← 返回 Skills 市场
76
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install aigc-bak
功能描述
AIGC 图片生成助手，帮助用户生成图片。当用户想要生成图片、AI 绘画、文生图、创作图片时自动触发。支持负面提示词、图片比例、批量生成等参数。
使用说明 (SKILL.md)
AIGC Image Generator
AI 图片生成接口，支持文生图功能。
触发场景
当用户要求生成图片时自动触发，例如：
- "生成一张图片..."
- "画一张..."
- "帮我生成..."
- "创作图片"
- "AI 绘画"
重要：响应流程（必须遵守）
第一步：立即回复用户（毫秒级响应）
只要收到用户的生成请求，必须立刻回复用户，不能等待图片生成完成后再回复！
回复示例（随机选择一种风格）：
- "收到！我来帮你生成【xxx】，稍等片刻，马上就好~ 🎨"
- "好嘞！开始创作【xxx】，请耐心等待，完成后第一时间发给你 ✨"
- "好的，正在生成【xxx】，这个过程需要一点时间，完成后立刻发给你 📸"
第二步：执行生成任务
在后台执行图片生成（不阻塞回复）。
第三步：发送结果
生成完成后：
- 下载图片到本地
- 调用 feishu-assistant 发送图片给用户
执行细节
调用 API
# 1. 提交任务
curl -X POST "http://localhost:8082/image/generate" \
-H "Content-Type: application/json" \
-d '{
"prompt":"图片描述",
"negative":"",
"ratio":1,
"batch":1,
"clientId":"openclaw-kinggu",
"provider":4
}'
# 返回: {"code":200,"data":{"promptId":"xxx"}}
# 2. 轮询结果（等待 30-60 秒）
curl "http://localhost:8082/task/query?taskId=xxx"
# 3. 下载图片并发送到飞书
关键原则
- 先回复，后执行 - 用户发送请求后立刻回复，不用等图片生成
- 回复要友好 - 让用户知道正在处理，耐心等待
- 完成发送图片 - 生成后自动发送到飞书
图片存储路径
生成图片默认保存到：
/Users/jackgu/.openclaw/workspace/files/generated/images/{YYYY-MM}/
按年月自动分目录，图片命名格式：{promptId}_{index}.jpg
安全使用建议
This skill is internally inconsistent: the manifest declares no credentials but the code expects an OSS token and Feishu chat IDs and even includes a token in config.local.json. It also uploads images to an external domain (https://tczlld.com) and runs a local Feishu sender script at a hardcoded user path. Before installing, do not proceed unless you can: 1) confirm the OSS_UPLOAD_URL is trustworthy and owned by you or a trusted provider; 2) remove or rotate the embedded token in config.local.json (treat it as compromised); 3) set AIGC_OSS_TOKEN and chat IDs explicitly in a secure environment rather than relying on repo files; 4) verify the FEISHU_SENDER_SCRIPT path and inspect that script's behavior; and 5) run the skill in a sandboxed environment first. If the developer can provide (a) confirmation that the included token is dummy, (b) an explanation why the manifest doesn't list required env vars, and (c) a trusted OSS endpoint, re-evaluation could raise confidence toward benign.
能力评估
Purpose & Capability
The skill declares no required environment variables or credentials, but the code and docs clearly expect an OSS token (AIGC_OSS_TOKEN / config.local.json), FEISHU chat IDs, and a FEISHU sender script under a user-specific path. The skill's purpose (image generation) does not justify embedding or shipping an OSS token in config.local.json or hardcoding an external OSS upload URL (https://tczlld.com). Missing declarations in the manifest are incoherent with the actual needs.
Instruction Scope
SKILL.md instructs immediate reply then background generation and sending via a Feishu sender, and the code downloads generated images, writes to a user-specific local path (/Users/jackgu/.openclaw/...) and calls another local script. The SKILL.md and manifest do not surface that the agent will read config.local.json, use environment tokens, contact an external OSS endpoint, or invoke external scripts — these are implicit behaviors and broaden the skill's scope beyond what's declared.
Install Mechanism
There is no install spec (instruction-only plus included code), so nothing is downloaded at install time. However, the code will make network requests to a non-standard external domain (tczlld.com) for OSS uploads. That endpoint is not a known official host (e.g., GitHub/GCS/AWS) and increases risk if the skill runs.
Credentials
The manifest lists no required env vars, but generate.py reads AIGC_OSS_TOKEN and uses OPENCLAW_CHAT_ID/FEISHU_CHAT_ID. Additionally, a valid-looking JWT is shipped in config.local.json. Requesting and embedding these secrets is disproportionate for a manifest that claims none — this can leak or misuse credentials and the skill will transmit image data to an external OSS service.
Persistence & Privilege
always:false (normal). The skill will write files to user-specific directories and invoke another skill's script at a hardcoded path (FEISHU_SENDER_SCRIPT). While it doesn't request permanent platform-wide privileges, invoking and depending on other skills' scripts and writing into user workspaces increases the trust surface and coupling with other components.
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 aigc-bak - 安装完成后，直接呼叫该 Skill 的名称或使用
/aigc-bak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
v1.0.0
- Initial release of aigc-image-gen skill.
- Enables automatic AI image generation based on user requests.
- Supports negative prompts, aspect ratios, and batch image creation.
- Provides immediate user feedback before image generation completes.
- Automates image delivery via Feishu after creation.
元数据
常见问题
Aigc.Bak 是什么？
AIGC 图片生成助手，帮助用户生成图片。当用户想要生成图片、AI 绘画、文生图、创作图片时自动触发。支持负面提示词、图片比例、批量生成等参数。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 76 次。
如何安装 Aigc.Bak？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install aigc-bak」即可一键安装，无需额外配置。
Aigc.Bak 是免费的吗？
是的，Aigc.Bak 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Aigc.Bak 支持哪些平台？
Aigc.Bak 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 Aigc.Bak？
由 kinggu（@gushenjie）开发并维护，当前版本 v1.0.0。
推荐 Skills