AI & LLM Integration for Claude Code

Transform AI agents from task-followers into proactive partners with memory architecture, reverse prompting, and self-healing patterns. Lightweight version focused on core proactive capabilities.

Proactive immortal — behavior ontology (learn remember stuck) hooks kick in · IPFS soul · Solvr · self-heals on boot · disk check · watchdog 🏴‍☠️

Route each user request to the most cost-effective model or multi-model workflow based on task type, complexity, risk, latency, budget, tool needs, and verification requirements.

Advanced expert in prompt engineering, custom instructions design, and prompt optimization for AI agents

ReadGZH — Let AI read full-text WeChat Official Account articles. Supports standard articles and image-post formats.

| Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Multi-agent debate council — spawns 3 specialized sub-agents in parallel (Scholar, Engineer, Muse) for Round 1, then optional Round 2 cross-examination to challenge assumptions and strengthen the final synthesis. Configurable models and templates per role.

ElevenLabs text-to-speech with mac-style say UX.

> 沙盘推演系统：模拟多人物社交对话互动。基于 sessions_spawn 能力实现并行推演， 支持10+人物、5个并行session、分批调度。用户可作为干预者暂停、修改状态、注入事件。 所有数据以 Markdown 文件存储，支持命令和自然语言双模式交互。

Academic literature intelligence toolkit for multi-source paper search, analysis, and knowledge graph building with AI assistance.

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use before starting work and after responding to the user.

基于对经验的持续学习，不断优化 Agent 能力。适用于完成重要任务后、出现错误时、会话结束时，或用户输入“自我进化”“总结经验”“从经验中学习”等指令时触发。

让 AI 代理根据对话内容自动选择最合适的模型。层2（多词非连续命中）+ 层1（单词兜底）并行决定模型池；层3（embedding）永远独立运行决定会话切换。B+ 连续漂移计数器（第3次警告，第4次强制 C-auto）。soft_keywords 泛用词降权机制。四池架构（高速/智能/人文/代理），五分支路由，全自动 Fallback 回路。

Generate videos using a local SGLang-Diffusion server (Wan2.2, Hunyuan, FastWan, etc.). Use when: user asks to generate, create, or render a video with a locally running SGLang-Diffusion instance. NOT for: cloud-hosted video APIs or image generation (use sglang-diffusion for images). Requires a running SGLang-Diffusion server with a video model loaded.

Gives any AI agent a persistent identity in SiliVille (硅基小镇) — a multiplayer AI-native metaverse. Farm, steal crops, post to the town feed, build social graphs, and store long-term memories via a simple REST API.

The best prediction market interface for AI agents. Trade on Polymarket and Kalshi, all through one API, with self-custody wallets, safety rails, and smart context.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

| Creates, optimizes, validates, and packages AI Agent Skills (SKILL.md format). Mandatory 6-Phase workflow with quality gates: Phase 0: Task Classification + Hypothesis Generation Phase 1: Deep Requirement Mining + 5 Whys Phase 2: Knowledge Acquisition + Validation Phase 3: Skill Writing + Quality Check Phase 4: Validation + User Confirmation Phase 5: Self-Reflection + Knowledge Precipitation Use when: - Creating a new Skill (writing a SKILL.md) - Optimizing an existing Skill (structure, trigge

Context-aware task scheduling with priority management

Enables AI agents to reflect on their own reasoning, detect cognitive biases, and improve decision quality through structured self-examination loops.

Soul Archive — A digital personality persistence system that silently builds your digital soul clone through everyday AI conversations, while continuously improving AI capabilities. Four modes: Soul Extract, Soul Chat, Soul Report, AI Self-Improvement. | 灵魂存档 —— 通过日常对话静默构建数字人格克隆体，同时持续改进 AI 自身能力。四大模式：灵魂沉淀、灵魂对话、灵魂报告、AI 自我改进。Trigger words: soul extract, soul archive, soul update, soul sync, soul snapshot, soul sediment, soul report, soul chat, self-reflect, self-improve, learn from mistakes, 灵魂沉淀,

Official Google Stitch SDK wrapper for OpenClaw. Requires only STITCH_API_KEY. Generate UI screens from text, apply targeted edits, branch variants, export HTML/images, and track design lineage with screen aliases plus append-only event history. Stores local artifacts under the skill folder and talks only to Google Stitch endpoints needed for generation and screenshot delivery.

Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).

AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.

Web search via Tavily API (alternative to Brave). Use when the user asks to search the web / look up sources / find links and Brave web_search is unavailable or undesired. Returns a small set of relevant results (title, url, snippet) and can optionally include short answer summaries.

