gitnexus-explorer

Serve an interactive codebase knowledge graph web UI.

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/research/gitnexus-explorer/SKILL.md

Quality

Content

71%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 skill is highly actionable with a well-sequenced, executable workflow and useful pitfalls, but it underuses progressive disclosure by inlining a bundle script that already exists as a file, which also inflates token cost. Pointing Step 4 at scripts/proxy.mjs and adding a validation feedback loop would raise the weakest dimensions.

Suggestions

Replace the inlined proxy.mjs source in Step 4 with a reference to the bundle file, e.g. "Copy scripts/proxy.mjs to $GITNEXUS_DIR/proxy.mjs" or "node scripts/proxy.mjs …", and keep only the invocation inline.

Add an explicit feedback loop around service startup: after `curl /api/repos`, instruct to restart the backend/proxy and re-check if the response is empty or the connection fails.

Guard the destructive cleanup (e.g. confirm `.claude/` is gitnexus-generated before `rm -rf`, or scope the removal) so the workflow's destructive steps have validation.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient commands and code with no concept over-explanation, but Step 4 inlines the full ~45-line proxy.mjs source that already exists as a bundle file, a notable duplication that could be tightened.	3 / 5
Actionability	Every step provides copy-paste-ready, fully executable guidance — bash setup, exact TypeScript patches, a complete Node proxy, and a curl verification command — covering the common cases end to end.	5 / 5
Workflow Clarity	Seven clearly numbered steps with an explicit verification checkpoint (curl /api/repos) and a Pitfalls section for error recovery; falls short of 5 because there is no validate→fix→retry feedback loop and the destructive `rm -rf .claude/` runs unguarded.	4 / 5
Progressive Disclosure	Section structure is clear (When to Use, Prerequisites, Size Warning, Steps, Pitfalls), but the proxy script that exists as scripts/proxy.mjs is inlined verbatim in Step 4 instead of being referenced, so content that should be separate is inline and the bundle file is never signaled.	3 / 5
	Total	15 / 20 Passed

Description

61%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 concise and names a distinct, recognizable niche, but it omits any explicit "when to use" trigger guidance and lists only one concrete action. Adding a "Use when..." clause with a couple more trigger phrases would lift completeness and trigger-term quality.

Suggestions

Append a trigger clause, e.g. "Use when the user wants to visually explore a codebase's architecture, build a dependency/knowledge graph of a repo, or share an interactive codebase explorer."

Add a second concrete action and a synonym (e.g. "index" / "dependency graph") to broaden trigger-term coverage and specificity.

Dimension	Reasoning	Score
Specificity	"Serve an interactive codebase knowledge graph web UI" names the domain (codebase knowledge graph) and one concrete action (serve a web UI), but lists only a single action and is not comprehensive, matching the 1-2 concrete actions anchor.	3 / 5
Completeness	The description gives a clear "what" but contains no "Use when..." clause or equivalent trigger guidance; per the rubric guideline, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Natural user-facing phrases like "codebase", "knowledge graph", and "web UI" appear, giving good keyword coverage; common synonyms such as "dependency graph", "code map", or "code exploration" are missing, so it is just short of comprehensive.	4 / 5
Distinctiveness Conflict Risk	"codebase knowledge graph web UI" carves a clear niche with distinct triggers and minimal conflict risk, with only minor overlap against closely related codebase-inspection skills (listed in metadata.related_skills).	4 / 5
	Total	14 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/research/gitnexus-explorer/SKILL.md
Commit: 48f69e5

Reviewed: 4 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.