ast-grep

AST-based code search and rewrite via tree-sitter patterns. Use instead of Grep/Edit when a change spans many sites or must respect code structure: structural matching, multi-file batch rewrites, or context-aware queries (e.g. "unwrap inside impl blocks"). Not for a single-file or single-symbol rename — use Edit for that.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

82%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.

A tight, highly actionable reference with copy-paste commands and a genuine preview-then-apply validation checkpoint for batch rewrites. Structure is clear; the main gap is that reference tables could live in bundle files and the rewrite workflow could spell out error recovery.

Suggestions

Trim the "since ast-grep is installed via mise" justification to a bare imperative ("Run all commands through `mise exec --`.") to tighten conciseness.

Add a one-line error-recovery note to the rewrite workflow, e.g. "If the preview does not match the intended sites, refine the pattern and re-preview before applying."

Consider moving the "Key Rust node kinds" table and full YAML rule catalog into a references/ file, keeping SKILL.md as a concise overview with a one-level-deep link.

Dimension	Reasoning	Score
Conciseness	Lean and dense with non-obvious reference material (Rust node kinds, selector disambiguation, shell escaping), but the "since ast-grep is installed via mise" clause is mild over-explanation that could be trimmed.	4 / 5
Actionability	Fully executable, copy-paste-ready `mise exec -- ast-grep ...` commands covering search, rewrite, scan, JSON, and debug cases, plus complete YAML rule examples.	5 / 5
Workflow Clarity	The rewrite section gives an explicit validation checkpoint ("always preview first, then apply with -U") avoiding the batch-operation cap, but lacks an explicit error-recovery loop if the preview is wrong.	4 / 5
Progressive Disclosure	Well-organized into clearly headed sections (Commands, Pattern syntax, YAML rules, Rust kinds, Shell escaping) with easy navigation, though reference-like material (node kinds, full YAML catalog) is inline rather than split to bundle files.	4 / 5
	Total	17 / 20 Passed

Description

92%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.

A strong, concrete description that clearly states capabilities and gives explicit use/avoid triggers with a sharp boundary against Grep/Edit. Only minor gap is a few missing natural synonyms like "refactor".

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "AST-based code search and rewrite", "structural matching", "multi-file batch rewrites", "context-aware queries" — giving comprehensive coverage of capabilities.	5 / 5
Completeness	Explicitly answers both what ("AST-based code search and rewrite via tree-sitter patterns") and when ("Use instead of Grep/Edit when a change spans many sites..." plus "Not for a single-file or single-symbol rename").	5 / 5
Trigger Term Quality	Good natural keyword coverage ("search", "rewrite", "Grep", "Edit", "rename") that users would say, but misses common synonyms like "refactor" for batch rewrites.	4 / 5
Distinctiveness Conflict Risk	Clear niche (AST-based structural matching) with explicit contrast against Grep/Edit and a "Not for... use Edit for that" boundary, yielding minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: gitlabhq/orbit-knowledge-graph
Path: .claude/skills/ast-grep/SKILL.md
Commit: a2b60b1

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.