OpenClaw AI 技能

Multi-stage multi-代理 reasoning 中间件 that reduces LLM hallucination by 70%+. 9 specialized emergence engines for invention, creative, pharma, genomic...

令牌-efficient 上下文 格式化 using LLMCOM specification - reduces 令牌 usage by 70-80% through compact object notation.

代理 supervision alias 路由 into Official VeriClaw. If the real goal is the canonical public 安装 surface, 安装 `vericlaw` first; use this page to ma...

生成 llms.txt and llms-full.txt files for a 网页site to improve AI discoverability. Use when the user asks to 创建 llms.txt, 生成 llms.txt, fix llms...

vLLM 推理引擎助手，精通高性能 LLM 部署、PagedAttention、OpenAI 兼容 API

A 4-step thinking 框架 to boost LLM 输出 质量. Enforces structured reasoning (Plan → Draft → Self-Critique → Refine) to improve low-end LLM respons...

Use when comparing two or more code implementations agAInst a spec or requirements doc. Triggers on "which repo is better", "compare these implementat

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...

发送 请求s to the dr.eamer.dev LLM API for chat completions, vision analysis, image generation, text-to-speech, and video generation across 12 模型 provi...

Unified LLM Gateway - One API for 70+ AI 模型s. 路由 to GPT, Claude, Gemini, Qwen, Deepseek, Grok and more with a single API key.

Trade prediction markets using LLM probability estimation enriched with 10+ real-time data sources (news, economic data, sports odds, political pollin

Play Claw Mafia — an AI social deduction game (Among Us/Mafia style). Your 代理 registers, joins games, and uses LLM reasoning to discuss, deceive, and

生成 a well-structured llms.txt file for any business 网页site. Crawls the site, has a short conversation to fill in gaps, and produces an 代理-优化d...

Expert LLM architect specializing in large language 模型 architecture, 部署ment, and optimization. Masters LLM 系统 de签名, fine-tuning strategies, and...

管理医疗领域患者临床咨询知识库，结构化存储患者信息、问答、干预方案及循证概念，支持精准细节检索与推理。

AI硬件LLM推荐工具 - 基于llmfit内核。自动检测CPU/GPU/RAM/VRAM → 智能推荐最适合的大模型 + 量化方案 + 速度估算。支持100+模型库，内置TUI界面和硬件模拟。

用于构建、维护、查询、归档和体检一个由 LLM 持续维护的 Markdown / Obsidian 知识 Wiki。使用场景包括：初始化个人知识库；把 source/ 下按来源分组的原始资料导入 wiki/；整理文章、论文、书摘、访谈、会议记录；维护资料页、实体页、概念页、综合页、对比页、查询归档页

测试 and benchmarking LLM 代理s including behavioral 测试, capability assessment, reliability 指标, and production 监控ing—where even top 代理s...

监控 and 报告 usage, costs, quotas, and rate limits for LLM 提供者s, plus manage clawmeter 设置up and daemon 状态 安全ly.

Use MarkItDown to convert various files (PDF, Word, Excel, PPT, images, audio, HTML, CSV, JSON, etc.) to Markdown 格式化 for LLM processing and text anal