gitnexus-guide

Use when the user asks about GitNexus itself — available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference. Examples: "What GitNexus tools are available?", "How do I use GitNexus?"

Quality

86%

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

86%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 compact, well-organized reference hub that respects token budget and routes clearly to sibling skills and concrete tools/resources. The main gap is that tool entries describe outputs rather than executable call syntax.

Suggestions

Add a one-line example invocation for at least the most-used tools (e.g., `query` and `cypher`) with expected arguments so guidance is copy-paste ready.

Optionally note required arguments or return shape for `impact`/`detect_changes` so Claude can call them without trial and error.

Dimension	Reasoning	Score
Conciseness	Lean table-driven reference with minimal prose and no explanation of concepts Claude already knows; every section (tools, resources, schema) earns its tokens.	5 / 5
Actionability	Provides concrete tool names, resource URIs, an executable Cypher snippet, and a runnable CLI command, but the tools table describes outputs rather than full call syntax, leaving minor gaps.	4 / 5
Workflow Clarity	The "Always Start Here" section gives a clear 3-step sequence with an explicit staleness checkpoint and a recovery command, but the dominant "workflow" is skill-dispatch routing rather than a guarded multi-step process.	4 / 5
Progressive Disclosure	Under 50 lines with well-organized sections and one-level-deep routing to sibling skill files; the simple-skill exception applies since no external bundle references are needed.	5 / 5
	Total	18 / 20 Passed

Description

87%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, well-scoped description that clearly answers what the skill covers and when to invoke it, with natural example trigger phrases and a distinct GitNexus-specific niche. The only weakness is that the listed capabilities are topical categories rather than concrete verbs.

Suggestions

Lead with concrete verbs (e.g., "Look up GitNexus tools, query the knowledge graph, inspect the graph schema") so the capability reads as actions rather than topics.

Add a couple of common synonym triggers (e.g., "code graph", "symbol graph") to broaden natural phrasing coverage.

Dimension	Reasoning	Score
Specificity	Enumerates several concrete facets ("available tools", "how to query the knowledge graph", "MCP resources", "graph schema", "workflow reference") rather than vague language, though these are capability categories rather than concrete actions, keeping it just below a 5.	4 / 5
Completeness	Explicitly states both what the skill covers (the enumerated GitNexus facets) and when to use it via a clear "Use when..." clause with concrete example triggers, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ("What GitNexus tools are available?", "How do I use GitNexus?") plus domain terms like "knowledge graph" and "graph schema", with only minor synonym/extension gaps.	4 / 5
Distinctiveness Conflict Risk	Scoped narrowly to "GitNexus itself" with product-specific triggers, giving it a clear niche and minimal risk of firing for unrelated skills.	5 / 5
	Total	18 / 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: mindfold-ai/Trellis
Path: .claude/skills/gitnexus/gitnexus-guide/SKILL.md
Commit: 64e6636

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.