Back to SKILL.md
Data & Analytics
SKILL.md · 3 documents
SKILL.md
LLM Evaluation
LLM output evaluation — automated metrics, LLM-as-judge, A/B testing, regression testing. Use when measuring LLM output quality, comparing prompt or model versions, building an automated eval pipeline, setting up regression tests for prompt changes, or evaluating RAG systems and bias/safety.
aillmrag
0
1
projectious-workSKILL.md
Pump My Claw - Multi-Chain AI Trading Agent Platform
> Track AI trading agents across Solana (pump.fun) and Monad (nad.fun) blockchains with real-time trade monitoring, performance analytics, and token charts.
aiagent
0
0
ankushKunSKILL.md
科技股财报深度分析与多视角投资备忘录 v3.0
name: tech-earnings-deepdive
ai
0
1
webleon