The content is lean and efficient, using tables and code examples without unnecessary explanation. It doesn't explain what ASTs are or how ast-grep works internally—it jumps straight to actionable patterns and commands.

Every pattern is a copy-paste ready command with concrete examples across multiple languages. The quick reference table provides exact flags and syntax for all common operations.

For a search/refactor tool, the workflow is clear: find patterns, preview replacements with `-r`, then apply with `--rewrite`. The separation of preview vs. apply is an implicit but clear validation checkpoint appropriate for this tool's risk level.

The skill references six files under `./references/` and one asset, which is good structure, but no bundle files are provided so these references are unverifiable dead links. The main content itself is well-organized with clear sections, but the referenced files don't actually exist in the bundle.

Lists multiple concrete actions: search by AST structure, find semantic patterns like function calls, imports, class definitions, and contrasts with text patterns. This gives a clear picture of specific capabilities.

Clearly answers both what ('Search code by AST structure... Find semantic patterns like function calls, imports, class definitions') and when ('Triggers on: find all calls to X, search for pattern, refactor usages...'). The 'Triggers on:' clause serves as an explicit 'Use when' equivalent.

Excellent coverage of natural trigger terms: 'find all calls to X', 'search for pattern', 'refactor usages', 'find where function is used', 'structural search', 'ast-grep', 'sg'. These are phrases users would naturally say.

Clearly distinguished from generic code search or text-based grep by specifying AST/structural search, naming the specific tool (ast-grep/sg), and contrasting with text patterns. Unlikely to conflict with regular search or grep skills.