pt-planning-recon
Defines penetration test scope and performs authorized reconnaissance using passive and active methods. Use when planning a test engagement, collecting target intelligence, building asset inventories, or preparing recon findings.
91
87%
Does it follow best practices?
Impact
96%
1.15xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-structured skill description with explicit 'Use when' guidance and good trigger term coverage for the security/pentesting domain. The main weakness is that the capabilities could be more specific - listing concrete reconnaissance actions rather than just 'passive and active methods' would strengthen it.
Suggestions
Add specific concrete actions like 'enumerate subdomains, scan ports, fingerprint services, gather OSINT' to improve specificity
Consider adding file type triggers if applicable (e.g., 'scope documents', 'target lists', '.nmap files')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (penetration testing) and mentions 'passive and active methods' but doesn't list specific concrete actions like 'enumerate subdomains, scan ports, fingerprint services'. The actions remain somewhat abstract. | 2 / 3 |
Completeness | Clearly answers both what ('Defines penetration test scope and performs authorized reconnaissance using passive and active methods') and when ('Use when planning a test engagement, collecting target intelligence, building asset inventories, or preparing recon findings'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'penetration test', 'reconnaissance', 'recon', 'target intelligence', 'asset inventories', 'test engagement'. Good coverage of terms a security professional would use. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche in penetration testing/security reconnaissance with distinct triggers like 'penetration test', 'recon', 'target intelligence'. Unlikely to conflict with general coding or document skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured planning and reconnaissance skill that excels at workflow clarity and organization. The main weakness is the lack of concrete, executable examples - the skill describes what to do but doesn't show specific commands or tool usage, which limits immediate actionability for the reconnaissance steps.
Suggestions
Add concrete command examples for passive recon (e.g., specific dig, whois, or subfinder commands with safe defaults)
Include an executable example for active recon showing host discovery with rate limiting (e.g., nmap with specific flags)
Add a brief example of what a populated Asset Inventory entry looks like with real-world-style data
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using bullet points and structured lists without explaining basic concepts Claude already knows. Every section serves a clear purpose with no padding or unnecessary context. | 3 / 3 |
Actionability | Provides clear procedural guidance and a useful output template, but lacks concrete executable commands or code examples. Phrases like 'host discovery and service fingerprinting' are described rather than demonstrated with specific tools/commands. | 2 / 3 |
Workflow Clarity | Clear 5-step workflow with explicit sequencing (passive before active), validation checkpoints in Quality Checks section, and explicit constraints. The workflow includes logging requirements and handoff criteria. | 3 / 3 |
Progressive Disclosure | For a skill of this size (~60 lines), the content is well-organized with clear sections. No external references are needed as the scope is appropriately bounded. Headers provide easy navigation. | 3 / 3 |
Total | 11 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- santosomar/ethical-hacking-agent-skills
- Commit
a8ff73a
- 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.