Content
62%Scale 1-3Reviews 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, comprehensive OSINT methodology framework that excels at workflow clarity and systematic organization of a complex multi-stage process. Its main weakness is that it operates as a high-level playbook that defers all concrete implementation details to a companion skill that isn't included in the bundle, reducing actionability. The content is reasonably concise for its ambitious scope but could be tightened in places where it explains concepts Claude would already know.
Suggestions
Include the referenced 'offensive-osint' companion skill in the bundle, or inline the most critical concrete implementations (e.g., key curl commands, top 5 dork patterns, bucket permutation wordlist) to make the skill independently actionable.
Split specialty domains (§13), client deliverable templates (§16), and bug bounty guidance (§15) into separate referenced files to reduce the monolithic nature of the main SKILL.md.
Add at least one end-to-end worked example showing a complete finding from seed discovery through to the output schema, demonstrating the pipeline with concrete tool commands rather than just tool names.
Trim the anti-patterns section (§14) to only items that are non-obvious — entries like 'Attribution by IP geolocation. VPNs and residential proxies exist.' explain things Claude already knows.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extensive (~480 lines) and covers a lot of ground efficiently for its scope, but includes some content Claude already knows (e.g., explaining what UTC is, basic concepts like 'VPNs and residential proxies exist'). The anti-patterns section and some table entries could be tighter. However, most content is domain-specific methodology that genuinely adds value. | 2 / 3 |
Actionability | The skill provides structured frameworks, severity rubrics, confidence upgrade workflows, and clear decision trees, which are highly actionable at a methodological level. However, it deliberately defers all concrete implementation (curl commands, regexes, wordlists, probe paths) to a companion skill 'offensive-osint' that is not included in the bundle. The skill tells you *what* to do but not *how* — no executable code, no copy-paste commands, no concrete tool invocations beyond tool names. | 2 / 3 |
Workflow Clarity | The 5-stage pipeline is clearly sequenced with explicit ordering, time budgets, abort conditions, and priority rankings. The detection-aware probing section (§6.4) provides an excellent back-off ladder with explicit escalation/de-escalation steps. Confidence upgrade workflows provide clear validation checkpoints for each asset type. The engagement profiles provide clear decision points for scope and depth. | 3 / 3 |
Progressive Disclosure | The skill makes extensive references to a companion skill 'offensive-osint' with specific section numbers (§13, §16.1, §16.8, §16.14, §16.15, §20, §21, §22, §23, §29.2), which is good progressive disclosure design. However, no bundle files are provided, meaning none of these references are actually resolvable. The SKILL.md itself is a monolithic document with 18 sections that could benefit from splitting some content (e.g., specialty OSINT domains, client deliverable templates) into separate files. | 2 / 3 |
Total | 9 / 12 Passed |