ast-grep

Write and debug ast-grep rules for structural code search and rewrite. Use when tasks require AST-aware matching (not plain text), such as finding specific syntax shapes, relational patterns (inside/has), composite logic (all/any/not), or precise code refactors across a codebase.

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%Weight 40%Scale 1-3

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

A well-structured, lean skill body with executable examples, a clear validated workflow, and clean progressive disclosure to two real reference files. No significant weaknesses to address.

Dimension	Reasoning	Score
Conciseness	The body is lean: short bullets, minimal prose, and no explanation of concepts Claude already knows (e.g. what an AST is), with every section earning its place.	3 / 3
Actionability	It provides copy-paste-ready commands ("sg run --pattern 'console.log($ARG)' --lang javascript src", "sg scan --rule rule.yml src") and a complete, executable YAML rule example.	3 / 3
Workflow Clarity	Steps 1-4 are clearly sequenced with a validation checkpoint ("Test on a tiny sample first") and a No-Match Triage feedback loop (run --json=compact, refine on [], fix parser errors first).	3 / 3
Progressive Disclosure	The body is an overview with well-signaled one-level-deep references to rule_reference.md and windows.md (both verified to exist), and explicitly directs loading only the needed reference.	3 / 3
	Total	12 / 12 Passed

Description

100%Weight 40%Scale 1-3

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

A strong, specific description with an explicit trigger clause and a clear, distinct niche. It would not be improved by adding fluff, and the only minor weakness is the slightly jargon-heavy parenthetical operator lists.

Dimension	Reasoning	Score
Specificity	"Write and debug ast-grep rules for structural code search and rewrite" lists multiple concrete actions (write, debug, search, rewrite) tied to a specific tool, matching the 'multiple specific concrete actions' anchor.	3 / 3
Completeness	It states what ("Write and debug ast-grep rules...") and an explicit "Use when tasks require AST-aware matching... such as finding specific syntax shapes...", clearly answering both what and when.	3 / 3
Trigger Term Quality	Natural developer-facing terms like "structural code search and rewrite", "precise code refactors", and "syntax shapes" give good coverage, though the parenthetical operator lists (inside/has, all/any/not) lean slightly technical.	3 / 3
Distinctiveness Conflict Risk	The ast-grep niche is clear and the "not plain text" contrast explicitly separates it from grep/ripgrep, making conflict with other skills unlikely.	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: BiFangKNT/mtga
Path: .codex/skills/ast-grep/SKILL.md
Commit: 72669fb

Reviewed: 20 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.