Conciseness

The body is ~26 lines of terse, dense directives with zero padding and no explanation of concepts Claude already knows. Every rule ("If a rule is organizational, enforce it on the server") carries information, matching 'Lean and efficient; every token earns its place'.

Actionability

Rules like "If a pattern repeats, capture it as a skill or project convention" and "If a rule is organizational, enforce it on the server" are concrete behavioral directives, but key terms are undefined — 'fake UX and fake controls', 'generic enterprise UI/architecture drift', and what a 'substantial' change is are left to guesswork, and there are no examples of rule violations or correct application. This is 'some concrete guidance but incomplete; missing key details' rather than the mostly-executable level of 4.

Workflow Clarity

The 'When to Use' section gives explicit use conditions and the rules are a simple flat checklist with no risky multi-step process, so the simple-skill pattern applies; the single action (apply these norms during the listed activities) is unambiguous. It does not reach 5 because there is no guidance on what to do when rules conflict or when a review finds a violation — a light decision/checkpoint step would complete it.

Progressive Disclosure

The skill is under 50 lines with no external references needed, and the content is cleanly split into three well-organized sections (When to Use, Cultural Rules, Collaboration Rules) with no inline content that belongs in a separate file. Per the rubric's simple-skill guideline, this warrants 5 on well-organized sections alone.

Specificity

The description names the domain clearly ("Cultural and collaboration norms for Engram contributors and agents") but lists no concrete actions or capabilities — it states what the skill is about, not what it does. It matches the anchor 'Names the domain but actions are minimal or generic'; it does not reach 3 because not even one concrete action (e.g., 'apply', 'check', 'enforce') is stated.

Completeness

Both parts are present: a 'what' ("Cultural and collaboration norms for Engram contributors and agents") and an explicit 'when' ("Trigger: Starting substantial work, reviewing changes, or defining team conventions"), which satisfies the explicit-trigger requirement. It falls short of 5 because the 'what' is a topical label rather than a concrete capability statement, so it doesn't 'clearly and explicitly answer both' at the level of the 5-anchor examples.

Trigger Term Quality

The trigger clause includes some natural phrases ("reviewing changes", "defining team conventions") but misses common variations and synonyms users would actually say — "starting substantial work" is not phrasing a user naturally produces, and there are no equivalents of synonyms or file-extension-style discriminators. This sits at 'Some relevant keywords but missing common variations or synonyms' rather than 4's 'good keyword coverage'.

Distinctiveness Conflict Risk

The 'Engram contributors and agents' framing carves out a clear niche with minimal overlap against generic skills, and 'defining team conventions' is a fairly distinct trigger. However, 'Starting substantial work' and 'reviewing changes' are broad phrases that could overlap with code-review or project-setup skills, keeping it below the 'clear niche with distinct triggers' of a 5 — this is 'mostly distinct; minor overlap risk'.