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

82%

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

The canonical home for this skill is gitnexus-guide in abhigyanpatwari/GitNexus

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 strong reference skill body: actionable tool guidance with exact parameters, a clear validated entry workflow with staleness checkpoints, and clean routing to sibling skills. The main improvement opportunities are adding example invocations for the remaining half of the tools and moving or trimming the inline staleness deep-dive.

DimensionReasoningScore

Conciseness

Dense, table-driven, and almost entirely GitNexus-specific (parameters, defaults, bounds) with no padding about concepts Claude already knows; minor rationale digressions in the staleness section (e.g., the design motivation citing issue #3291) could be trimmed, keeping it at the 'efficient with minor over-explanation' anchor.

4 / 5

Actionability

Copy-paste-ready invocations with exact options for the hot tools (query/context filter tables, trace examples, the list_repos pagination loop) plus explicit defaults and maxima; roughly half the Tools Reference entries (detect_changes, route_map, shape_check, api_impact, tool_map, check, group_*) remain one-line descriptions without example calls, preventing a 5.

4 / 5

Workflow Clarity

'Always Start Here' gives a clear numbered sequence with explicit validation checkpoints (read staleness.status and staleness.branch before using answers, re-analyze only for behind or diverged) and error-recovery feedback loops (ambiguous names return ranked candidates, hasMore: false terminates pagination, rename previews via dry_run/plan_token before applying).

5 / 5

Progressive Disclosure

The task-to-skill routing table clearly signals one-level-deep sibling skill files, sections are well organized, and hot-path guidance is up front; the ~45-line staleness deep-dive with three JSON example blocks is inline reference material that could live in a separate file, which keeps it at the 'good structure, minor organization gaps' anchor.

4 / 5

Total

17

/

20

Passed

Description

73%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 well-constructed trigger description with an explicit 'Use when' clause, concrete example questions, and a clearly bounded niche. Its main weakness is that the skill's own function (a quick reference for GitNexus MCP tools, resources, and schema) is implied by topic list rather than explicitly stated.

Suggestions

Lead with a one-clause statement of what the skill provides (e.g., "Quick reference for GitNexus MCP tools, resources, and the knowledge graph schema.") before the 'Use when' clause so both 'what' and 'when' are explicit.

Add a couple of natural synonyms users might say, such as "code graph" or "codebase map", alongside "knowledge graph" to broaden trigger coverage.

DimensionReasoningScore

Specificity

Names the domain and enumerates covered topics ("available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference") but never states what the skill itself does, matching the 'domain plus 1-2 concrete actions, not comprehensive' anchor rather than the 'several specific actions' anchor.

3 / 5

Completeness

Has an explicit 'Use when' clause with concrete example trigger phrases, satisfying the 'when' clearly; the 'what' is only implied by the topic list rather than stated as a skill action, so it sits at the 4 anchor rather than 5.

4 / 5

Trigger Term Quality

Good natural keywords ("GitNexus tools", "knowledge graph", "MCP resources", "graph schema") plus literal example questions users would say; a few natural synonyms for the graph concept (e.g., "code graph", "codebase map") are missing.

4 / 5

Distinctiveness Conflict Risk

"Use when the user asks about GitNexus itself" carves a clear niche (questions about the tool) that is distinct from task-oriented sibling skills (exploring, debugging, impact analysis, refactoring), with minimal conflict risk.

5 / 5

Total

16

/

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

abhigyanpatwari/GitNexus

Path

.claude/skills/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.