structural-search
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.
96
96%
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), differentiates itself from text-based search, and provides explicit trigger terms covering both natural language queries and tool-specific keywords. It follows third-person voice and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | 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. | 3 / 3 |
Completeness | Clearly answers both what (search code by AST structure, find semantic patterns) and when (explicit 'Triggers on:' clause with multiple natural language triggers). The trigger guidance is explicit and comprehensive. | 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. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly distinguished from generic code search or text-based grep by emphasizing AST/structural search, semantic patterns, and specific tool names (ast-grep, sg). Unlikely to conflict with text search or other code tools. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
92%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, well-structured skill that provides highly actionable ast-grep commands organized into clear sections. The pattern syntax table, top 10 patterns, and quick reference are all concise and immediately useful. The main weakness is that the referenced bundle files (references/*.md, assets/*.yaml) are not provided, making the progressive disclosure structure unverifiable.
Suggestions
Provide the referenced bundle files (js-ts-patterns.md, python-patterns.md, etc.) or remove the references if they don't exist to avoid broken navigation.
| 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 commands. | 3 / 3 |
Actionability | Every pattern is a concrete, copy-paste-ready command. The top 10 patterns section provides fully executable sg commands with real-world use cases, and the quick reference table covers all major flags. | 3 / 3 |
Workflow Clarity | For a search/refactor tool, the workflow is clear: find pattern → preview replacement → apply with --rewrite. The distinction between preview (-r) and apply (--rewrite) serves as an implicit validation checkpoint. This is a simple, single-purpose skill where the actions are unambiguous. | 3 / 3 |
Progressive Disclosure | The skill references six files under ./references/ and ./assets/ for advanced content, which is good structure. However, no bundle files are provided, so these references are unverifiable and potentially broken. The main content is well-organized with clear sections but the referenced files don't exist in the bundle. | 2 / 3 |
Total | 11 / 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.
- Repository
- NeverSight/skills_feed
- Commit
3ae408c
- Reviewed
Table of Contents
Is this your skill?
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.