pentest-commands

This skill should be used when the user asks to "run pentest commands", "scan with nmap", "use metasploit exploits", "crack passwords with hydra or john", "scan web vulnerabilities with nikto", "enumerate networks", or needs essential penetration testing command references.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/pentest-commands/SKILL.md

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, copy-paste-ready command reference that assumes Claude's competence and avoids concept bloat, but it is organized as a flat tool catalog rather than a sequenced workflow and is a large monolith with no progressive disclosure into bundle files. Adding a process sequence with validation and splitting per-tool references would meaningfully improve it.

Suggestions

Add a brief sequenced pentest workflow (recon -> enumeration -> exploitation -> credential cracking -> web testing) with validation checkpoints before destructive steps like brute forcing and exploitation, so the "Core Workflow" is an actual workflow rather than a tool catalog.

Split the large per-tool command blocks into reference files (e.g. references/nmap.md, references/metasploit.md) and have SKILL.md point to them one level deep, turning the monolith into a navigable overview.

Remove the redundancy between the "Quick Reference"/"Examples" sections and the earlier per-tool blocks so every token earns its place.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean command blocks with brief comments and minimal concept explanation, but the "Quick Reference" and "Examples" sections duplicate commands already shown (e.g. "nmap -sV --script vuln", "nmap -F"), so it could be tightened.	2 / 3
Actionability	It is packed with concrete, executable, copy-paste-ready commands (e.g. "nmap -sS 192.168.1.1", "hydra -l admin -P /usr/share/wordlists/rockyou.txt ssh://192.168.1.1", "msfvenom -p windows/meterpreter/reverse_tcp ... -f exe > shell.exe") with specific syntax throughout.	3 / 3
Workflow Clarity	Sections are numbered by tool category rather than a sequenced pentest workflow (recon -> enumerate -> exploit -> crack), and there are no validation checkpoints despite destructive operations like brute forcing and exploitation; the "Constraints" section notes risks but provides no verify-before-proceeding steps.	2 / 3
Progressive Disclosure	The content is well-organized with clear section headers, but it is a monolithic ~430-line SKILL.md with no bundle files (references/, scripts/, assets/ all absent); per-tool command references that could live in separate files are all inlined.	2 / 3
	Total	9 / 12 Passed

Description

72%

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 trigger-focused description with explicit natural-language phrasing and a clear, conflict-resistant niche, weakened by a vague and buried statement of what the skill actually provides. Leading with a concrete capability statement would lift specificity and completeness.

Suggestions

Lead with a concise capability statement in third person (e.g., "Provides command references for penetration testing tools including nmap, metasploit, hydra, john, and nikto.") so the "what" is explicit before the triggers.

Reword the trailing "or needs essential penetration testing command references" into a clear skill action ("Looks up essential penetration testing commands") instead of a user-need clause.

Trim redundancy between the quoted trigger list and the trailing references phrase so every clause earns its place.

Dimension	Reasoning	Score
Specificity	The description names concrete tools ("scan with nmap", "use metasploit exploits", "crack passwords with hydra or john", "scan web vulnerabilities with nikto"), but the skill's own capability is stated only once and vaguely as "essential penetration testing command references", with the actions framed as user triggers rather than what the skill does.	2 / 3
Completeness	The "when" is strongly explicit via quoted triggers, but the "what" is a weak subordinate clause ("or needs essential penetration testing command references") blended into the trigger list rather than a clear leading capability statement, so it does not cleanly answer both.	2 / 3
Trigger Term Quality	It includes explicit quoted natural-language triggers a user would actually say ("run pentest commands", "scan with nmap", "enumerate networks"), giving good coverage of natural terms across the pentest domain.	3 / 3
Distinctiveness Conflict Risk	The pentest niche with named tools (nmap, metasploit, hydra, john, nikto) and distinct tool-specific triggers is clearly distinguishable and unlikely to fire for the wrong skill.	3 / 3
	Total	10 / 12 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: zebbern/claude-code-guide
Path: skills/pentest-commands/SKILL.md
Commit: af7d491

Reviewed: about 9 hours 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.