LucaDominici

close-gold-gap

Use when the gold-audit reports an N/P gap (or a manual check) and you want the deterministic remediation recipe — scaffold/test/config/process — that closes it for a REAL reason, never by faking it.

Use when the user wants to measure how close the project is to gold-standard quality — runs the deterministic `arbiter audit readiness` engine and reports the level band plus a prioritized list of what is missing. Read-only; never changes code.

levelup

Use when the user wants to raise a governed project's gold level honestly — runs /gold-audit, composes a remediation wave that closes each gap for a REAL reason via /close-gold-gap, then re-audits with the no-regress ratchet + anti-fake-green guards. The level rises only by a real verdict flip; un-closeable gaps become needs-human, never faked.

refutation

Adversarial refutation-by-majority protocol (M13). Dispatch N independent read-only skeptics with an explicit REFUTE mandate per high-stakes finding; a finding survives only with a strict UPHELD majority. Persist skeptic verdicts as E1 agent-return envelopes and write the refutation-required marker so scripts/check-refutation-verdicts.mjs can adjudicate.

senior-survey

Use BEFORE creating any new file under src/. Guides grep + classify + decide protocol and emits a structured Survey block for the plan that the pre-edit hook can validate.

ssot-navigation

Use when starting any task to determine which arbiter SSOT documents to read and in what order.

visual-verification

Automated visual regression check via Playwright — 5 DOM checks × 3 viewports (375/768/1280). Produces pass/fail grid + screenshot paths under .arbiter/evidence/visual/.

wave-drain

Select ready compatible backlog work and deliver each capability train through the same result-first Ship contract.

tabletop

Use when the user wants a use case walked end to end the way a user lives it — narrate the journey as the persona, execute every read-only or dry-run step, compare what the docs promise against what actually happens, and record the disagreements as owned findings. Evidence only; never changes the repo.

product-acceptance

Use when a product is approaching completion and needs testing as a finished thing rather than as code — chartered sessions that drive the real product, find promises it does not keep, and produce evidence matrices plus remediation issues. Also use to decide WHICH sessions to run now and which to defer until after a planned rework. Complements code review and gates; never replaces them.

codebase-audit

Use when running a comprehensive codebase verification. Dispatches parallel agents across disjoint scopes to check invariant compliance, dead code, test coverage gaps, and naming consistency.

Code & Development Listed

clean-code

Gate-map for code quality — which gate mechanically enforces each limit (jscpd/knip/madge/complexity/ratchet). Use when reviewing code quality or before adding code that might duplicate or over-complicate.

Testing & QA Listed

tdd

Use when implementing any feature or bugfix. Red-Green-Refactor cycle enforced. Write the failing test first, then minimal implementation.

architect-review

Use when introducing new modules, adding external dependencies, or making structural changes that cross module boundaries. On-demand architecture review.

brainstorming

Structured brainstorming skill — explore solution space, produce design doc and GH issue, then STOP. No auto-implementation.

configure

Use when the user wants to change arbiter.json settings (governance level, feature flags, thresholds) without re-running the full wizard.

epic-decompose

Use when breaking down a large feature (epic) into independently deliverable tasks. Produces a sequenced task list with dependencies, acceptance criteria, and size estimates.

understand-code

Use when exploring an unfamiliar code path, tracing a feature end-to-end, or when asked "how does X work?". Structured 4-step comprehension protocol. READ-ONLY.