The body assumes Claude's competence — it never explains what a Chrome extension or service worker is — and concentrates on non-obvious, load-bearing facts (the literal `return true`, JSON-vs-structured-clone payload table, first-listener-wins, 30-second idle termination), so tokens earn their place rather than padding basics; the mild re-listing of the five shapes in "How to use" step 1 is reinforcing, not fluff.

Authoring gives real, copy-paste-ready JavaScript for sender/listener pairs and executable jest-style tests (e.g. `expect(response).toEqual({ statusCode: 200 })` and the `connecting with an unknown port name disconnects immediately` test in the ports reference), not pseudocode; the small `sendFromContentScript` / `settle` helpers are obvious test utilities rather than missing key details.

"How to use" is a clear six-step sequence ending in an explicit validation checkpoint ("Re-check the draft against the Anti-patterns table before committing"), backed by the Anti-patterns table and the worked-example test checklist; the missing-validation cap does not apply because this is test authoring, not a destructive or batch operation.

SKILL.md is an overview that keeps the two one-shot shapes inline and pushes the more incidental depth to two clearly signaled, one-level-deep companion files — references/long-lived-ports.md and references/cross-boundary-messaging.md, both present and pointing back to Chrome docs rather than nesting further — exactly matching the well-organized overview-plus-references anchor.

Lists multiple specific concrete actions — "one-shot chrome.runtime.sendMessage plus the literal return true", "chrome.tabs.sendMessage into one tab's content script", "long-lived chrome.runtime.connect ports and their onDisconnect triggers", "externally_connectable", "chrome.runtime.connectNative native-messaging hosts" — matching the anchor that names several concrete actions rather than vague domain language.

It explicitly answers both what ("Asserts Chrome extension message-passing behaviour against a running extension") and when ("Use when a message reaches no listener, a sendResponse callback never fires, a port disconnects mid-test, or a page origin has to be proven allowed before publishing"), satisfying the explicit-trigger requirement that would otherwise cap completeness at 2.

The "Use when" clause supplies natural symptom phrasings a developer would actually say — "a message reaches no listener", "a sendResponse callback never fires", "a port disconnects mid-test", "a page origin has to be proven allowed" — alongside the exact chrome.* API names that are the domain's natural vocabulary, giving good coverage rather than a single generic keyword.

The niche is sharply bounded — messaging behaviour on an already-running extension, with an explicit "not the install or reload step" scope carve-out — so its triggers are distinct and unlikely to fire for adjacent extension-development skills.