Conciseness

The body is lean and assumes Claude's competence — no padding, no explanation of basic concepts, and every line earns its place, matching the 'lean and efficient' anchor.

Actionability

Steps are concrete and include a specific staged-evidence example ('Fake execution of prisoners, display their bodies as proof'), but as an instruction-only skill some steps remain high-level rather than fully copy-paste executable.

Workflow Clarity

A clear 7-step sequence is paired with a dedicated Verification section containing validation checkpoints, but the steps are descriptive rather than command-driven and the error-recovery feedback loop is only lightly sketched.

Progressive Disclosure

At under 50 lines, single-purpose, with no external references needed and well-organized sections (Overview, Steps, Risk Factors, Failure Points, Outcomes, Verification), this meets the simple-skill exception for a top score.

Specificity

Names the domain and several concrete actions ('agent selection, credibility establishment, force coordination, and engagement triggers') with only minor coverage gaps, matching the 'lists several specific actions' anchor rather than the comprehensive 5.

Completeness

Explicitly answers both 'what' ('Covers agent selection...') and 'when' ('Use when planning military ambushes...') with concrete trigger phrases, matching the top anchor.

Trigger Term Quality

'Use when planning military ambushes using double agents and staged evidence' provides natural trigger phrasing users would actually say, though synonym/extension coverage is limited compared to the comprehensive 5.

Distinctiveness Conflict Risk

The military-ambush/deception niche is highly specific with distinct triggers and minimal overlap risk with other skills, matching the 'clear niche' anchor.