CtrlK
BlogDocsLog inGet started
Tessl Logo

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?"

65

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/gitnexus-guide/SKILL.md

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body is a strong, highly actionable reference: exact tool-call shapes, parameter bounds, and real Cypher make it copy-paste ready, and the entry workflow carries an explicit staleness checkpoint. It is held back from the top band by verbosity in the staleness section (three overlapping JSONC examples) and inlined reference material that could be split out.

Suggestions

Collapse the three staleness JSONC examples (current/behind/diverged) into one compact table or a single annotated example to cut redundancy and raise conciseness.

Move the detailed pagination walkthrough and full staleness semantics into a separate reference file (e.g., `references/staleness.md`) and link to it, keeping SKILL.md as a lean overview.

Tighten or merge the duplicated staleness guidance between the "Always Start Here" callout and the "Inline staleness signal" subsection to avoid stating the same rule twice.

DimensionReasoningScore

Conciseness

The body is information-dense and largely assumes Claude's competence (tool tables, field shapes, status semantics), but the staleness section runs long with three near-redundant JSONC examples and extended prose explaining edge cases that could be tightened, putting it between the 3 and 4 anchors; the repetition of the same guidance across intro and the inline-staleness subsection pulls it toward 3.

3 / 5

Actionability

It provides concrete, executable guidance throughout — exact tool call shapes (e.g., `trace { from: "validateUser", to: "executeQuery" }`, `list_repos { offset: 50 }`), parameter defaults/maxes, real Cypher, and runnable CLI (`node .gitnexus/run.cjs analyze`) — covering common cases copy-paste ready, matching the fully-executable anchor.

5 / 5

Workflow Clarity

The "Always Start Here" section gives a clear numbered sequence with a staleness checkpoint (read `staleness.status` before using answers, re-analyze only for behind/diverged), but the document is reference-oriented rather than a single destructive/batch workflow, so validation checkpoints exist for the risky read path but are not as tightly looped as a validate->fix->retry cycle; this fits just above the 3 anchor but below the explicit-feedback-loop 5.

4 / 5

Progressive Disclosure

Structure is good with well-organized sections (Always Start Here, Skills, Tools, Resources, Graph Schema) and one-level-deep references to other skill files (e.g., `gitnexus-pdg-query` skill, `gitnexus://repo/{name}/schema`); however, no bundle files exist and several large reference blocks (full staleness JSONC examples, pagination walkthrough) are inlined where they could live in a separate reference, so it sits at 4 rather than 5.

4 / 5

Total

16

/

20

Passed

Description

81%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.

The description is well-formed: it gives explicit when-trigger guidance, concrete example prompts, and a product-specific niche that minimizes conflict risk. The main weakness is that capabilities are framed as topics/objects rather than discrete concrete actions, which limits specificity.

Suggestions

Reframe the capability list as concrete actions (e.g., "Look up available GitNexus tools, query the knowledge graph, read MCP resources, inspect the graph schema") rather than noun phrases to raise specificity.

Add a natural synonym or two beyond the product name (e.g., "code knowledge graph", "code graph") to broaden trigger term coverage.

DimensionReasoningScore

Specificity

The description names the domain (GitNexus) and enumerates several concrete capability areas ("available tools, how to query the knowledge graph, MCP resources, graph schema, or workflow reference") but these are objects/topics rather than discrete actions, leaving it between the 3 and 4 anchors; it stops short of listing multiple specific concrete actions, so 3 fits best.

3 / 5

Completeness

It explicitly answers both what (reference for tools, query, MCP resources, graph schema, workflow reference) and when ("Use when the user asks about GitNexus itself") with concrete trigger phrases and example questions, matching the anchor for clearly answering both what AND when.

5 / 5

Trigger Term Quality

Natural trigger phrasing is strong with example quotes a user would actually say ("What GitNexus tools are available?", "How do I use GitNexus?") plus the term "GitNexus" itself, but coverage of natural synonyms beyond the product name is limited, placing it clearly above midpoint but not comprehensive enough for a 5.

4 / 5

Distinctiveness Conflict Risk

The product name "GitNexus" forms a clear niche with distinct triggers, and the "Use when the user asks about GitNexus itself" clause sharply bounds it against other skills, giving 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
abhigyanpatwari/GitNexus
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.