全部能力

Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50%…

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding…

用于问题追踪器的 Agent 技能 - 使用 $agent-issue-tracker 调用

Diagnose and improve humor using systems thinking. Use when jokes fall flat, when humor feels forced, when punchlines don't land, or when you want to…

性能监控代理技能 - 使用 $agent-performance-monitor 调用

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance…

将 Agentica SDK 与 Claude Code CLI 代理集成的指南

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want…

Set up comprehensive infrastructure monitoring with Prometheus, Grafana, and alerting systems for metrics, health checks, and performance tracking.

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task…

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6×…

Agentica server + Claude proxy 设置 - 架构、启动顺序、调试

用于 hierarchical-coordinator 的 Agent 技能 - 使用 $agent-hierarchical-coordinator 调用

Dump all Hyvä CMS components from active modules. This skill should be used when the user wants to list all CMS components, view available components, debug…

使用 Agentica SDK 构建 Python 智能体 —— @agentic 装饰器、spawn()、持久化、MCP 集成

Use this skill for reinforcement learning tasks including training RL agents (PPO, SAC, DQN, TD3, DDPG, A2C, etc.), creating custom Gym environments,…

性能基准测试代理技能 - 使用 $agent-performance-benchmarker 调用

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with…

NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII…

用于 quorum-manager 的 Agent 技能 - 使用 $agent-quorum-manager 调用