The description names the domain ('agent-first operating principles') and some actions ('principle lookup, governance invariants'), but the actual capabilities are abstract — it describes what the skill contains rather than concrete actions it performs like 'list principles', 'explain a specific principle', or 'check compliance against principles'.

Clearly answers both 'what' (the 10 agent-first operating principles governing agent behavior) and 'when' (USE FOR clause with explicit triggers, plus a DO NOT USE clause for negative triggers). The explicit USE FOR / DO NOT USE structure serves as strong trigger guidance.

Good coverage of natural trigger terms: 'agent behavior rules', 'operating philosophy', 'principle lookup', 'governance invariants'. The DO NOT USE clause also helps prevent false matches with terms like 'Azure infrastructure', 'code generation', 'troubleshooting', 'diagram creation'.

Highly distinctive with a clear niche — operating principles and governance invariants for agents. The explicit DO NOT USE clause further reduces conflict risk by ruling out common adjacent domains like Azure infrastructure and code generation.

The content is reasonably well-structured but includes some redundancy. The 'How to Apply These Principles' section partially restates what the principles already convey. The 'Test' blocks add value but some principles could be tighter (e.g., Principle 9 largely restates Principle 2). Overall mostly efficient but not maximally lean.

Each principle includes a concrete 'Test' question which provides actionable verification criteria, and the 'How to Apply' section gives specific guidance for different roles. However, there are no executable code examples or commands — the guidance is directional rather than copy-paste ready. For a governance/philosophy skill this is acceptable but still lacks concrete artifacts like example ADR templates or validation commands.

The 'How to Apply' section provides sequenced guidance (read this first, then azure-defaults, etc.) and the progressive loading order is mentioned in Principle 8. However, there are no explicit validation checkpoints or feedback loops for applying the principles. For a governance skill this is adequate but the workflow for principle enforcement is implicit rather than explicit.

The skill practices what it preaches — it serves as an overview with clear pointers to deeper sources (azure-defaults skill, azure-artifacts templates, AGENTS.md, scripts/validate-artifacts.mjs). References are one level deep and well-signaled. The content is appropriately scoped as a principles overview without inlining detailed implementation guidance.