Content
57%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 thorough, well-structured reference with concrete emulation guidance, but it is monolithic and verbose, and its destructive-operation workflow lacks explicit validation checkpoints.
Suggestions
Add validation/verification checkpoints to the emulation workflow (e.g. confirm scope authorization before each destructive play, verify implant behavior in an isolated lab before scaling) to lift workflow clarity above the destructive-ops cap.
Move the detailed TTP-by-tactic catalog and signature-tooling table into a separate references file (e.g. TTPS.md) referenced from SKILL.md, keeping the overview and emulation guidance inline for progressive disclosure.
Trim redundant per-technique prose (e.g. consolidate the repeated malware-family lists) to improve token efficiency.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The body is information-dense and avoids explaining concepts Claude already knows, but at ~265 lines it is encyclopedic; several per-technique descriptions and campaign recaps could be tightened without losing value. | 3 / 5 |
Actionability | The 'Emulation guidance (Decepticon)' section maps each play to concrete tools and ATT&CK techniques (phishing skill, payload-builder, c2 skill, Sliver, Mimikatz, AD skill), giving mostly executable instructional guidance with minor gaps. | 4 / 5 |
Workflow Clarity | Plays are loosely ordered by ATT&CK tactic (a rough lifecycle sequence) but there are no explicit validation checkpoints or feedback loops; because the skill covers destructive operations (kernel rootkits, T1485), workflow clarity is capped at 3. | 3 / 5 |
Progressive Disclosure | Section headers are clear and well-organized, but the entire profile — campaign history, full TTP catalog, tooling table — is inlined in one ~265-line SKILL.md with no bundle files or one-level-deep references to split it. | 3 / 5 |
Total | 13 / 20 Passed |