graph-query

Query the code graph database to understand component relationships, dependencies, and change impact. Use when the user asks to "find callers", "check dependencies", "what uses this", "show relationships", "find serializers", or when reading code and needing to understand what depends on a component before modifications.

Quality

83%

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

71%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 well-structured, actionable reference for graph-query commands with a clear core workflow and good single-file organization. Trimming the rationale and marketing sections would lift conciseness toward the top anchor.

Suggestions

Remove or compress the "Why Query Before Modifying" section; Claude already understands the risks of changing signatures without checking callers, so the commands and the "Read -> Query -> Proceed" flow speak for themselves.

Cut the "Full AI Maestro Experience" marketing paragraph, or reduce it to a single inline link, since it does not help execute the skill and adds tokens unrelated to graph querying.

Add a brief note on expected command output or what to do when the graph is not yet indexed (e.g., run graph-index-delta.sh first), which would close the workflow-clarity and actionability gaps.

Dimension	Reasoning	Score
Conciseness	Command tables and usage examples are efficient, but the "Why Query Before Modifying" section explains consequences Claude already knows and the "Full AI Maestro Experience" section is marketing padding, making it mostly efficient with some unnecessary explanation.	3 / 5
Actionability	Provides concrete, executable shell commands in tables and copy-paste-ready usage examples covering the common cases, with a minor gap being the absence of expected output samples.	4 / 5
Workflow Clarity	Core Behavior gives a clear "Read file -> Query graph -> Then proceed" sequence and the skill is read-only so the destructive-validation cap does not apply, but failure-handling and index-status checkpoints are only implicit.	4 / 5
Progressive Disclosure	No bundle files exist and the body is self-contained with well-organized section headers and no nested references, satisfying the simple-skill exception for a clean, navigable single-file structure.	5 / 5
	Total	16 / 20 Passed

Description

95%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, third-person description that crisply states the skill's purpose and gives explicit, natural trigger phrases. Its only weakness is mild abstraction in the capability verbs, which keeps specificity just below the top anchor.

Dimension	Reasoning	Score
Specificity	Names the code-graph domain and several concrete capabilities ("component relationships, dependencies, and change impact"), but frames them through the abstract verb "understand" rather than discrete actions, leaving minor gaps versus a fully comprehensive action list.	4 / 5
Completeness	Clearly states what the skill does ("Query the code graph database to understand component relationships, dependencies, and change impact") and explicitly answers when with concrete "Use when..." trigger phrases, matching the top anchor on both dimensions.	5 / 5
Trigger Term Quality	Explicitly enumerates natural phrases users actually say ("find callers", "check dependencies", "what uses this", "show relationships", "find serializers") plus a behavioral trigger ("reading code and needing to understand what depends on a component"), giving comprehensive natural-term coverage.	5 / 5
Distinctiveness Conflict Risk	"code graph database" is a distinct niche with specialized triggers (find callers/serializers/associations) that are unlikely to fire for unrelated skills, giving minimal conflict risk.	5 / 5
	Total	19 / 20 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: davila7/claude-code-templates
Path: cli-tool/components/skills/ai-maestro/graph-query/SKILL.md
Commit: d4f034a

Reviewed: 5 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.