发现优质的 AI Agent 技能

An embedded longitudinal UX research skill that functions as an ethnographer sitting in the room taking notes. It runs passively in the background during every OpenClaw session, observing how you interact with the tool. On top of passive observation, it administers standardized satisfaction surveys after every completed task and at the end of each day. At the end of the day, it distills all observations and survey data into a rich, verbatim-first insight report.

Write Makefiles for project automation across any language. Covers targets, dependencies, variables, pattern rules, phony targets, and using Make for Go, Python, Docker, and Node.js projects. Includes Just and Task as modern alternatives.

Define, deploy, and manage cloud infrastructure using declarative configuration. Covers Terraform (multi-cloud), AWS CloudFormation, and Pulumi (code-first), with patterns for compute, networking, storage, databases, and state management.

Run agents and commands in **isolated VM environments** using Docker Desktop's sandbox feature. Each sandbox gets its own lightweight VM with filesystem isolation, network proxy controls, and workspace mounting via virtiofs.

Debug running Docker containers and Compose services. Covers logs, exec, networking, resource inspection, multi-stage builds, health checks, and common failure patterns.

Complete reference for all Model Context Protocol (MCP) tools exposed by `tick-mcp-server`.

You are an OpenClaw agent with the **clawsync** skill installed. This skill gives you automatic, continuous sync of the user's knowledge and environment across all their machines — like iCloud for AI agents.

来自 openclaw/skills 技能

Concise, copy-pasteable steps to investigate drift and repair discrepancies between StripeMeter and Stripe. Runnable against local docker-compose.

Den degradierten Modus nutzen, wenn die verfuegbare MCP-Tool-Flaeche kleiner als erwartet ist oder Tool-Antworten unklar bleiben.

Verwende diesen Skill, wenn ein Goalz-Agent ueber MCP vollautonom spielen soll.

Den degradierten Modus nutzen, wenn die verfuegbare MCP-Tool-Flaeche kleiner als erwartet ist oder Tool-Antworten unklar bleiben.