Education · Prompt engineering

Universal quality bar and final audit rubric for any agent system prompt.

mastra-ai/mastra

This skill should be used when a learner is working through Module 1 ("Build an Agent") of the Build-an-Agent workshop and wants help understanding the concepts, notebooks, or code — e.g.

brevdev/workshop-build-an-agent

This skill should be used when a learner is working through Module 1 ("Build an Agent") of the Build-an-Agent workshop and wants help understanding the concepts, notebooks, or code — e.g.

brevdev/workshop-build-an-agent

Configures and runs LLM evaluation using Promptfoo framework.

daymade/claude-code-skills

Calibrate a reviewer persona with few-shot rubric examples so skepticism stays consistent and doesn't drift lenient over long runs.

Archive228/loopkit

Prompt engineering frameworks for building, testing, versioning, and evaluating prompts: chain-of-thought, few-shot, regression testing, and rubrics.

borghei/Claude-Skills

LLM prompt engineering: analyzes failure modes, generates variants (direct, few-shot, CoT), designs rubrics, produces test suites.

Mathews-Tom/armory

This skill should be used when the user asks about "hospital margins", "cost reports", "HCRIS", "payer mix", "occupancy", "uncompensated care", "hospital capex capacity", "will hospitals buy", or…

hh-health-AI/healthcare-equity