ast-grep

AST-based code search and rewrite via tree-sitter patterns. Use instead of Grep/Edit for structural matching, batch rewrites, or context-aware queries (e.g. "unwrap inside impl blocks").

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

100%

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 skill body built from executable commands and tables, with a preview-first validation checkpoint for batch rewrites and clean section organization. It assumes Claude's competence and avoids concept re-explanation.

Dimension	Reasoning	Score
Conciseness	Lean body of executable commands and tables with no padding explaining AST/tree-sitter basics; assumes Claude's competence and every line earns its place.	3 / 3
Actionability	Fully executable, copy-paste-ready `mise exec -- ast-grep` commands with real flags and a concrete pattern-syntax table, matching the anchor for fully executable examples.	3 / 3
Workflow Clarity	The batch-rewrite workflow has an explicit validation checkpoint ("always preview first, then apply with -U") plus debug-query tools for error recovery, satisfying the feedback-loop requirement for batch operations.	3 / 3
Progressive Disclosure	Single-file skill with no bundle files but clearly organized into well-signaled sections (Commands, Pattern syntax, YAML rule structure, Key Rust node kinds, Shell escaping) for easy navigation.	3 / 3
	Total	12 / 12 Passed

Description

85%

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 specific, well-scoped description that clearly states capabilities and gives an explicit usage trigger differentiating it from Grep/Edit. Its only weakness is trigger-term naturalness: it relies on technical jargon rather than phrases users would naturally utter.

Suggestions

Add natural-language trigger phrases a user might actually say (e.g. "structural code search", "refactor all unwraps", "find code patterns across a codebase") alongside the technical terms.

Consider adding a concrete "Use when ..." clause naming recognizable scenarios (e.g. "Use when rewriting a pattern across many files or matching code by structure rather than text").

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "AST-based code search and rewrite", "structural matching, batch rewrites, or context-aware queries" — matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Answers both what ("AST-based code search and rewrite via tree-sitter patterns") and when via an explicit "Use instead of Grep/Edit for ..." trigger clause.	3 / 3
Trigger Term Quality	Has some relevant keywords ("structural matching", "batch rewrites") but leans on technical jargon ("AST-based", "tree-sitter patterns") a user would not naturally say, and misses common natural variations.	2 / 3
Distinctiveness Conflict Risk	Clear niche (structural AST matching) with an explicit "Use instead of Grep/Edit" differentiator, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 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
Commit: 00ca361

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.