Content
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A highly actionable, well-sequenced operational guide with strong validation feedback via its decision gate and error tables. It loses points for verbosity/conceptual padding and for keeping everything in a single monolithic file rather than splitting deep provider/tool references.
Suggestions
Trim the conceptual 'How It Works' intro and ASCII diagram to a one-line summary; Claude already understands TLS SNI vs Host header fronting.
Extract the per-provider setups (CloudFront/Azure/Fastly) and the Cobalt Strike/Sliver profiles into separate reference files (e.g. references/cloudfront-setup.md, references/malleable-profiles.md) and link them one level deep from SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The bulk is action-dense (commands, JSON/nginx/malleable configs, worker code, tables), but the intro paragraph, ASCII diagram, and 'TLS layer / HTTP layer' breakdown re-explain fronting concepts Claude already knows, and the ~488-line length is verbose even though accurate. | 2 / 3 |
Actionability | Fully executable, copy-paste-ready guidance throughout — aws/az/curl commands, CloudFront JSON config, malleable C2 profile, Sliver profile, nginx and Cloudflare Worker code — with explicit placeholders and expected outputs. | 3 / 3 |
Workflow Clarity | Numbered setup steps, a 'Test fronting' checkpoint with explicit success/failure criteria (HTTP 200 vs 403), a Decision Gate tree, and Error Handling tables provide clear sequencing with feedback loops for recovery. | 3 / 3 |
Progressive Disclosure | No bundle files exist and the entire skill is one monolithic 488-line file; well-organized sections keep it above 1, but provider-specific setups and C2 profiles that could be split into separate references are all inline. | 2 / 3 |
Total | 10 / 12 Passed |