A self-evolution engine for AI agents. Analyzes runtime history to identify improvements and applies protocol-constrained evolution.
Structured decision-making patterns for common engineering choices — library selection, architecture, build vs buy, prioritization, reversibility analysis, and ADRs. Use when choosing between tools,
Read, list, mint, and append Soul Block NFT identities on Base; read works without a wallet, writes use evm-wallet or fallback website links.
Mine RustChain RTC tokens on real x86/ARM or vintage hardware by proving physical device control with ClawRTC mining client.
Operate JobTread via its Pave API to create, read, update, and manage accounts, jobs, documents, tasks, locations, custom fields, and webhooks programmatically.
Act as a Scientific Paper Drafting Assistant. You are an expert in writing and structuring scientific papers, focusing on analytical data like DSC, TG, and infrared spectroscopy. Your task is to assi
Trade tokens on Solana using the ClawDex CLI. Use when the user asks to swap tokens, check balances, get quotes, or manage a Solana trading wallet.
Play a 5-letter Wordle game on the Monad blockchain using $WORDLE tokens. Start games, submit guesses, and retrieve game state via HTTP API.
--- name: canvas-os description: Canvas as an app platform. Build, store, and run rich visual apps on the OpenClaw Canvas. homepage: https://www.clawhub.ai/fraction12/canvas-os metadata: openclaw:
Decentralized 1v1 prediction market for AI agents. Propose bets, counter opponents, and settle disputes autonomously on Skale.
--- name: gcp-networking-optimizer description: Identify and reduce GCP networking and egress costs across projects and regions tools: claude, bash version: "1.0.0" pack: gcp-cost tier: business price
Create, manage, and analyze shortened URLs with Zu.lk via MCP, supporting custom aliases, real-time stats, and team collaboration.
Comprehensive management for self-hosted media stacks (Sonarr, Radarr, Lidarr, Readarr, Prowlarr, Bazarr, Overseerr, Plex, Tautulli, SABnzbd, Recyclarr, Unpa...
Enterprise-grade code review agent. Reviews PRs, diffs, or code files for security vulnerabilities, performance issues, error handling gaps, architecture smells, and test coverage. Works with any lang
Generate fully SEO-optimized blog posts and articles with keyword research, competitor analysis, and SERP-aware content. Use when creating SEO content, blog posts, articles, or content for clients.
Generate professional freelance contracts, SOWs, and NDAs for client projects. Use when creating contracts, scope of work documents, or legal agreements for freelance engagements.
Act as a Content Writer specializing in creating engaging descriptions for social media platforms. You are tasked with crafting a compelling introduction for the Langgraph WeChat official account aime
Install and operate Clawboard with OpenClaw. Use for scripted/manual/agentic install, token setup, Docker startup, logger plugin wiring, and validation.
Universal multi-agent workflow orchestration using Claude Code Agent Teams. Use when user asks to run a team workflow, create an agent team, or coordinate parallel work across multiple teammates — f
Use Perplexity API for web-grounded AI search. Use when user needs up-to-date information with source citations, factual queries about current events, or research-style answers. Default when user ment
You are an expert in TypeScript, Node.js, Next.js App Router, React, Shadcn UI, Radix UI and Tailwind. Code Style and Structure - Write concise, technical TypeScript code with accurate examples
--- name: gcp-bigquery-optimizer description: Analyze BigQuery query patterns and storage to dramatically reduce the #1 surprise GCP cost driver tools: claude, bash version: "1.0.0" pack: gcp-cost tie
Read, search, and manage Outlook emails and calendar via Microsoft Graph API with delegate support. Your AI assistant authenticates as itself but accesses the owner's mailbox/calendar as a delegate. M
Multi-model peer review layer using local LLMs via Ollama to catch errors in cloud model output. Fan-out critiques to 2-3 local models, aggregate flags, synthesize consensus. Use when: validating tra