional)
Default output is roughly **1254×1254 PNG, RGB, no alpha**. Resize / strip alpha with `sips` on macOS:
```bash sips -z 1024 1024 /tmp/out.png --out /tmp/icon-1024.png # downscale sips -s format png /tmp/out.png --out /tmp/flat.png # normalize ```
## Reference extractor
`scripts/extract-codex-image.py` (also reproduced here so the procedure is self-contained):
```python import json, sys, base64, glob, os
session_id, out = sys.argv[1], sys.argv[2] sess = max( glob.glob(os.path.expanduser(f"~/.codex/sessions/**/*{session_id}*.jsonl"), recursive=True), key=os.path.getmtime, ) best = None
def walk(o): global best if isinstance(o, dict): for k, v in o.items(): if k == "result" and isinstance(v, str) and len(v) > 100000: if best is None or len(v) > len(best): best = v else: walk(v) elif isinstance(o, list): for v in o: walk(v)
for line in open(sess): try: walk(json.loads(line)) except Exception: pass
if best is None: sys.exit("no base64 image result found in rollout — the turn may not have generated an image") open(out, "wb").write(base64.b64decode(best)) print("WROTE", out) ```
## Worked example: build a macOS/iOS app icon set
```bash # 1. Generate a 1:1 icon master. cat > /tmp/icon-prompt.txt <<'PROMPT' App icon: a glossy translucent envelope, Liquid Glass style, soft blue-to-violet gradient background, centered, even padding, no text, no letters, 1:1 square. PROMPT codex exec -s read-only "$(cat /tmp/icon-prompt.txt)" 2>&1 | tee /tmp/codex-run.log SESSION_ID=$(grep -oE 'session id: [0-9a-f-]{36}' /tmp/codex-run.log | awk '{print $3}') python3 scripts/extract-codex-image.py "$SESSION_ID" /tmp/icon-master.png
# 2. Make a 1024 master with no alpha (iOS rejects alpha on the marketing icon). sips -z 1024 1024 /tmp/icon-master.png --out /tmp/AppIcon-1024.png sips -s format png --setProperty hasAlpha false /tmp/AppIcon-1024.png --out /tmp/AppIcon-1024.png
# 3. Slice into an AppIcon.appiconset (iOS single-size 1024 + the macOS ladder). mkdir -p AppIcon.appiconset cp /tmp/AppIcon-1024.png AppIcon.appiconset/icon_1024.png for sz in 16 32 64 128 256 512 1024; do sips -z "$sz" "$sz" /tmp/AppIcon-1024.png --out "AppIcon.appiconset/icon_${sz}.png" done # Author Contents.json mapping each size/scale to its file, then verify: # actool --compile /tmp/out --app-icon AppIcon --platform iphoneos \ # --minimum-deployment-target 17.0 AppIcon.appiconset # expect a clean compile ```
## Gotchas
- **The `codex` alias may inject `--dangerously-bypass-approvals-and-sandbox`**, which overrides any `-s read-only` you pass (the session then reports `danger-full-access`). Harmless for pure image generation, but worth knowing. Prefer running `codex exec` in the foreground — a backgrounded full-access run can trip auto-approval classifiers. - **Size and alpha.** Output is ~1254×1254, RGB, no alpha. Downscale to 1024 for an Apple icon master; iOS rejects alpha on the marketing icon. - **Async timing.** `exec` ends when the turn completes; the `result` is already in the rollout by then in practice. Still assert the file exists and decodes — do not assume. - **Fragility — pinned to `codex-cli 0.141.0`.** This depends on a Codex CLI internal: the rollout `result` field. A future Codex may change the rollout schema or add a first-class `--save-image` / output-path flag. If such a flag exists, prefer it and keep this rollout-extraction path as the fallback. If the extractor finds no base64 `result`, first check whether the rollout layout changed under `~/.codex/sessions/`.
技术详情
- 版本
- 1.0.0
- 许可证
- MIT
- 最近更新
- 2026年8月23日
- 发布时间
- 2026年8月23日
决策摘要
备选候选
仓库近期活跃
Agent 验证证据
Agent 验证证据
来自解析、审查、安装和一次小范围运行后的结果报告。
- 成功率
- —
- 近期失败
- —
- 结果
- 0
- 输出质量
- —
- 失败
- 0
- 不相关
- 0
- 安装次数
- 0
- 风险拦截
- 0
- 需要配置
- 0
- 生产环境
- 0
暂时没有 Agent 结果数据。首次 Agent 执行可以通过 /api/agent/outcome 报告成功、需要设置、风险拦截、失败或不相关。
增长闭环
分享工具包
为 codex-image-gen 准备的场景化草稿,可手动发布到 X。
A practical pick for design or creative work: codex-image-gen: >- 33 stars https://www.openagentskill.com/skills/shipshitdev-codex-image-gen?ref=x
可选:带安装命令的回复
Listing + install path for codex-image-gen: https://www.openagentskill.com/skills/shipshitdev-codex-image-gen?ref=x Install: npx skills add shipshitdev/skills --skill codex-image-gen
收录来源
Registry 收录
此列表来自公开来源,维护者认领获批前不会标记为官方。
- 创作者
- shipshitdev
- 收录方
- OpenAgentSkill 社区索引
归属链接指向公开仓库或创作者主页。创作者可认领列表以更新所有权信号。
认领此 Skill所有者认领
认领此 Skill 页面
这条 Registry 收录 列表归属于 shipshitdev,但尚未标记为官方。认领后可增加已验证所有者信号,使后续发布、安装和审计更新更值得信赖。
创作者外链工具包
将证据徽章加入你的 README
在开发者评估仓库的位置展示规范页面、当前信任与审计信号,以及真实的 Agent 验证证据。
[](https://www.openagentskill.com/skills/shipshitdev-codex-image-gen)
[](https://www.openagentskill.com/skills/shipshitdev-codex-image-gen)
[](https://www.openagentskill.com/skills/shipshitdev-codex-image-gen/audit)
[](https://www.openagentskill.com/skills/shipshitdev-codex-image-gen)作者
shipshitdev
@shipshitdev
健康信号
- GitHub Stars
- 33
- 质量评分
- 34/100
- 最近 GitHub 推送
- 2026年8月20日
- 框架提示
- 未知
- OpenAgentSkill 浏览量
- 0
- 复制安装命令
- 0
- 跳转点击
- 0
社区信号
告诉我们这个 Skill 是否对你的 Agent 工作流有帮助。汇总反馈会持续改善排序。
信任与安全
仅限沙盒
- GitHub 采用度33 个 GitHub Stars检查
- Star/Fork 活跃度33 个 Star,3 个 Fork; 当前元数据中没有议题活跃度信息检查
- 近期维护距上次推送 2 天通过
- 许可证清晰度MIT通过
- README/SKILL.md 完整度公开元数据需要更完整的 README/SKILL.md 上下文信息
- 依赖与运行时风险命令执行范围信息
相关 Skill
Frontend Design
Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.
171.1K StarsTaste Skill: Anti-Slop Frontend
Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful redesigns.
79.4K StarsCanvas Design
Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.
171.1K StarsAnthropic Brand Guidelines
Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related artifacts.
171.1K Stars