CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 lean, highly actionable reference body: no token waste, concrete call syntax for the complex tools, and an explicit entry workflow with a staleness validation checkpoint. The two minor weaknesses are the lack of call signatures for most tools in the reference table and extended specs inlined where reference files could keep the overview leaner.

Suggestions

Add minimal call signatures or example arguments to the Tools Reference table entries (e.g., for impact, context, query, detect_changes, route_map) so users can invoke tools that lack a dedicated subsection.

Move the extended pagination and trace/pdg_query specifications into a references/ file (e.g., references/tools.md) and keep one-line summaries with pointers in SKILL.md.

DimensionReasoningScore

Conciseness

The body is dense, purely GitNexus-specific operational detail — defaults, max bounds, pagination semantics, error statuses, caveats — with zero padding or explanation of concepts Claude already knows. Every section earns its tokens.

5 / 5

Actionability

Concrete, copy-paste-ready call syntax with real example arguments for the tricky tools (trace, pdg_query, explain) plus a runnable Cypher snippet and CLI command. Minor gap: roughly 11 of the 17 tools in the Tools Reference table get only a one-line "what it gives you" description without call signatures or example arguments.

4 / 5

Workflow Clarity

The "Always Start Here" section gives a numbered 3-step sequence with an explicit validation checkpoint (index-freshness check via the context resource) and a concrete remediation command when stale. Tool sections additionally document error statuses and recovery behavior (ambiguous names return ranked candidates; trace returns a status enum).

5 / 5

Progressive Disclosure

Well-organized sections with clearly signaled, one-level-deep pointers to external material (MCP resources like `gitnexus://repo/{name}/schema` and sibling skills like "See the `gitnexus-pdg-query` skill"). At ~133 lines, however, extended inline specs (pagination details, trace cross-repo behavior) could live in reference files to keep SKILL.md a leaner overview — a minor organization gap.

4 / 5

Total

18

/

20

Passed

Description

78%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 description with an explicit 'Use when' clause, concrete trigger examples, and a distinctive named-domain scope. Its main weakness is that the 'what' is conveyed only as a topic enumeration rather than an explicit capability statement, and a few natural synonyms are absent.

Suggestions

Open with a brief capability statement (e.g., "Quick reference for GitNexus MCP tools, resources, and graph schema") before the 'Use when' clause to make the 'what' fully explicit.

Add one or two natural trigger synonyms users might say, such as "code graph" or "code intelligence", to widen trigger coverage.

DimensionReasoningScore

Specificity

The description enumerates several concrete coverage areas — "available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference" — going well beyond naming the domain, but has minor gaps (CLI commands, taint/PDG layers) that keep it from comprehensive 5.

4 / 5

Completeness

The 'when' is explicit and trigger-phrased ("Use when the user asks about GitNexus itself — ..."), and the 'what' is present as an enumeration of covered areas, but it lacks a capability statement (e.g., "Quick reference for...") that would make the 'what' fully explicit for a 5.

4 / 5

Trigger Term Quality

Includes natural terms users would say ("tools", "knowledge graph", "MCP resources", "graph schema") plus literal example phrases ("What GitNexus tools are available?", "How do I use GitNexus?"). A few natural synonyms such as "code graph", "impact analysis", or "code intelligence" are missing.

4 / 5

Distinctiveness Conflict Risk

"GitNexus" is a distinctive product name and the scope is explicitly narrowed to questions about GitNexus itself, clearly distinguishing it from the task-oriented sibling skills (exploring, debugging, refactoring). Minimal conflict risk.

5 / 5

Total

17

/

20

Passed

Validation

100%

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

tslateman/shipyard

Path

.claude/skills/gitnexus/gitnexus-guide/SKILL.md

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.