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.
Install with Tessl CLI
npx tessl i github:NeverSight/skills_feed --skill structural-search100
Does it follow best practices?
Validation for skill structure
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 its purpose (AST-based code search), provides concrete examples of what it finds (function calls, imports, class definitions), and includes explicit trigger terms that users would naturally use. The description effectively differentiates itself from text-based search tools.
| 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. | 3 / 3 |
Completeness | Clearly answers both what ('Search code by AST structure', 'Find semantic patterns') AND when ('Triggers on:' followed by explicit trigger phrases). The 'Triggers on:' clause serves as an explicit 'Use when' equivalent. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'find all calls to X', 'search for pattern', 'refactor usages', 'find where function is used', 'structural search', 'ast-grep', 'sg'. These are realistic user phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche distinguishing AST/structural search from text-based grep or regex search. Terms like 'AST structure', 'semantic patterns', 'structural search' create a distinct identity unlikely to conflict with general code 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 exemplary skill file that maximizes information density while maintaining clarity. It provides immediately actionable patterns for the most common use cases, a comprehensive quick reference table, and well-organized pointers to additional resources. The content respects Claude's intelligence by avoiding explanations of basic concepts while providing the specific syntax and examples needed for effective use.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely lean and efficient. Uses tables for quick reference, provides executable commands without unnecessary explanation. No verbose descriptions of what AST or ast-grep is—assumes Claude's competence. | 3 / 3 |
Actionability | Provides 10 copy-paste ready command examples covering common use cases. Quick reference table gives exact command syntax for all major operations. Every example is executable. | 3 / 3 |
Workflow Clarity | For a search tool skill, the workflow is appropriately simple. The refactoring section clearly shows preview-then-apply pattern (preview with -r, apply with --rewrite), which is the key validation checkpoint for this tool. | 3 / 3 |
Progressive Disclosure | Excellent structure with clear sections (Pattern Syntax, Essential Patterns, Quick Reference, When to Use). References to additional language-specific patterns and advanced usage are clearly signaled and one level deep. | 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.
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.