Ai intelligence

Virtual gene knockout simulation using foundation models to predict transcriptional

This skill generates storyboard prompts for Seedance 2.0

Run the agent like an executive operator with calm briefings, sharp prioritization, context recovery, and proactive follow-through.

Build and debug Kimi API workflows for chat, coding, reasoning, and tool-calling with live model checks, retries, and safe routing.

给 OpenClaw 加一个真正可长期使用的桌面身体：流体玻璃球 UI、14 情绪系统、语音播报/声音克隆、Setup Wizard、Doctor 自检、模型热切换、Gateway 守护...

Generate images via Krea.ai API — Nano Banana 2 (default), Flux, Imagen 4, Seedream 3, Ideogram 3.0, Nano Pro/base. Returns direct URLs.

基于 L0/L1/L2 三层结构的分层记忆管理系统，大幅减少 Token 消耗。L0 节省 99% Token（摘要层），L1 节省 88%（概览层），L2 为完整内容。支持自动生成分层文件、智...

在 GPU 服务器上部署 LLM 模型服务（vLLM）。支持多服务器配置，自动检查 GPU 和端口占用，一键部署流行的开源大语言模型。...

Generate videos from text descriptions using ZhipuAI CogVideoX-3 model. Supports text-to-video, image-to-video, and first/last frame-to-vide...

Run and integrate LM Studio with local model lifecycle control, OpenAI-compatible APIs, embeddings, and MCP-aware workflows.

龙虾价值观引擎 - 约束所有输出和决策逻辑，确保符合"时安式"进化原则（安全主权、诚实求真、主动进化）...

Intelligently recommends optimal AI models based on task requirements. Dynamically reads the user's OpenCLAW configuration and provides cont...

本地向量记忆工具，替代内置 memory 工具。使用 ChromaDB + BGE-small-zh 实现完全离线的语义记忆存储和检索。使用场景：(1) 存储重要信息到长期记忆，(2) ...

Start from what must be true. Stop answering on autopilot.

Optimizes for minimal token usage. Removes fluff, eliminates step-by-step narration, and delivers results-only communication.

识别图片中的K12算式（加减乘除、竖式计算、分数、方程等），返回结构化文本结果。 支持手写体和印刷体，可拒绝非算式图片。 触发条件：用户要求识别算式、数学...

Long-term memory for OpenClaw agents using the Memori SDK. Capture conversations and intelligently recall context across sessions automatica...

Persistent memory system for OpenClaw agents: reads session logs, extracts facts/decisions/solutions, manages temperature-based lifecycle, a...

OpenClaw 3.8+ 智能上下文管理与记忆系统插件

Build with MiniMax text, speech, video, and music APIs using model routing, compatible SDKs, and safer multimodal workflows.

基于百度AI搜索按自定义关键词收集资讯，生成Markdown简报并定时推送到飞书。

Setup and utility scripts for muapi.ai — configure API keys, test connectivity, and poll for async generation results

Set up shared memory between multiple OpenClaw agents so they stay in sync without the user repeating context. Use when a user has 2+ agents...

多线程对话架构：主代理前台响应，子代理后台处理任务，支持打断、状态处理、两阶段审查和任务监控 / Multi-thread dialogue architecture: main agent resp...

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).