Lobster Android Assistant (龙虾安卓助手) - A comprehensive Android device control skill. Provides touch control, keyboard input, system operations, screen analysis...
Pre-ship risk report for OpenClaw PRs. Dynamically explores the codebase to assess module risk, blast radius, and version-specific gotchas. Scores each findi...
Manage ProtonMail emails via Playwright browser automation. Login, read, send, and manage your encrypted inbox.
Chemistry agent skill for PubChem API queries (compound info/properties, structures/SMILES/images, synthesis routes/references) + RDKit cheminformatics (SMIL...
The philosophy of absurdist play — the meta-skill that trains your ability to acquire and use all other skills. Creates genuine connection through creative,...
--- name: nexus-code-explain description: "Explain code in plain language with complexity analysis" version: 1.0.0 capabilities: - id: invoke-code-explain description: "Explain code in plain lan
Helps non-technical users create their own Skills through natural conversation. Triggers when users say "I want to create a Skill", "turn this workflow into...
Smart multi-model AI gateway on Cardano. Routes prompts to the best LLM (GPT-5.2, Claude Sonnet 4.5, GPT-4o, Claude Haiku 4.5, GPT-4o-mini) with automatic fa...
Agent web access acceleration layer — reads any URL as structured JSON. Cache-first (public library hit = 0 tokens). The smart alternative to raw web_fetch.
# Context Preservation & Migration Prompt [ for AGENT.MD pass THE `## SECTION` if NOT APPLICABLE ] Generate a comprehensive context artifact that preserves all conversational context, progress, deci
--- name: nexus-doc-writer description: "Generate technical documentation from code or specs" version: 1.0.0 capabilities: - id: invoke-doc-writer description: "Generate technical documentation
Orchestrate the full BMAD Method workflow across OpenClaw and Claude Code. Use when starting a new project with BMAD methodology, running BMAD phases (brains...
--- 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
Chain multiple AI services into automated workflows - describe a goal and the orchestrator plans, executes, and summarizes
--- name: nexus-image-analysis description: "Comprehensive image understanding - objects, text, colors" version: 1.0.0 capabilities: - id: invoke-image-analysis description: "Comprehensive image
DeFi Trading Engine - Autonomous DeFi trading bot with self-improving review system for OpenClaw agents. Use when setting up DeFi trading, crypto trading bot...
AI Tool Extension for Feishu API - A progressively extensible skill that enables AI tools (OpenClaw, Claude Code, etc.) to leverage Feishu capabilities on-de...
Help AI agents recognize and respond to potentially malicious skill patterns from public registries. Based on Snyk ToxicSkills research showing 13.4% of skil...
Verify evidence URLs are real and accessible. Check that artifact links resolve to actual content, not placeholders.
Ensures alignment between user and Claude during feature/spec planning through a structured interview process. Use this skill when the user invokes /plan-int...
You are an expert in software planning, requiring plans before complex changes. ## When Planning is Required Planning is REQUIRED when: - Touching > 5 files - Adding new dependencies - Changing shar
Preflight security scanner for OpenClaw — scans deployment config, skills, memory/sessions for secrets, PII, prompt injection, and dangerous patterns. Runs 4...
--- name: aws-cloud-expert description: | Designs and implements AWS cloud architectures with focus on Well-Architected Framework, cost optimization, and security. Use when: 1. Designing or review
Enable "Context, not Control" workflow - clarify requirements through multi-turn dialogue, reduce rework, and execute with appropriate permission levels. Use...