Conciseness

The body is dense with repo-specific, non-inferable facts (condition tier lists, build-skipping semantics, pragma-attachment hard errors) and explains nothing Claude already knows, but the off-state cost calculus is stated three times — "browser e2e time is considerable, so skip the run" in item 3, item 4, and again in "Is the off-state run worth its cost?" ("For a new API the calculus flips: … so the off state costs almost nothing"), and the use-offline example and stale-gate semantics are each repeated. That is more than the 5 anchor's 'every token earns its place' but is trimmable redundancy rather than padding, so 4 rather than 3 or 5.

Actionability

Guidance is fully executable: copy-paste-ready verification commands with env vars ("__NEXT_TEST_AXIS=A NEXT_SKIP_ISOLATE=1 pnpm test-start-webpack test/e2e/app-dir/<suite>/<suite>.test.ts"), an executable fixture config snippet, concrete pragma examples, exact condition names, and real working-example directories ("test/e2e/app-dir/use-offline/", "test/e2e/app-dir/concurrent-router-queue/"). Specific examples cover the common cases, matching the 5 anchor.

Workflow Clarity

The decision sequence is clearly laid out (numbered directive-choice cases → condition tiers → fixture pattern → pitfalls) and the "Verify a gated suite in every state it can run in" section provides explicit validation checkpoints with expected outcomes per state ("expect `○ skipped` at collection, no fixture boot", "expect `⚠ gated test failed as expected`"), plus error-recovery guidance in Pitfalls. This is not a destructive or batch operation, so no cap applies, and it matches the explicit-validation 5 anchor rather than the minor-gaps 4 anchor.

Progressive Disclosure

No bundle files exist, and the body opens with a clearly signaled one-level reference — "Full reference: [`test/lib/gate/README.md`](../../../test/lib/gate/README.md). This skill is the decision guide" — keeping only the decision guide inline and appropriately deferring full detail. Sections are well-organized with no nested references and easy navigation, matching the clear-overview 5 anchor.

Specificity

Names multiple concrete actions — "How to use the `@gate` / `@force-gate` test directives instead of `it.skip`", "converting `if (isNextDev) return` guards", "adding a condition to test/lib/gate/conditions.ts", "keying a fixture's experimental flag on a __NEXT_TEST_AXIS letter" — and every topic it claims ("directive choice, condition tiers, the test-axis fixture pattern, pitfalls, and verification commands") is verifiably present in the body. Comprehensive coverage with no gaps, so it fits the 5 anchor rather than 4.

Completeness

Explicitly answers "what" (how to use the @gate/@force-gate directives instead of skip patterns) with an explicit multi-clause "Use when…" listing four concrete trigger scenarios. The explicit 'Use when' clause is present with concrete trigger phrases, so this is the 5 anchor, not the 4 anchor where the 'when' could be more specific.

Trigger Term Quality

Contains the exact tokens a user needing this skill would naturally say: "it.skip", "describe.skip", "known-failing", "dev mode", "a bundler", "an experimental flag like cacheComponents", "__NEXT_TEST_AXIS", plus the directive names themselves. Coverage includes the literal API names and their synonyms ("fake-green skip patterns"), matching the comprehensive-coverage anchor rather than the few-terms-missing 4 anchor.

Distinctiveness Conflict Risk

Tied to a clear niche via distinct triggers — "`@gate` / `@force-gate` test directives", "test/lib/gate/conditions.ts", "__NEXT_TEST_AXIS" — that no generic testing or skip-related skill would share. Minimal conflict risk, matching the clear-niche 5 anchor rather than the minor-overlap 4 anchor.