8803 个 Skills
Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFa...
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace,...
This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.
Build evaluation frameworks for agent systems. Use when testing agent performance, validating context engineering choices, or measuring improvements over time.
Defines evaluation criteria and scoring methodologies for deliverable assessment
Independent assessment without debate context — adversarial loop prevents gaming
Evaluator-Optimizer pattern knowledge for automatic iteration cycles.Implements Anthropic's agent ar
Add new events to Bob The Skull's event-driven architecture. Use when creating new events, event pub
Design and implement event stores for event-sourced systems. Use when building event sourcing infrastructure, choosing event store technologies, or implementing event persistence patterns.
AWS EventBridge serverless event bus for event-driven architectures. Use when creating rules, configuring event patterns, setting up scheduled events, integrating with SaaS, or building cross-account event routing.
自我進化 Agent - 已遷移至原子化架構
Self-Evolving Development Loop - Dynamic skill generation with learning and evolution