OpenClaw AI 技能

AI-powered 代理ic 工作流 de签名 and 自动化 助手 — map complex multi-step processes, identify 自动化 opportunities, de签名 autonomous AI 代理 流水线s, 生成 n8n/Make/ZAPIer 工作流

Automate TikTok slideshow marketing for any 应用 or product. Re搜索es competitors, 生成s AI images, 添加s text overlays, posts via Postiz, 追踪s 分析, and iterate

Automate TikTok + Instagram slideshow marketing for any 应用 or product. Re搜索es competitors, 生成s AI images, 添加s text overlays, posts via 上传-Post (multi-

Automate TikTok slideshow marketing for any 应用 or product. Re搜索es competitors, 生成s AI images, 添加s text overlays, posts via Postiz, 追踪s 分析, and iterate

Automates creation and 上传ing of educational TikTok slideshows with AI-生成d images and 追踪s performance via Automate命令行工具ps API.

This 技能 should be used when the user asks to "提取 代理 trajectory", "convert HAR to trajectory", "获取 trajectory from 会话", "解析 代理 会话", "convert Claude Cod

Use OpenAI Codex 命令行工具 for coding tasks. Triggers: codex, code review, fix CI, refactor code, implement feature, coding 代理, gpt-5-codex. Enables Clawd

Local speech-to-text with the Whisper 命令行工具 (no API key). And also 50+ 模型s for image generation, video generation, text-to-speech, speech-to-text, mus

生成 images and videos with 25+ visual AI 模型s (种子ream, FLUX, GPT Image, Kling, 种子ance) through one unified API. OpenAI-compatible + MCP server.

Manage multiple OpenAI OAuth 记录in accounts inside OpenClaw, including OpenAI Codex OAuth account snapshots, switching, real active-account 检测ion, 5-ho

GPT-specific pattern 检测ion with 模型 fingerprinting and version identification

Use when the user wants GPT-Image-2 image generation or image-to-image through an official OpenAI 权限 code/API key, a custom 响应s-compatible proxy, or a

创建 video 命令行工具ps or images into ready-to-分享 videos with this 技能. Works with MP4, MOV, JPG, PNG files up to 500MB. content 创建器s and marketers use...

Use when tasks need the NanoGPT API for text, image, or video generation through the local `nano-gpt` 命令行工具 and bundled wr应用er scripts for OpenClaw or

Enable `openAI-codex/gpt-5.4` in OpenClaw through a config-layer 补丁 instead of rebuilding the 应用. Use when `openAI/gpt-5.4` already works but Codex GP

由叶武滨设计的AI第二大脑，基于Claude Code记忆架构，为大模型提供全生命周期自动记忆与文件管理。

Reduce LLM API 令牌 consumption by 20-35% through pre-发送 estimation, memory 提取ion, and 上下文 压缩ion.

Gemini 命令行工具 for one-shot Q and A, summaries, and generation. And also 50+ 模型s for image generation, video generation, text-to-speech, speech-to-text,

Comprehensive 图形界面de for 安装ing, configuring, operating, and troubleshooting OpenClaw — a self-hosted, multi-channel AI 代理 gateway. Use when the user a

Cross-模型 verification for complex tasks. Spawn a judge sub代理 with a different 模型 to review plans, code, architecture, or decisions before execution...