Content
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a competent OSINT skill that covers the domain broadly and includes some executable commands, a useful output template, and appropriate ethical guardrails. However, it leans toward being a reference catalog of sources rather than a tightly actionable workflow — many sections list what to check without providing concrete commands or code. The skill would benefit from more executable examples and a clearer step-by-step investigation workflow with explicit validation checkpoints.
Suggestions
Convert the bullet-point source lists (Organization OSINT, Email OSINT, Threat Intelligence) into concrete commands or API calls where possible — e.g., provide actual curl commands for HaveIBeenPwned API, searchsploit syntax, or VirusTotal lookups.
Add an explicit numbered workflow (Step 1: Define scope → Step 2: Infrastructure collection → Step 3: Cross-reference → Step 4: Validate findings → Step 5: Generate report) with validation checkpoints between phases.
Move the detailed output report template and the full collection techniques catalog into separate bundle files (e.g., REPORT_TEMPLATE.md, COLLECTION_TECHNIQUES.md) and reference them from the main skill to improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary explanatory text (e.g., the Organization OSINT bullet list is mostly things Claude already knows how to look up, and the Ethics Check section is somewhat verbose). The cross-references paragraph at the top is useful but wordy. | 2 / 3 |
Actionability | Provides some executable commands (whois, dig, crt.sh curl, exiftool, Google dorks) but many sections are just bullet-point lists of sources without concrete commands or code. Email/Username OSINT, Organization OSINT, and Threat Intelligence sections describe rather than instruct. | 2 / 3 |
Workflow Clarity | The overall flow (ethics check → collection → analysis → output) is implicit but not explicitly sequenced with numbered steps or validation checkpoints. The Analysis section mentions cross-referencing and validation but lacks a concrete feedback loop or verification process for the multi-step investigation workflow. | 2 / 3 |
Progressive Disclosure | Content is reasonably well-organized with clear section headers, but everything is inline in a single file with no bundle files to offload detailed content. The references section at the bottom is minimal and external-only. Sections like the full output template and detailed collection techniques could benefit from being split into separate files. | 2 / 3 |
Total | 8 / 12 Passed |