Total 50,903 skills, AI & Machine Learning has 8525 skills
Showing 12 of 8525 skills
AI 개발/활용 도구 생태계(LangChain, LangGraph, CrewAI, 코딩 에이전트 등)를 비교하고 목적에 맞게 선택하는 모듈.
Migrate hardcoded prompts to Langfuse for version control and deployment-free iteration. Use when user wants to externalize prompts, move prompts to Langfuse, or set up prompt management.
Deploy and manage live trading agents on Hyperliquid. ⚠️ HIGH RISK - REAL CAPITAL AT STAKE ⚠️ Provides deployment_create (launch agent, $0.50), deployment_list (monitor), deployment_start/stop (control), and account tools (credit management). Supports EOA (1 deployment max) and Hyperliquid Vault (200+ USDC required, unlimited deployments). CRITICAL: NEVER deploy without thorough backtesting (6+ months, Sharpe >1.0, drawdown <20%). Start small, monitor daily, define exit criteria before deploying.
Execute complex tasks with intelligent workflow management and cross-session persistence. Use when managing large projects, tracking progress across sessions, or orchestrating multi-phase work.
Real-time monitoring and detection of adversarial attacks and model drift in production
Create narrative lore entries that transform technical work into mythological stories. Use when generating agent memory, documenting changes as narrative, or building persistent knowledge through storytelling.
Universal environment variable loader for AI agent environments. Loads secrets and config from Claude.ai, Claude Code, OpenAI Codex, Jules, and standard .env files.
Manage git-backed memory repos. Load this skill when working with git-backed agent memory, setting up remote memory repos, resolving sync conflicts, or managing memory via git workflows.
Orchestrate in-session Task tool teams for parallel work. Fan-out research, implementation, review, and documentation across subagents. Use when: parallel tasks, fan-out, subagent team, Task tool, in-session agents.
Control and manage the OpenClaw AI Assistant. Used to send messages to OpenClaw, check status, manage configurations, and install skills. Use this skill when you want to interact with or manage OpenClaw.
Template skill for repository authors; excluded from public publishing.
TDD-style testing methodology for skills using fresh subagent instances to prevent priming bias and validate skill effectiveness. Use when validating skill improvements, testing skill effectiveness, preventing priming bias, measuring skill impact on behavior. Do not use when implementing skills (use skill-authoring instead), creating hooks (use hook-authoring instead).