homelab-network-auditor

Audit homelab network topology, scan for open ports and exposed services, review firewall rules, and generate network security reports.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/homelab-network-auditor/SKILL.md

Quality

Content

72%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 concise, well-structured, and safe-by-design, but it offers no executable commands or concrete nmap/firewall examples and lacks validation checkpoints in its scanning workflow. Adding specific commands and a validate-against-expected step would meaningfully raise actionability and workflow clarity.

Suggestions

Add concrete, copy-paste-ready commands for key steps (e.g., `nmap -sn 192.168.1.0/24` for discovery, `nmap -sV <host>` for service scanning) to lift actionability.

Insert an explicit validation checkpoint after scanning — e.g., compare detected open ports against a documented expected-services list and flag mismatches before reporting.

Either populate references/scripts bundle files and link to them, or remove the implication of bundled tooling so progressive disclosure fully matches the actual structure.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-organized with short purpose, invocation, workflow, and safety sections that assume Claude's competence and explain only what is specific to the homelab context — every token earns its place.	5 / 5
Actionability	Workflow names concrete tools (nmap, ARP scan, firewall API) but provides no executable commands, code, or example invocations — guidance stays at the descriptive level rather than copy-paste ready, matching the score-3 anchor of incomplete/pseudocode-level guidance.	3 / 5
Workflow Clarity	The 8-step sequence is clearly listed, but this skill performs batch/destructive-adjacent scanning operations and lacks explicit validation checkpoints or feedback loops (e.g., confirm scan results against expected services), so the missing-feedback-loop cap holds it at 3 despite the clear sequence.	3 / 5
Progressive Disclosure	Content is well-sectioned into Purpose/Invocation/Workflow/Safety/MCP/References with one-level-deep external links and named companion skills, but the references/ and scripts/ bundle directories are empty (.gitkeep only), so the structure is clean without actual bundle files to organize — minor gaps keep it below 5.	4 / 5
	Total	15 / 20 Passed

Description

63%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 specific and action-oriented with natural trigger terms, but it lacks an explicit "Use when..." clause that would fully answer when Claude should invoke it. Adding a trigger phrase would lift completeness and distinctiveness.

Suggestions

Append an explicit "Use when..." clause (e.g., "Use when auditing homelab network security, scanning for open ports, or reviewing firewall rules") to raise completeness above 3.

Add common synonyms or variations (e.g., "port scan", "nmap", "VLAN") to broaden trigger term coverage.

Tighten "Audit homelab network topology" into a more concrete action to reach the fully enumerated action list of the top anchor.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "scan for open ports and exposed services, review firewall rules" and "generate network security reports" — covering the domain well, though "audit topology" is slightly generic compared to the score-5 anchor's fully enumerated action list.	4 / 5
Completeness	Has a clear "what" but no explicit "Use when..." trigger clause, so "when" is only weakly implied — the judging guideline caps completeness at 3 for a missing explicit trigger.	3 / 5
Trigger Term Quality	Contains natural phrases users would say ("scan for open ports", "exposed services", "firewall rules", "network security report") with good coverage, but lacks synonyms and file/extension-style terms that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	The homelab-network-auditor niche is fairly distinct with specific triggers (open ports, firewall, exposed services), with only minor overlap risk against adjacent homelab skills like topology-mapper or safe-ops.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pvnkmnk/AgenticSelfHostSkills
Path: skills/homelab-network-auditor/SKILL.md
Commit: 0f62e6b

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.