CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

79

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

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, action-oriented skill body: executable commands throughout, a preview-then-apply checkpoint for destructive rewrites, and clean sectioned organization with no concept padding. It meets the top anchor on all four content dimensions.

DimensionReasoningScore

Conciseness

The body is dense with executable commands and reference tables and explains no concepts Claude already knows; every section (commands, pattern syntax, node kinds, escaping) earns its tokens, matching the lean-and-efficient anchor.

3 / 3

Actionability

Every example is a complete, copy-paste-ready command (e.g. `mise exec -- ast-grep run -p '$X.unwrap()' -l rust .`) plus concrete YAML rules, matching the fully-executable anchor.

3 / 3

Workflow Clarity

The destructive rewrite workflow is sequenced with an explicit checkpoint — "always preview first, then apply with -U" — providing the validate-then-apply feedback loop the rubric requires for batch operations.

3 / 3

Progressive Disclosure

A single self-contained file with clearly organized sections (Commands, Pattern syntax, YAML rule structure, Key Rust node kinds, Shell escaping) and no nested references, matching the well-organized-sections anchor for reference-free skills.

3 / 3

Total

12

/

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.

A concise, third-person description that states concrete capabilities, gives an explicit use-when trigger, and actively distinguishes itself from Grep/Edit. It satisfies every dimension at the top anchor with no verbosity or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "AST-based code search and rewrite", "structural matching", "multi-file batch rewrites", and "context-aware queries" — matching the score-3 anchor of several specific concrete actions.

3 / 3

Completeness

Explicitly states what it does (AST-based search/rewrite) and when to use it ("Use instead of Grep/Edit when a change spans many sites or must respect code structure"), satisfying the both what-AND-when-with-explicit-triggers anchor.

3 / 3

Trigger Term Quality

Covers natural terms a user would say ("code search", "rewrite", "multi-file batch rewrites", "rename") with good variation, matching the score-3 anchor for coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

Carves a clear niche and explicitly disambiguates from peers ("Not for a single-file or single-symbol rename — use Edit for that"), matching the clear-niche-low-conflict anchor.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
gitlabhq/orbit-knowledge-graph
Reviewed

Table of Contents

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.