Conciseness

The ~90-line body contains zero explanations of concepts Claude already knows; every line instructs ('Never claim green from stale logs', 'bail on failure by default', 'Confirm cwd is the POSCursor repo root'). It matches the lean/every-token-earns-its-place anchor rather than the 4 anchor because no padding or over-explanation is trimmable.

Actionability

Commands are copy-paste ready and cover the common cases: full run ('node .agents/skills/systematic-test-matrix/scripts/run_matrix.mjs'), debug ('--skip-playwright --skip-smoke'), resume ('--only=playwright_full'), and collect-all-failures ('--no-bail'), plus concrete artifact paths (summary.json, jest-buckets.json, *.log, smoke.json). Fully executable with no gaps.

Workflow Clarity

The workflow is a fixed, numbered order (baseline → Jest buckets → integrated surfaces → export smoke) with explicit validation: 'bail on failure by default', the reporting rule 'Do not mark release-ready if summary.ok is false', and 'Open the newest summary.json and any failing *.log before reporting results'. Error recovery is covered (report step/exit code/log/first actionable error; --only resume). Although this is a batch operation, validation checkpoints are present, so the ≤3 cap does not apply; it is not a 4 because checkpoints and feedback loops are explicit rather than minor-gapped.

Progressive Disclosure

Scored against the actual bundle: the body is an overview, the surface catalog is properly split into references/test-surfaces.md (a real 90-line file, clearly signaled in both 'Agent reporting rules' and 'Related'), and execution detail lives in scripts/run_matrix.mjs (a real 351-line script referenced by path). References are one level deep with no nesting, matching the well-signaled clear-overview anchor.

Specificity

The description enumerates every concrete surface — 'tsc, expo-doctor, Jest buckets, full Jest, Playwright, web export, export smoke' — and specifies the evidence mechanism ('timestamped evidence under tmp/systematic-test-matrix/'), matching the comprehensive-coverage anchor. It is not a 4 because there are no gaps in the action coverage.

Completeness

It explicitly answers both: 'what' ('Run the full POSCursor verification matrix with timestamped evidence...') and 'when' ('Use for release readiness, pre-deploy QA, or when the user asks to systematically run all test surfaces'), with concrete trigger phrases and a negative boundary ('Not for authoring individual unit tests'). Not a 4 because the 'when' clause is fully explicit rather than vague.

Trigger Term Quality

Natural phrases like 'release readiness', 'pre-deploy QA', and 'systematically run all test surfaces' would plausibly be said by users, giving good keyword coverage. It falls short of 5 because common synonyms such as 'run the full test suite', 'is everything green', or 'pre-release check' are missing.

Distinctiveness Conflict Risk

It carves a clear niche (the full verification matrix for release confidence) and explicitly disambiguates the nearest neighbor: 'Not for authoring individual unit tests — use the testing skill for that'. Conflict risk is minimal, matching the clear-niche anchor rather than the minor-overlap anchor at 4.