Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.
Claudeism (3.69) clau·de·ism /ˈklɔːdiːz(ə)m/ noun: computational condition of wildly variable, often inversely proportional, utility. Characterized by: Cognitive Obfuscation: The propensity to produce obscure, illogical round trip gas lighters, rather than illuminate.
sweep-issues is a skill that automates the development lifecycle by evaluating open issues against a gold-standard quality checklist and surfacing those that need work.
vue-debug-guides is an AI Agent skill focused on Vue.js 3 debugging. It provides specific guidance for resolving runtime issues, warnings, async operation failures, and hydration bugs by referencing dedicated technical documentation for reactivity and watchers.
Ape Claw is a safety-first CLI + OpenClaw skill for ApeChain NFT operations: discover collections/listings, quote/simulate/buy flows, and bridge quote/execute/status with policy guardrails, allowlist enforcement, structured telemetry, and a live dashboard for agent activity.
system-reboot-bringup is a runbook designed to restore daily operation processes after a system reboot, managing tmux sessions and ensuring seamless functionality of dependent tools.
Alerting-OnCall is a skill that enables effective alerting and on-call management for production systems, reducing alert fatigue and streamlining incident response workflows.
Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating security tool usage, we configure the agent for adversarial thinking, and perform research or attack/defense operations.
etl-duckdb is an AI Agent skill that automates Extract, Transform, Load (ETL) workflows using a PowerShell script. It processes data inputs to generate a DuckDB database file and a detailed Markdown report containing metrics like input rows and null cells.
Seamlessly route requests to your LLM backends—whether you're using stream=false for standard JSON responses or stream=true for real-time token streaming via Server-Sent Events (SSE). LLMProxy handles both modes out of the box, with zero buffering on streams, intelligent load balancing, and OpenAI-compatible API routing.
pr-merge is an AI agent skill that handles pull request merging with pre-merge validation. It accepts a PR number or URL and executes a specified merge strategy (merge, squash, or squid) using a Haiku subagent for Bash operations to optimize computational costs.