Content
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a solid, well-structured workflow for pen test planning and reconnaissance with appropriate safety guardrails and a useful output template. Its main weakness is the lack of concrete, executable examples—no specific tool commands, queries, or real-world examples are provided, keeping the guidance at an abstract instructional level. The structure and safety considerations are strengths, but actionability would benefit significantly from tool-specific examples.
Suggestions
Add concrete command examples for key recon steps (e.g., specific nmap, dig, subfinder, or amass commands with recommended flags and safe defaults).
Include a brief worked example showing a sample recon output populated with realistic (fictional) data to demonstrate expected deliverable quality.
Consider splitting tool-specific guidance into a referenced file (e.g., RECON_TOOLS.md) to keep the main skill lean while providing depth.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient and doesn't over-explain concepts Claude already knows, but some bullet points are somewhat generic (e.g., 'Deduplicate assets and map to owners/business function when known') and could be tightened. The output template adds useful structure but is partially redundant with the workflow description. | 2 / 3 |
Actionability | The skill provides a clear process and output template, but lacks concrete executable commands or tool-specific examples. For a recon skill, specific commands (e.g., nmap flags, dig queries, subfinder usage) or at least named tool recommendations would significantly improve actionability. The guidance remains at the descriptive/instructional level rather than copy-paste ready. | 2 / 3 |
Workflow Clarity | The workflow is clearly sequenced with a logical progression: confirm scope → passive recon → active recon → normalize → handoff. The 'Quality Checks' section serves as a validation checkpoint, and the explicit requirement to confirm authorization before proceeding and log every command provides appropriate safeguards for this high-risk domain. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and a useful output template, but everything is inline in a single file. For a skill of this complexity, references to separate files for tool-specific commands, example recon reports, or detailed methodology guides would improve navigation and reduce the main file's density. | 2 / 3 |
Total | 9 / 12 Passed |