Content
100%Weight 40%Scale 1-3Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
A tight, well-structured investigative skill body: concise, actionable, with a clear sequenced workflow, a prove-it verification step, and a single clearly-signaled reference file that exists in the bundle.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Lean and efficient with no padding or explanation of concepts Claude already knows; every line is investigative guidance that earns its place, matching the 'lean and efficient; assumes Claude's competence' anchor. | 3 / 3 |
Actionability | Although there is no code (appropriate for an instruction-only analytical skill), the guidance is concrete and specific — 'Correlate consent logs, sign-ins, message traces, inbox rules...' and 'Compress the path to the smallest sequence: lure or grant -> token or delegate edge -> mailbox or transport mutation -> resulting mail effect' — meeting the actionable standard without being penalized for absent code. | 3 / 3 |
Workflow Clarity | A clear three-step sequence (Map -> Prove -> Reduce) with an explicit verification checkpoint in Quick Start step 5 ('Reproduce the smallest mail effect that proves persistence, exfiltration, or privilege'); for a simple analytical skill this satisfies the 'clear sequence with explicit validation steps' anchor. | 3 / 3 |
Progressive Disclosure | Under 50 lines and well-organized into clear sections, with a single one-level-deep, clearly signaled reference to references/mailbox-abuse.md (verified to exist) — meeting the 'well-organized sections' allowance for short skills. | 3 / 3 |
Total | 12 / 12 Passed |