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.

4.00x

Quality

90%

Does it follow best practices?

Impact

96%

4.00x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

80%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly concise and fully actionable with copy-paste ast-grep commands, but workflow clarity is capped because the batch '--rewrite' refactor path lacks an explicit validate-before-apply checkpoint, and progressive disclosure is weakened by references to bundle files that do not exist.

Suggestions

Add an explicit validation checkpoint to the refactoring workflow: after the preview (#8), instruct to review the diff and only run '--rewrite' (#9) once the preview is confirmed correct, forming a validate-then-apply feedback loop.

Create the referenced bundle files (references/js-ts-patterns.md, python-patterns.md, go-rust-patterns.md, security-patterns.md, advanced-usage.md, and assets/rule-template.yaml) so the 'Additional Resources' links resolve, or remove the links.

Dimension	Reasoning	Score
Conciseness	The body is lean tables of patterns and commands with no concept padding ('Pattern Syntax', 'Top 10 Essential Patterns', 'Quick Reference'); it assumes Claude knows AST concepts and every token earns its place. Not a 4 because there is no noticeable over-explanation to trim.	5 / 5
Actionability	Quotes like 'sg -p \"console.log($_)\"', 'sg -p \"var $NAME = $_\" -r \"const $NAME = $_\" --rewrite' are copy-paste ready executable commands covering the common search and refactor cases. Not a 4 because the examples are fully executable and span the common cases.	5 / 5
Workflow Clarity	Item #9 'Apply refactoring' with '--rewrite' is a batch/destructive operation and #8 'Preview refactoring' exists but there is no explicit validation checkpoint (e.g. review preview then apply only when correct), so per the rubric the destructive/batch cap of 3 applies. Not a 4 because the missing explicit validate-then-apply feedback loop triggers the cap; not a 2 because a rough preview/apply sequence is present.	3 / 5
Progressive Disclosure	The body signals one-level-deep references ('./references/js-ts-patterns.md' ... './assets/rule-template.yaml') under 'Additional Resources', but those bundle files do not exist in references/ or assets/, so the navigation does not resolve. Not a 4 because the referenced files are missing, which undermines clear navigation; not a 2 because the in-body structure itself is well organized with clearly signaled reference paths.	3 / 5
	Total	16 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is strong across all dimensions: it states concrete capabilities, includes a comprehensive explicit 'Triggers on' clause, and occupies a distinct niche. It fully answers both what and when with natural user phrasings.

Dimension	Reasoning	Score
Specificity	Quotes 'Search code by AST structure using ast-grep' and 'Find semantic patterns like function calls, imports, class definitions instead of text patterns' list multiple concrete actions and example pattern types; coverage is comprehensive. Not a 4 because the named concrete targets (function calls, imports, class definitions) are several and specific, not minor gaps.	5 / 5
Completeness	Quotes give a clear 'what' ('Search code by AST structure using ast-grep') and an explicit 'when' via the 'Triggers on:' clause with concrete trigger phrases. Not a 4 because 'when' is fully explicit rather than weakly specified.	5 / 5
Trigger Term Quality	Quotes 'Triggers on: find all calls to X, search for pattern, refactor usages, find where function is used, structural search, ast-grep, sg' cover natural phrasings plus synonyms and tool aliases. Not a 4 because synonyms (ast-grep, sg) and multiple natural user phrasings are all present, matching the comprehensive anchor.	5 / 5
Distinctiveness Conflict Risk	The AST/ast-grep niche with distinct tool-specific triggers ('ast-grep', 'sg', 'structural search') has minimal conflict risk with other skills. Not a 4 because the niche is clear and triggers are tool-specific, not just 'mostly distinct'.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: NeverSight/skills_feed
Path: data/skills-md/0xdarkmatter/claude-mods/structural-search/SKILL.md
Commit: 2f57aec

Reviewed: about 21 hours ago

Table of Contents

Discovery Implementation Validation

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.