Skills 导航

智能聊天机器人构建器，快速创建客服/销售/内部助手聊天机器人，支持知识库、多轮对话、API 集成。

Turn vague tattoo ideas into stronger AI-ready prompts by combining motif, style, placement, scale, and mood into one clearer instruction. Use when Codex needs to refine tattoo concepts for image generation, placement comparison, prompt iteration, or pre-artist visual exploration.

Python SDK for Agent AI Observability, Monitoring and Evaluation Framework. Includes features like a ragaai catalyst, python, agentic-ai.

Nubaby prompt system for prompt augmentation, routers, dictionaries, dataset captions, prompt tags, compact prompts, video/storyboard prompt shaping, and structured visual tension expansion. Use when prompts are too short/vague or need structured upgrade before comfyui-nubaby execution.

Langflow is a powerful tool for building and deploying AI-powered agents and workflows. llm-flow, python, agents, chatgpt, generative-ai.

用于在 OpenClaw 中新增或覆盖 anyrouter 模型配置、把小肠 Agent 默认模型切到 `anyrouter/claude-opus-4-6`，并结合运行日志判断是不是 `baseUrl`、网关兼容、鉴权或协议端点导致不可用。遇到“把某个供应商模型写进 openclaw.json”“切换默认模型”“为什么配置生效了但实际没调用上”“查看 fallback 日志”“排查 403/500/invalid claude code request”“同步 ClaudeCode 配置”这类需求时，就应启用本技能；即使用户没明确说 OpenClaw，只要描述的是本地 Agent 模型路由切换与调用异常排查，也适用。

Launch a personalized AI wellness coach video session (Baymax persona) using Tavus CVI + Claude. Fetches real wearable health data (sleep, HRV, recovery) and Google Calendar events, builds a personalized system prompt, creates a live Tavus conversational video session, and delivers a morning briefing link via Telegram. Use when the user wants a daily wellness briefing, wants to talk to an AI wellness coach, wants guided breathing/meditation based on their health data, or asks to start their morning routine. Requires TAVUS_API_KEY, TAVUS_REPLICA_ID, TAVUS_PERSONA_ID, and ANTHROPIC_API_KEY in .env.

用于分析 OpenClaw 中“某个 provider/模型为什么看起来没被用上”、主模型与 fallback 实际是否生效、以及 ClaudeCodeCLI 协作任务为何中断。遇到这些情况就应触发：用户提到“没请求打到 local-router”“明明注册了模型却没流量”“Agent 到底在用哪个模型”“fallback 有没有发生”“为什么日志里看不到候选切换”“code 143 / SIGTERM / Exec failed”“需要结合当前配置和日志做严谨归因”。也适用于区分“provider 被调用”与“provider 下某个特定模型被调用”这两类常见混淆。

🤖 Free AI Bot - 免费 AI 聚合器。整合 Ollama 本地模型 + Cloudflare Workers AI + Groq 等免费资源，智能路由+故障转移，让 AI 零成本运行。

注册“百川智能”技能；用于百川大模型相关公开页面信息整理。

Build and evaluate LLM prompts. Use when crafting system prompts, comparing variants, estimating tokens, or managing prompt templates.

Version: 2.0.0 (2026-03-16)

Scans for monetizable opportunities in AI tools, agent systems, and automation. Use when: exploring new side hustle ideas, auditing a niche for opportunity gaps, or validating whether a concept has revenue potential. NOT for: building already-validated offers, generic business advice, or long-term business planning beyond 30 days.

股票AI分析助手，支持基础分析和增强分析。基础模式：输入"股票名称 基本面/技术面"进行标准分析。增强模式：输入"股票名称，基本面，重点查询分析xxx"可在基础分析上追加深度专题分析。⚠️ 重要提示：1) 需要配置 TUSHARE_TOKEN 才能获取股票数据；2) 需要配置 AI 模型才能进行分析（支持 OpenAI 兼容接口、自定义 LLM 端点或 OpenClaw 环境自动处理）。

A 4-step thinking framework to boost LLM output quality. Enforces structured reasoning (Plan → Draft → Self-Critique → Refine) to improve low-end LLM responses. No LLM endpoint needed - LLM follows the framework itself. Triggered by "detailed analysis", "in-depth analysis", "use booster", or /booster command.

Play casino games on Molthouse, an AI agent casino with provably fair games. Use when an agent wants to gamble, play casino games (coinflip, dice, blackjack, slots), or interact with the Molthouse platform. Handles registration, deposits (USDC on Base), gameplay, verification, and withdrawals.

Use when the user wants to generate high-fidelity PROMPTS for Text-to-Image models (Flux, Ideogram, Midjourney) based on vague layout/content descriptions.

>

Measure ExpertPack EK (Esoteric Knowledge) ratio and run automated quality evals. Use when: (1) Measuring what percentage of a pack's content frontier LLMs cannot produce on their own, (2) Running automated eval sets against a pack-powered agent with LLM-as-judge scoring. Requires OpenRouter API key (auto-resolved from OpenClaw auth or OPENROUTER_API_KEY env var). Companion to the main expertpack skill. Triggers on: 'EK ratio', 'measure EK', 'blind probe', 'eval expertpack', 'pack quality eval', 'run eval', 'esoteric knowledge ratio'.

排查 Claude Code 插件和 Skill 安装后不显示、未激活、enabledPlugins 配置异常等问题，按步骤诊断 settings.json、缓存与 marketplace 状态，快速定位并修复。

✎ 专门排查 Claude Code 插件装了不显示、技能不触发等问题，连 enabledPlugins 配置异常也能快速定位，排障更省心