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

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 dense, highly actionable reference that correctly assumes Claude's competence and provides copy-ready tool invocations. Its main weakness is structural: detailed sections (staleness semantics, pagination, response filters) are inlined rather than split into one-level-deep reference files.

Suggestions

Move the inline staleness deep-dive (the three JSON examples and per-status semantics) and the list_repos pagination details into a references/ file (e.g. references/staleness.md, references/pagination.md), keeping a one-line 'read staleness.status before using the answer; re-analyze only for behind/diverged' rule in SKILL.md.

Condense the three near-identical staleness JSON examples into one canonical example plus a short per-status delta table, and remove the duplication between the 'Always Start Here' note and the staleness section.

Consider extracting the response-filter/response_sections surface (the 'Choose a focused response' subsection) into a reference file, leaving only the quick-decision table inline.

DimensionReasoningScore

Conciseness

Nearly every line is GitNexus-specific knowledge Claude cannot already know, presented in dense tables with no padding or basic-concept explanations. Minor tightening is possible — staleness advice is repeated between the "Always Start Here" note and the staleness section, and the three near-identical staleness JSON examples could be condensed to one plus deltas.

4 / 5

Actionability

Guidance is fully executable: exact tool calls with concrete parameter sets (`query: limit: 3, response_sections: [...]`, `pdg_query { mode: "controls", target: "..." }`, `trace { from: "validateUser", to: "executeQuery" }`), a runnable pagination loop with `nextOffset`, a Cypher example, and the terminal command `node .gitnexus/run.cjs analyze`.

5 / 5

Workflow Clarity

"Always Start Here" gives a numbered entry sequence with an explicit staleness validation checkpoint and a re-analyze feedback loop ("Re-analyze only for behind or diverged"). It falls short of anchor 5 because the process guidance is concentrated in a short intro while the bulk of the document is reference material without per-tool step sequences or checklists.

4 / 5

Progressive Disclosure

Headers, tables, and a one-level routing table to sibling skill files provide real structure, but no bundle files exist and roughly 120 lines of deep material — staleness response semantics, list_repos pagination details, and the full response-filter surface — are inlined in SKILL.md where they would fit better in dedicated reference files.

3 / 5

Total

16

/

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 trigger clause, natural example questions, and a distinct niche. The main gap is that the "what" is conveyed as a list of topics rather than concrete actions the skill performs.

DimensionReasoningScore

Specificity

The description enumerates several concrete coverage areas — "available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference" — which is specific and broad, though it lists topics rather than concrete actions, keeping it below the comprehensive anchor 5.

4 / 5

Completeness

The "when" is explicit with a clear "Use when…" clause and concrete trigger example quotes; the "what" is present as a topic enumeration rather than a capability statement ("quick reference" framing lives in the body, not the description), so it falls just short of anchor 5.

4 / 5

Trigger Term Quality

It includes natural phrases users would actually say ("What GitNexus tools are available?", "How do I use GitNexus?") plus domain terms like "knowledge graph" and "MCP resources", but misses a few natural variations such as "code graph" or "code navigation".

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche — questions about GitNexus itself — and is cleanly distinguished from the task-based sibling skills (exploring, debugging, impact analysis), minimizing 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

abhigyanpatwari/GitNexus

Path

gitnexus-claude-plugin/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.