Search code by AST structure using ast-grep. Find semantic patterns like function calls, imports, class definitions instead of text patterns. Triggers on: find all calls to X, search for pattern, refactor usages, find where function is used, structural search, ast-grep, sg.
99
100%
Does it follow best practices?
Impact
96%
4.00xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly communicates what the skill does (AST-based structural code search), how it differs from alternatives (semantic patterns vs text patterns), and when to use it (with a comprehensive 'Triggers on' clause). The description is concise, uses third person voice, and includes both tool-specific terms (ast-grep, sg) and natural language triggers.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Search code by AST structure', 'Find semantic patterns like function calls, imports, class definitions'. Clearly distinguishes from text-based search by specifying structural/semantic pattern matching. | 3 / 3 |
Completeness | Clearly answers both 'what' (search code by AST structure, find semantic patterns like function calls, imports, class definitions) and 'when' (explicit 'Triggers on:' clause with multiple natural trigger phrases). | 3 / 3 |
Trigger Term Quality | 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 when needing this capability. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly distinguishes itself from generic code search or text-based grep by emphasizing AST/structural search, semantic patterns, and the specific tool ast-grep/sg. The distinction from text patterns is explicitly stated, reducing conflict with regular search skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill that is concise, highly actionable, and well-structured. It provides 10 essential copy-paste ready patterns covering the most common use cases, a comprehensive quick reference table, and clear pointers to additional resources for deeper exploration. The preview-then-apply workflow for refactoring is a nice safety touch.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables and code examples without unnecessary explanation. It assumes Claude knows what AST search is and jumps straight to syntax and patterns. | 3 / 3 |
Actionability | Every pattern is a copy-paste ready command with concrete examples across multiple languages. The quick reference table provides executable commands for all common tasks. | 3 / 3 |
Workflow Clarity | For this single-purpose search skill, the workflow is unambiguous: find patterns, optionally preview replacements, then apply. The preview-before-apply pattern (items #8 and #9) provides an implicit validation checkpoint for the destructive rewrite operation. | 3 / 3 |
Progressive Disclosure | The skill provides a concise overview with essential patterns inline, then clearly signals one-level-deep references to language-specific patterns, security patterns, and advanced usage in the Additional Resources section. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
16e7fa6
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.