← 返回 Skills 市场
pic-gen
作者
Roland Dickens
· GitHub ↗
· v1.1.0
· MIT-0
169
总下载
0
收藏
1
当前安装
4
版本数
在 OpenClaw 中安装
/install pic-gen
功能描述
AI 图片生成与提示词优化工具。支持通义万相、Banana (Flux)、DALL-E 等多模型。用于：根据用户简单描述生成高质量图片提示词、优化已有提示词、直接调用配置好的模型出图。触发场景：「生成图片」「画一个 XXX」「优化这个提示词」「设置 API key」「切换模型」。用户可直接发送密钥给 bot，自动...
安全使用建议
This skill appears to implement the advertised features (prompt optimization and calling Qwen/Banana/OpenAI image APIs), but there are a few things to consider before installing: 1) Metadata mismatch — the registry says no env vars are required but the code expects DASHSCOPE_API_KEY, BANANA_API_KEY, and OPENAI_API_KEY (or keys in config/models.yaml). 2) The skill asks users to paste API keys into chat and will write them to pic-gen/config/models.yaml; avoid pasting secrets into public or semi-public chats and avoid committing that file to source control. Prefer setting keys via environment variables or a secure secrets manager instead. 3) Because the skill persists keys, review the code (scripts/update_config.py, scripts/*.py) to confirm no unexpected network endpoints or exfiltration; the listed network calls target known APIs (dashscope.aliyuncs.com, api.banana.dev, api.openai.com). 4) If you install, run it in a sandboxed environment, keep API keys minimal-scoped where possible, and consider manually setting environment variables rather than providing keys via chat. If you want higher assurance, ask the author to: (a) update registry metadata to declare required env vars and dependencies, and (b) remove the recommendation to paste keys into chat or add an explicit confirmation mechanism and clear audit/log guidance.
功能分析
Type: OpenClaw Skill
Name: pic-gen
Version: 1.1.0
The pic-gen skill bundle is a well-structured tool for AI image generation and prompt optimization across multiple platforms (Qwen, Banana/Flux, DALL-E 3). The bundle includes Python scripts for API interaction, prompt enhancement logic, and configuration management. While the skill handles sensitive API keys, it follows security best practices by supporting environment variables, implementing key masking in the configuration display script (update_config.py), and providing explicit warnings to users about not sharing secrets. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
能力标签
能力评估
Purpose & Capability
The skill's code and SKILL.md clearly need API keys (DASHSCOPE_API_KEY, BANANA_API_KEY, OPENAI_API_KEY) and Python packages (requests, pyyaml, banana-dev). However the registry metadata listed no required environment variables or binaries. Requesting API keys is proportionate to the stated purpose (calling external image-generation services), but the metadata mismatch is inconsistent and could mislead users about what will be needed.
Instruction Scope
SKILL.md explicitly instructs the agent to ask users to paste API keys in chat and the code (scripts/update_config.py) will write those keys to pic-gen/config/models.yaml. Persisting secrets collected from chat and instructing users to provide keys via conversation is within the skill's purpose but expands the data-surface (secrets stored on disk and transit in chat). There's no sign the skill transmits keys to unexpected external endpoints, but storing secrets in a file and encouraging chat-based key entry is a risky UX and should be made explicit to users.
Install Mechanism
There is no automated install spec (instruction-only in registry), but the package includes requirements.txt and SKILL.md lists Python packages to be present. The code uses standard pip-installable packages (requests, pyyaml, banana-dev). Lack of an install step means the environment may not have required dependencies; it's an inconsistency rather than a direct supply-chain red flag (no remote arbitrary downloads or unknown URLs).
Credentials
The external API keys requested are reasonable for contacting DashScope (qwen), Banana/Flux, and OpenAI, but the skill will persist keys to a local YAML file by default and suggests users paste keys into chat. The registry/manifest claimed no required env vars, but the code reads specific env vars (DASHSCOPE_API_KEY, BANANA_API_KEY, OPENAI_API_KEY). Requiring and storing multiple credentials is justified by the multi-model functionality but amplifies risk if keys are provided via chat or the config file is checked into source control.
Persistence & Privilege
The skill does not request always:true, does not modify other skills, and only writes to its own config path (pic-gen/config/models.yaml). Its persistence is limited to storing user-provided API keys and settings — expected for this functionality.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install pic-gen - 安装完成后，直接呼叫该 Skill 的名称或使用
/pic-gen触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.1.0
pic-gen v1.1.0
- Added initial test suite with basic test and initialization files.
- Updated Banana and DALL-E generation scripts for improved functionality or bugfixes.
- Enhanced configuration update handling in update_config.py.
- Improved code structure and testability.
v1.0.2
Add requirements.txt, requires metadata for dependency scan, reorder API key config options with env vars as recommended, add plaintext config security warning
v1.0.1
Rewrite description as problem-solution pitch for better ClawHub conversion
v1.0.0
Initial release: AI image generation prompt optimizer supporting Qwen/Banana/Flux/DALL-E
元数据
常见问题
pic-gen 是什么？
AI 图片生成与提示词优化工具。支持通义万相、Banana (Flux)、DALL-E 等多模型。用于：根据用户简单描述生成高质量图片提示词、优化已有提示词、直接调用配置好的模型出图。触发场景：「生成图片」「画一个 XXX」「优化这个提示词」「设置 API key」「切换模型」。用户可直接发送密钥给 bot，自动... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 169 次。
如何安装 pic-gen？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install pic-gen」即可一键安装，无需额外配置。
pic-gen 是免费的吗？
是的，pic-gen 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
pic-gen 支持哪些平台？
pic-gen 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 pic-gen？
由 Roland Dickens（@aoturlab）开发并维护，当前版本 v1.1.0。
推荐 Skills