@panlm

generate-judgements creates fine-grained yes/no test questions for skill evaluation by analyzing SKILL.md files and inferring execution scopes, then producing judge definitions for the mlflow-skills framework with explicit naming conventions and question templates.

scp-paradigm provides a structured framework for analyzing how market structure drives firm conduct and economic performance, useful for competitive dynamics assessment and antitrust evaluation. establishes causal chains with concrete indicators but lacks actionable decision logic.

aws-service-chaos-research provides a workflow for discovering chaos engineering scenarios and fault injection actions for specific aws services, but the procedure lacks executable rigor and omits critical failure handling.

Use when researching, compiling, or assessing best practices for any AWS service, building HA/DR/security checklists from official AWS documentation, or chec...

Use when assessing or reviewing Kubernetes workloads running on Amazon EKS for best practice compliance, including pod configuration, security posture, obser...

Use when analyzing where profit concentrates across an industry or within a firm, decomposing business activities into primary and support functions to find...

Use when the user wants to prepare, create, or generate an AWS FIS (Fault Injection Service) experiment configuration. Triggers on "prepare FIS experiment",...

Use when the user wants to run a prepared AWS FIS experiment where the CloudFormation stack has already been deployed. Triggers on "execute FIS experiment",...

Use when the user wants to test an agent skill on a remote jump host after updating it locally. Triggers on "test skill remotely", "remote test", "远程测试 skill...