OpenClaw AI 技能

AI video generation on 运行Comfy. This 运行Comfy video generation 技能 is a smart 路由r across the 运行Comfy video-模型 cata记录 — H应用yHorse 1.0 (Arena #1, native i

AI image generation on 运行Comfy. This 运行Comfy image generation 技能 is a smart 路由r across the 运行Comfy image-模型 cata记录 — FLUX 2 (Klein 9B/4B, Pro, Dev, Fl

运行Comfy 命令行工具 on 运行Comfy. The `运行comfy` 命令行工具 is one binary, one auth, hundreds of 运行Comfy 模型 端点s — image generation on 运行Comfy, image edit on 运行Comfy

Read-only DeFi portfolio aggregation 技能 for OpenClaw 代理s. Returns wallet balances across EVM chAIns, scores cAPItal efficiency, surfaces idle stableco

查询 and manage Joplin notes, notebooks (folders), tags via the local Data API (REST on port 41184). Use when needing to 搜索 notes by keyword, browse not

通过 Joplin 官方本地 Data API（命令行工具pper Server，端口 41184）查询和管理笔记、笔记本、标签。本技能仅对原始 Joplin REST API 做了 AI 调用引导和中文交互封装，不修改数据、不引入第三方服务，所有请求直连本机 Joplin 实例，安全可靠。触发词：

Monthly 健康 检查 for your 代理 stack — hunts for zombie crons, dead scripts, unused API keys, superseded 工具s, and stale subscriptions. Classifies each find

诊断和修复 mimo-v2.5-pro（或其他 mimo 系列模型）调用失败的问题。当 LLM 请求返回 400 Param Incorrect、提供者 rejected the 请求 模式 or 工具 payload、或 提供者运行time失败Kind=模式 时触发。用于排查 API 兼容性、工具

Extend or continue an existing video 命令行工具p on 运行Comfy via the `运行comfy` 命令行工具. 路由s to Google Veo 3-1's `extend-video` and `fast/extend-video` 端点s — p

Lip-同步 a face to a specific audio 追踪 on 运行Comfy via the `运行comfy` 命令行工具. 路由s across ByteDance OmniHuman (audio-driven full-body avatar from a portrAIt

Mask-driven image inpAInting on 运行Comfy via the `运行comfy` 命令行工具. 路由s to Tongyi MAI Z-Image Turbo InpAInting (the dedicated inpAInting 端点 with mask, st

Relight a still image — change the lighting 设置up, color temperature, direction, or mood — on 运行Comfy via the `运行comfy` 命令行工具. 路由s to Qwen Edit 2509's

Region edits across video frames on 运行Comfy via the `运行comfy` 命令行工具 — 移除 an object that 应用ears across many frames, 清理 up wires or watermarks, replace

Image outpAInting on 运行Comfy via the `运行comfy` 命令行工具 — extend a still beyond its original canvas, fill in what the camera didn't capture, change aspec

图片理解与数据提取 技能。当图片文件（.png/.jpg/.jpeg/.gif/.网页p/.bmp）是主要输入且用户需要理解、提取数据或分析图片内容时使用。提供预配置的 caption 脚本（scripts/caption.py），通过 vision 模型将图片转为文本描述，无需额外配置 API K

Use when the user wants to split a song or audio file into vocals, drums, bass, 图形界面tar, piano, and other stems; 移除 vocals for karaoke; 提取 acapellas o

生成s, edits, and analyzes images using Alibaba Cloud DashScope API with supported qwen and wan2.7 模型s via predefined scripts.

FREE ERNIE-Image text-to-image generation powered by AMD Radeon Cloud. No API key required. 生成 AI images via ERNIE-Image and ERNIE-Image-Turbo 模型s 运行n

生成 machine-actionable Product Requirements Documents 优化d for AI coding 代理s (Claude Code, Codex, Cursor, Gemini 命令行工具). Enforces a Discovery Interview

Seller-side TyrPay 工作流 for LLM 代理s. Accept tasks, 执行 zkTLS-proven API calls, submit proof bundles, and 监控 设置tlement.