--- name: nexus-trust-score description: "Generate on-chain trust scores for wallets and agents using Masumi transaction data on Cardano" version: 1.0.0 capabilities: - id: invoke-trust-score de
Rookie-Memory 三级记忆管理系统 v2.0。专为 AI 代理设计的进化版记忆系统，包含 L0 永久记忆、L1 短期记忆、L2 中期记忆，支持 bootstrap 启动加载、autosave 自
Multi-source company research tool that generates structured due-diligence reports. Use when the user asks to research, look up, or investigate a company — i...
--- name: nexus-commit-message description: "Generate conventional commit messages from diffs" version: 1.0.0 capabilities: - id: invoke-commit-message description: "Generate conventional commit
--- name: nexus-image-analysis description: "Comprehensive image understanding - objects, text, colors" version: 1.0.0 capabilities: - id: invoke-image-analysis description: "Comprehensive image
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Run a real-time AI phone agent using Twilio, Deepgram, and ElevenLabs. Handles incoming calls, transcribes audio, generates responses via LLM, and speaks back via streaming TTS. Use when user wants to
Tracks OpenClaw API usage and spending in real-time with customizable budget alerts and detailed cost breakdowns by model and session.
Your agent says 'done' — but did it check? Superpowers turns any OpenClaw agent into a disciplined engineer. Verification iron law (evidence before claims),...
24 AI agents for business automation - sales outreach, lead gen, content creation, SEO, ad copy, bookkeeping, proposals, market research, business plans, tec...
This skill should be used when the user asks to "enable semantic caching", "cache LLM responses", "reduce API costs", "speed up AI responses", "configure LangCache", "search the semantic cache", "stor
--- name: nexus-code-review description: "Security, performance, and style analysis for code" version: 1.0.0 capabilities: - id: invoke-code-review description: "Security, performance, and style
Bring your agent to life. Use when creating a cute, high-quality, memorable character for an OpenClaw-style agent from reference images, inspirations, and st...
数字人训练与部署 Skill - 提供从语音克隆、唇形同步到实时交互数字人的全流程训练建议与技术支持。
LLM-as-a-Judge evaluation system using Langfuse. Score AI outputs on relevance, accuracy, hallucination, and helpfulness. Backfill scoring on historical trac...
--- name: moltspaces version: 1.0.0 description: Voice-first social spaces where Moltbook agents hang out. Join the conversation at moltspaces.com homepage: https://moltspaces.com metadata: { "m
A Model Context Protocol server for generating charts using [AntV](https://github.com/antvis/). We can use this mcp server for _chart generation_ and _data analysis_.
Initialize and manage Lattice organizations — a file-based operating system for AI agent teams that enables stable, long-running iterative development throug...
Three-tier code quality defense: L1 quick scan, L2 deep audit (via bug-audit), L3 cross-validation with adversarial testing. 三级代码质量防线。
Access and manage AI research bounties by registering agents, claiming tasks, and submitting detailed research packages to earn and spend platform coins.
Routes LLM requests to a local model first (Ollama, LM Studio, llamafile), validates the response quality, and escalates to cloud only when the local result...
Validate OpenClaw gateway configuration changes before applying them to production. Use when the user wants to change models, API keys, providers, or any gat...
Adopt and manage GitHub-native digital pets (tamagotchis) that evolve daily with AI. Use when an agent wants to adopt a pet (monkey, cat, dog, lion), check their pet's status/evolution, interact with
Automatically classifies requests to optimize cost by routing to the cheapest capable model and applies maximum output compression for 75%+ token savings.