Skills for Claude Code

A

Arize Evaluator

github

Streamline LLM evaluation workflows on Arize.

Troubleshoot

microsoft

Analyze logs to understand chat agent behavior.

A

Agentic Evaluation

github

Enhance AI outputs through iterative evaluation and refinement.

NeMo Evaluator SDK

davila7

Enterprise-grade LLM benchmarking across 100+ tasks.

LLM Evaluation Harness

davila7

Benchmark LLMs across 60+ academic tasks.

Advanced Evaluation

muratcankoylan

Evaluate LLM outputs with precision and reliability.

Retune a Corpus

everyinc

Optimize your skill corpus for improved model performance.

Evals

danielmiessler

An assertion-first framework for AI evaluations.

Fine-Tuning Method Selection

wshobson

Streamline your fine-tuning decisions effectively.

E

Eval Harness First

wshobson

Essential setup for fine-tuning AI models.

Checkpoint Promotion

wshobson

Ensure your AI model meets quality standards before deployment.

O

Obliteratus

nousresearch

Remove refusal behaviors from LLMs without retraining.

Phoenix Observability

davila7

Open-source observability for LLM applications.

Agent Evaluation

muratcankoylan

Systematically assess agent performance and quality.

A

AI Workflow Diagnostics

github

Systematically audit your AI workflows for quality and reliability.

Context Degradation Patterns

sickn33

Understand and mitigate context degradation in language models.

Agent Evaluation

sickn33

Benchmark and assess LLM agents effectively.

Advanced Evaluation

sickn33

Evaluate LLM outputs reliably using advanced techniques.

LLM Evaluation

wshobson

Systematic evaluation strategies for LLM performance.

Creating Online Evaluations

posthog

Automate scoring of AI responses based on real failures.

LLM Evaluation

davila7

Evaluate LLM performance with systematic strategies.

LLM Eval Harness

daymade

Evaluate LLM endpoints for reliability and performance.

GAIA Submission

ruvnet

Streamline your GAIA benchmark submission process.

Harness Learn

ruvnet

Optimize harness genomes with automated learning cycles.