Content
82%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A highly actionable, token-efficient reference with concrete commands across AWS, GCP, and Azure, well-sequenced with an explicit IMDSv2 failure boundary. Structure is good but the single-file density and unresolved cross-skill references leave modest room for progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Dense tables and copy-paste commands with no explanation of concepts Claude already knows. Minor redundancy (endpoint URLs repeated between the §1 table and §2–5 commands) and tangential sections (CVSS, defender remediation, exemplars) keep it below the lean-anchor 5. | 4 / 5 |
Actionability | Fully executable, copy-paste-ready curl commands for AWS IMDSv1/v2, GCP, and Azure, plus concrete bypass encodings ('2852039166', '0xA9FEA9FE', '169.254.169.0254') and jq/env export steps covering the common cases. | 5 / 5 |
Workflow Clarity | Clearly sequenced 1–8 (identify provider → extract → bypass filters → promote) with a verification checkpoint (aws sts get-caller-identity) and an explicit failure boundary in §7. Not 5 because error-recovery guidance for partial failures (e.g., empty token, 401 responses) is absent. | 4 / 5 |
Progressive Disclosure | Well-organized sections with clear headers and no bundle files to manage, but ~180 lines of dense per-cloud reference plus defender/CVSS/exemplar content could be split into reference files; cross-skill pointers ('Pivot to aws-iam-enum/SKILL.md', 'SSRF skill catalog') are not clearly resolved one-level-deep references. | 4 / 5 |
Total | 17 / 20 Passed |