Content
86%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 lean, high-signal evidence standard: it states exactly what to record for each class of postexploit claim (shells, credentials, file transfers, C2 callbacks, cleanup) and what does not count as proof, with no over-explanation and no padding. Its main gaps are the absence of a worked example of a recorded evidence entry and its reliance on sibling technique skills for implementation details.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~38-line body assumes Claude's competence — it drops "a ticket's SPN, realm and delegation constraints" without explanation — and every sentence is directive (what to record, what counts as proof, e.g. "A successful TCP connection or a shell-like banner is not proof of code execution"). This matches 'Lean and efficient; assumes Claude's competence; every token earns its place'; nothing reads as padding to trim. | 5 / 5 |
Actionability | The guidance is concrete and specific for an instruction-only skill — "record protected artifact paths, source identity, credential type, validity window and the service where use was actually validated" and "record source/destination paths, hash and byte count" are near-checklist directives. It stops short of anchor 5 because there is no worked example of a recorded evidence entry and implementation details are deferred to sibling technique skills ("Use the relevant existing technique skills for implementation details"). | 4 / 5 |
Workflow Clarity | Content is organized by claim type with explicit evidentiary checkpoints ("Privilege and lateral-access claims require before/after identity and a concrete observable at each claimed hop") and explicit handling of missing information ("Separate attempted actions, observed defender events and unavailable telemetry"). It is not anchor 5 because no sequence or validate-fix-retry loop is given — the skill deliberately disclaims defining "an engagement stage order" — leaving the workflow implicit. | 4 / 5 |
Progressive Disclosure | The body is under 50 lines, self-contained, and organized into two clear sections ("Access and credential evidence", "State changes and transport") with no external file references needed, matching the rubric exception where short simple skills score 5 on well-organized sections alone. No bundle files exist and none are referenced, so there is no buried or nested content. | 5 / 5 |
Total | 18 / 20 Passed |