The actionable workflow is efficient, but the Overview ('A flaky test is a test that produces inconsistent pass/fail results across runs without an underlying code change') and the 'Terminology note' / ISTQB-provenance and 'Industry consensus' rationale restate concepts Claude already knows, fitting 'mostly efficient but includes some unnecessary explanation' rather than the lean 3 anchor.

Fully executable examples across frameworks — Playwright test.fixme(), playwright.config.ts retries, Cypress config, Jest/JUnit annotations — plus a parseable annotation-format table and a worked example, with the report script and CI workflow supplied in the bundle. Not 2 because code is real and copy-paste ready, not pseudocode.

A clear 6-step 'How to use' sequence maps to numbered Step sections, with an explicit entry-validation gate ('Confirm it is a flake, not a regression' via the 1–50% rate) and prune-time verification ('re-run the test at depth to confirm it is green'), satisfying the validation-checkpoint anchor despite destructive delete/prune outcomes.

The body is a focused overview that offloads the heavy CI automation to a single clearly-signaled, one-level-deep reference (references/ci-quarantine-report.md), which exists as a real file containing the actual script and workflow rather than further nested pointers.

Lists multiple concrete actions — 'marks the test with the framework's skip/fixme/retry annotation', 'records the failure-rate observation and a bisect link', 'sets an auto-expiry date', 'produces a CI report listing every quarantined test that has expired' — matching the multi-action anchor rather than the single-domain anchor at 2.

Explicitly answers both what (builds the quarantine workflow: mark/annotate/expiry/report) and when ('Use when a flaky test is blocking the trunk and must be removed from the gating path'), matching the 'clearly answers both what AND when with explicit triggers' anchor.

Natural terms a user would actually say appear prominently — 'flaky test', 'blocking the trunk', 'gating path' — with 'flaky test' as the core term repeated in the trigger clause. Not down to 2 because the dominant user phrasing is present rather than missing common variations.

Occupies a clear niche (flaky-test quarantine) with distinct triggers tied to flakiness and trunk-blocking, making it unlikely to fire for unrelated skills. Not 2 because the trigger is specific rather than broadly overlapping.