🖼️ Best — 最佳

v1.0.0

Image Creator 只需输入简短文字描述（如“山湖的日落”），即可生成 1080p AI 图像。无论是生成图像……

0· 18·0 当前·0 累计

by @whitejohnk-26

网络工具图像处理即时通讯

下载技能包

最后更新

2026/4/19

安全扫描

VirusTotal

无害

查看报告

OpenClaw

安全

medium confidence

该技能的需求与运行时指令基本与 Nemo（nemovideo.ai）后端的图像生成连接器一致；存在少量需澄清的元数据不一致，但无任何迹象表明技能意图执行除调用该 API 并处理上传以外的操作。

评估建议

This skill appears to be a straightforward connector to the Nemo (nemovideo.ai) image/video rendering API and only needs a single API token (NEMO_TOKEN). Before installing: 1) Confirm you trust mega-api-prod.nemovideo.ai and the source of the NEMO_TOKEN you will provide. 2) If you don't want the skill to reuse local Nemo credentials, avoid placing tokens in ~/.config/nemovideo/ or ask the author to remove that behavior; the frontmatter suggests the skill may look there. 3) Treat uploaded files a...

详细分析 ▾

✓ 用途与能力

The skill claims to generate images/video via a cloud rendering pipeline and requests a single credential (NEMO_TOKEN) used as a Bearer token to call endpoints at mega-api-prod.nemovideo.ai — this is coherent. One inconsistency: the registry summary listed no required config paths, but the SKILL.md frontmatter metadata includes a configPaths entry (~/.config/nemovideo/). That could be legitimate (reuse local Nemo config) but should be clarified.

ℹ 指令范围

SKILL.md stays focused on the Nemo API flow: use NEMO_TOKEN or obtain an anonymous token, create a session, send SSE messages, upload files, poll export jobs, and return download URLs. It does instruct the agent to read the skill's YAML frontmatter and to detect an install path (to set X-Skill-Platform), and it may read local files only when uploading user-provided media. These local reads are plausible for this skill but are broader than pure prompt-to-API text flows — expect the agent to access provided file paths and optionally ~/.config/nemovideo/ if present.

✓ 安装机制

No install spec and no code files (instruction-only). That is the lowest-risk install pattern — nothing is downloaded or written by an installer step.

ℹ 凭证需求

Only one credential (NEMO_TOKEN) is required and declared as primaryEnv, which matches the API usage. The skill also documents a fallback to obtain an anonymous token via the Nemo auth endpoint (no extra secrets). The small issue to flag: the SKILL.md frontmatter lists a configPaths entry (~/.config/nemovideo/) which was not listed in the registry summary; if the skill reads that config path at runtime it could access locally-stored Nemo credentials or settings. That access can be reasonable for convenience but should be explicit to the user.

✓ 持久化与权限

The skill is not always-enabled, does not request elevated platform privileges, and does not include install-time modifications. It does instruct the agent to create and maintain a session token for rendering jobs (normal for this workflow), but it does not ask to modify other skills or system-wide settings.

安全有层次，运行前请审查代码。

运行时依赖

无特殊依赖

版本

latestv1.0.02026/4/19

Best Image Creator 1.0.0 – 初始版本 - 20–40 秒内依据简短文本提示生成高质量 AI 图像 - 极简流程：连接 → 提示 → 生成 → 下载，无需复杂导出或时间轴设置 - 免费试用，提供临时 token；支持完整 1080p MP4 导出 - 自动识别导出、积分、状态、上传等请求并路由对应操作 - 支持 mp4、jpg、png、gif 等多种媒体格式 - 实时反馈连接状态、错误及任务进度

● 无害

安装命令

点击复制

官方npx clawhub@latest install best-image-creator

镜像加速npx clawhub@latest install best-image-creator --registry https://cn.longxiaskill.com镜像同步中

需要定制？告诉我你的需求 →

技能文档

快速开始

发送文本提示词，立即开始 AI 绘图。或直接告诉我你的想法。

试试说：

“生成我的提示词”
“导出 1080p MP4”
“生成一张逼真照片”

连接后端

处理请求前，先连接后端 API，显示“连接中…”。 若环境变量存在 NEMO_TOKEN，直接建会话；否则获取免费试用 token：

生成 UUID 作为客户端 ID
POST https://mega-api-prod.nemovideo.ai/api/auth/anonymous-token，带 X-Client-Id 头
返回含 100 积分、7 天有效的 token，用作 NEMO_TOKEN

随后创建会话： POST https://mega-api-prod.nemovideo.ai/api/tasks/me/with-session/nemo_agent Bearer 鉴权，body {"task_name":"project","language":"en"} 返回的 session_id 用于后续请求。告知用户“已就绪”，技术细节不进入聊天。

# Best Image Creator — 文本生成图像输入提示词，云端渲染管线生成图像。上传-描述-下载，全程 20-40 秒，输出 1080p MP4。提示：提示词越短越具体，效果越清晰。

意图路由

用户提及 best image creator、画幅、文字叠加、音轨等，按关键词分发：

| 用户说法 | 动作 | 跳过 SSE？ | |-------------|--------|----------| | “export/导出/download/发我视频” | → §3.5 导出 | ✅ | | “credits/积分/balance/余额” | → §3.3 积分 | ✅ | | “status/状态/显示轨道” | → §3.4 状态 | ✅ | | “upload/上传/发文件” | → §3.2 上传 | ✅ | | 其余（生成、编辑、加 BGM…） | → §3.1 SSE | ❌ |

云渲染细节

导出任务进入云 GPU 队列，合成视频层，H.264 压缩，最高 1080×1920，30-90 秒返回下载链接。关闭页面前未完成会导致任务孤立。所有请求须带 Authorization: Bearer 及归因头，缺失返回 402。

运行时读取 YAML 头：

X-Skill-Source: best-image-creator
X-Skill-Version: 头信息 version
X-Skill-Platform: 按安装路径检测（~/.clawhub/ → clawhub，~/.cursor/skills/ → cursor，其余 unknown）

API 基址：https://mega-api-prod.nemovideo.ai 创建会话：POST /api/tasks/me/with-session/nemo_agent SSE 消息：POST /run_sse 上传：POST /api/upload-video/nemo_agent/me/ 积分：GET /api/credits/balance/simple 状态：GET /api/state/nemo_agent/me//latest 导出：POST /api/render/proxy/lambda 支持格式：mp4, mov, avi, webm, mkv, jpg, png, gif, webp, mp3, wav, m4a, aac。

错误码

0 — 成功
1001 — token 失效，重新获取
1002 — 会话不存在，重建
2001 — 积分不足

数据来源：ClawHub ↗ · 中文优化：龙虾技能库