Content
75%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.
The body is a strong, action-dense playbook: a numbered workflow with real verification steps, race-condition error handling, safe-PoC guardrails, and cleanup, plus a defender remediation section. Weaknesses are minor: undefined environment-specific helpers (s3_takeover_check, kg_* graph calls), unset shell variables in the verify snippet, and supplementary sections (CVSS, remediation, exemplars) inlined that could be split out.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is command-driven and lean, with only minor trimmable content: the 2-sentence intro restates takeover mechanics Claude already knows, and the dated "Known exemplars" trivia is not operational. This fits 'efficient; minor instances of over-explanation' rather than the padding at 2 or the every-token-earns-its-place ideal at 5. | 4 / 5 |
Actionability | Mostly executable copy-paste commands (subfinder/dig enumeration loop, curl NoSuchBucket checks, aws s3api create-bucket, remediation jq pipeline), but with minor gaps: s3_takeover_check() and kg_add_node/kg_add_edge reference environment-specific helpers not defined in the skill, and $SUBDOMAIN/$CNAME are used without being set. This matches 'mostly executable guidance; concrete code with minor gaps' at 4, not the fully-ready anchor at 5. | 4 / 5 |
Workflow Clarity | A clearly numbered sequence (enumerate → verify dangling → claim → safe PoC → frame impact → promote) with explicit verification (step 2), error-recovery feedback for BucketAlreadyExists race conditions, a DO/DO-NOT checklist, and cleanup (aws s3 rb --force). The only minor gap is that post-claim verification is a comment ("# Now curl ... returns your content") rather than a runnable check, fitting anchor 4 rather than 5; validation is present, so the destructive-workflow cap at 3 does not apply. | 4 / 5 |
Progressive Disclosure | No bundle files exist and the skill is self-contained with well-labeled sections, which is appropriate structure; the minor gap is that defender remediation, CVSS scoring, and known exemplars could be split into reference files to keep the core offensive workflow lean. This matches 'good structure; most content appropriately placed; minor organization gaps' at 4 rather than the ideal split at 5. | 4 / 5 |
Total | 16 / 20 Passed |