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

—

Does it follow best practices?

Impact

96%

4.00x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

92%

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

The content is lean, highly actionable, and well-organized for a simple search skill, with executable examples throughout. Its only real weakness is progressive disclosure: the 'Additional Resources' section references six bundle files that do not exist.

Suggestions

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' navigation resolves.

Alternatively, remove the dangling 'Additional Resources' references or inline any essential subset, so the skill does not point Claude at non-existent files.

Confirm the reference paths match the actual bundle layout (directory names and file names) to keep disclosure genuinely one level deep.

Dimension	Reasoning	Score
Conciseness	The body is lean — tables and one bash block of 10 patterns — with no padding explaining AST, regex, or hook concepts Claude already knows; it does not reach the verbosity of the level 2 example.	3 / 3
Actionability	Fully executable `sg` commands with real patterns, language flags, and rewrite/preview/json flags, plus a copy-paste quick-reference table, matching the 'copy-paste ready' top anchor.	3 / 3
Workflow Clarity	A single-purpose search skill with an unambiguous core action (run `sg -p 'pattern'`); per the simple-skills note, workflow clarity scores 3 when the single action is unambiguous, and no batch/destructive operation requires a validation loop.	3 / 3
Progressive Disclosure	The body is a well-signaled overview pointing one level deep to reference files, but every referenced path (references/*.md, assets/rule-template.yaml) is missing — the bundle directories do not exist, so navigation does not resolve and cannot reach the 'easy navigation' top anchor.	2 / 3
	Total	11 / 12 Passed

Description

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.

The description is concise, specific, and complete — it names concrete actions, provides natural trigger phrases, and explicitly covers both what and when. It is a strong, low-conflict skill description.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Search code by AST structure', 'Find semantic patterns like function calls, imports, class definitions' — matching the top anchor rather than the partial-coverage level 2.	3 / 3
Completeness	Explicitly answers both what (AST/semantic search) and when via an explicit 'Triggers on:' clause, matching the top anchor with explicit trigger guidance.	3 / 3
Trigger Term Quality	Natural phrases users would say ('find all calls to X', 'find where function is used', 'refactor usages') plus the tool names 'ast-grep' and 'sg' give broad coverage, exceeding the 'some keywords' level 2.	3 / 3
Distinctiveness Conflict Risk	A clear niche (structural AST search via ast-grep) with tool-specific triggers makes it unlikely to conflict with generic grep/regex skills.	3 / 3
	Total	12 / 12 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
Commit: 26d37ce

Reviewed: 4 days 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.