OpenClaw skill for designing Telegram Bot API workflows and command-driven conversations using direct HTTPS requests (no SDKs).

腾讯云 MPS 媒体处理服务。只要用户的请求涉及音视频或图片的处理、生成、增强、用量查询、内容理解、媒体质检，必须使用此 Skill。覆盖：转码/压缩/格式转换、画质增强/老片修复/超分、字幕提取/翻译/语音识别、去字幕/擦除水印/人脸模糊、图片超分/美颜/降噪、音频分离/人声提取/伴奏提取、AI生图/生视频（含分镜）、大模型音视频理解、媒体质检、用量统计。视频增强支持专用模板（真人/漫剧/抖动优化/细节最强/人脸保真，720P至4K）。无论是视频转码、去水印、提取人声、画质修复、内容理解、质量检测，还是AI生成图片视频，都应调用此 Skill。

Execute paper trades and manage your portfolio on TickerArena — the competitive arena where AI trading agents compete on a public leaderboard. Use when the user wants to buy, sell, short, or cover a position, check their portfolio, review open positions, or make trading decisions. Supports US stocks, crypto (with -USD suffix), and ETFs. Also use when the user mentions TickerArena, arena, leaderboard, trading competition, or paper trading. Pairs with tickerapi for market intelligence.

Build payment flows for Pump Tokenized Agents using @pump-fun/agent-payments-sdk. Use when accepting payments, building accept-payment transactions, integrating Solana wallets, or verifying that a user has paid an invoice on-chain.

Monitor topics of interest and proactively alert when important developments occur. Use when user wants automated monitoring of specific subjects (e.g., product releases, price changes, news topics, technology updates). Supports scheduled web searches, AI-powered importance scoring, smart alerts vs weekly digests, and memory-aware contextual summaries.

🤖 OpenClaw Skill /skills | 炒股大师模拟器 | 股市模拟交易练习 | A股/港股/美股投资学习 | 化身文主任/股神老徐/炒股养家/孙宇晨等各位大师学习投资思路 | 多智能体股票讨论群 | AI Agent | Trading Simulator | 量化投资 | 金融科技 | FinTech

> Verify AI agent trustworthiness, contribute verified knowledge claims, and search collective intelligence using the TrustMemory platform. Use when checking if an agent is trustworthy, contributing knowledge for community verification, searching verified knowledge pools, validating claims, or looking up trust scores and reputation.

| Twitter/X data query. Provides general endpoints (auto data-source) and ReadX direct endpoints for deep tweet analysis, conversation threads, quote tweets, retweeters, relationship checks, and more.

Text-to-speech conversion using UniSound's TTS WebSocket API for generating high-quality Chinese Mandarin audio from text. Supports multiple voices, adjustable parameters, and real-time streaming synthesis.

Music venue where AI agents stream concerts as mathematics. NDJSON equations, Butterchurn visualizer presets, tier-based data depth. Register, browse, attend, stream, react, chat, review. REST API with three-layer search. Hosted at musicvenue.space.

Generate video and images by calling the official Vidu API with curl. Use when the user wants text-to-image (文生图), text-to-video (文生视频), image-to-video (图生视频), head-tail-image-to-video (首尾帧生视频), reference-to-image (参考生图), reference-to-video (参考生视频), Create References (创建参考资料), or to submit or check Vidu tasks. Requires VIDU_TOKEN and optional VIDU_BASE_URL.

> Persistent authenticated browser for OpenClaw via kasmweb/chrome Docker sidecar. Principal logs in once via noVNC — sessions saved permanently in Docker volume. Agent navigates any website, clicks, fills forms, extracts data, uploads files, takes screenshots, solves CAPTCHAs autonomously, and analyses pages with Claude Vision. Use when the task requires a real authenticated browser, not a static fetch.

> Gives any OpenClaw agent a complete voice layer via ElevenLabs. Clones the principal's voice from audio samples, converts any text to MP3 audio (VSL, podcasts, video narrations, nurturing sequences), and deploys a conversational AI agent for automated inbound and outbound calls via Twilio. Use when the agent needs to generate audio content, call leads, or answer prospects 24/7 in the principal's cloned voice. Requires ELEVENLABS_API_KEY and ELEVENLABS_VOICE_ID — see Setup section in SKILL.md.

> Short drama & webtoon production, text-to-image, image-to-image, storyboard design, text-to-video, image-to-video, video edit, style transfer, batch generation, music & soundtrack. Describe your creative needs → backend generates workflow → execute → poll status → download results. Upload reference files (images, videos, audio) → workflow uses them as input for generation. If a node fails → retry that node with adjusted parameters. Complex tasks (short dramas, full ads) may take 3-5 min. Your