sr-agent-skill-authoring

Standardize AI agent skills by applying strict frontmatter validation and structural templates to enforce predictable documentation patterns and completion criteria. This ensures all in-repo skills follow a high-quality structure that agents can reliably execute.

YAML frontmatter validation for agent workflows is the process of checking skill files against specific schemas and character limits to ensure optimal agent performance and context management. It enforces predictable documentation patterns required for reliable execution.

Validate frontmatter and content length by using a validation framework that applies the exact constraints and logic used by the SR Agent. This checks YAML schemas and character limits to ensure documentation is properly formatted and token-efficient.

Yes, strict frontmatter validation prevents quality drift by enforcing standardized templates and specific schemas across all in-repo AI agent skills. This addresses inconsistency issues and ensures capabilities maintain predictable, high-quality documentation structures.

The character limits for optimizing agent skill descriptions are enforced through specific YAML frontmatter schemas to ensure token efficiency and optimal context management. Adhering to these limits maintains predictable agent performance during execution.

Yes, you can use standardized templates to add new capabilities to an AI agent by following a peer-matched structure that includes overview, triggers, and verification steps. This ensures documentation is properly formatted with robust completion criteria.