Use this skill to gate Phoenix LiveView realtime UIs with a pass/fail adversarial review — two blind reviewer subagents judge a diff or file set against 32 decidable rules covering state ownership and lifecycle (patch vs remount, callback load placement, connected-mount guards, form recovery), realtime data flow (broadcast placement, scoped topics, presence mechanisms), async responsiveness (blocking external calls, socket-copying closures, lifecycle-owned tasks, rendered failure states), render and wire efficiency (the constructs that silently disable HEEx change tracking), streams (growing collections in assigns, the stream DOM contract, bounded infinite scroll), component and context boundaries, client trust (per-event authorization, scoped lookups, live_session boundaries, revocation disconnects), and mechanism-presence interaction feedback (JS commands, in-flight feedback, debounce, hook contracts, overlay focus). Verdicts only, never fixes.
Use this skill to gate Elixir/OTP systems on BEAM runtime architecture with a pass/fail adversarial review — two blind reviewer subagents judge a diff or file set against 23 decidable rules covering supervision and failure design (restart strategy vs child dependencies, blocking init, durability in terminate, restart amnesia, unsupervised fire-and-forget), backpressure (cast on externally-driven ingest, push pipelines without demand, silenced or retried call timeouts, unbounded fan-out), event delivery semantics (PubSub treated as durable, jobs enqueued outside the creating transaction, non-idempotent consumers under at-least-once delivery, cross-source ordering, telemetry handlers that block or detach), shared-state races (check-then-act on ETS/Registry, hot reads through one mailbox, persistent_term churn), distribution (global singletons in netsplits, node-local uniqueness assumed cluster-wide), and runtime mechanics (wall-clock durations, sub-binary leaks, minted atoms). Verdicts only, never fixes.
Use this skill to gate Elixir, OTP, Ecto, and Phoenix code with a pass/fail adversarial review — two blind reviewer subagents independently judge a diff or file set against 19 decidable rules that catch architecture ported from an alien paradigm, covering enterprise layering (repository wrappers over Ecto, service-object tiers, DI behaviours with a single implementation, logic trapped in effectful callbacks), processes as objects (GenServer-per-entity, Agents as mutable variables, leaked message protocols, singleton managers), anemic data (bare maps as entities, boolean-flag state, hand-rolled type dispatch, 32+-field structs), defensive control flow (raise/rescue as branching, nil-guard swallowing, raw input past the boundary), transliterated loops, and needless metaprogramming (macro DSLs for data, use-as-import, compile-time coupling). Trigger it before merging Elixir work, or to check agent-authored code. It renders verdicts only, never fixes; Ecto-dependent rules go N/A without Ecto.
Use this skill to gate Swift and SwiftUI code with a pass/fail adversarial review — two blind reviewer subagents independently judge a diff or file set against 44 decidable rules distilled from expert Swift and SwiftUI reference material, covering SwiftUI state and observation (@Observable over ObservableObject, @State ownership), view identity (applyIf-style branching, AnyLayout), view update cost (init side effects, body derivations), task lifecycle (.task over onAppear+Task), lists and geometry (AnyView rows, GeometryReader measurement), accessibility (icon-only buttons, semantic styling), Swift concurrency (unresumed continuations, retain cycles, cancellation, serialized awaits, main-actor CPU work), and API and type design (@unknown default, CaseIterable, private(set), rethrows). Trigger it before merging Swift or SwiftUI work, or to check agent-authored code. It renders verdicts only, never fixes; SwiftUI categories go N/A on non-UI Swift.
Adversarial pass/fail review gate that enforces the feature-arch skill's React feature-based architecture rules. Use when a diff, branch, PR, or src/ tree must be judged for architecture conformance before merge — feature folder structure, import boundaries, cross-feature isolation, data-fetching, state, testing, and naming rules. Two blind reviewers independently render per-rule PASS/FAIL verdicts with cited evidence and the verdict merges fail-closed. Use the feature-arch skill itself to design or migrate an architecture; use this gate to judge whether work conforms to it.
Use this skill to gate TypeScript and React application code with a pass/fail adversarial review of design-pattern usage — two blind reviewer subagents independently judge a diff or file set against 18 decidable rules covering implicit state machines (boolean-flag lifecycles, useEffect chains, stored derived state, non-exhaustive union matches) and over-engineered OO/enterprise ports (getInstance singletons, factory and builder classes, single-method strategy classes, State/Visitor hierarchies, event buses inside a React tree, pass-through repositories, DI containers, single-implementation interfaces, component inheritance, logic-only HOCs, static-only classes, trivial accessors). Trigger it before merging TS/React work, when asked to gate or pass/fail pattern usage, or as a check that agent-authored code is not porting Java/C# idioms. It renders verdicts only; for teaching-style guidance use implementation-design-patterns or implementation-functional-patterns.
Use this skill to gate Zod 4 schema code in TypeScript and TanStack Start apps with a pass/fail adversarial review — two blind reviewer subagents independently judge a diff or file set against 24 decidable rules covering silent Zod 3-to-4 semantic breaks (defaults, enum-keyed records, boolean coercion), removed APIs (including the z.interface hallucination), unified error customization, deprecated method forms, recursion and codec composition, adapter-free TanStack Start validators, and packaging. Trigger it before merging Zod schema work, when asked to gate, adversarially review, or pass/fail Zod usage, or as a currency check that agent-authored schemas use the latest Zod 4.x surface. It renders verdicts only and never fixes the work; for teaching-style Zod feedback use the curated zod skill instead.
Use this skill when reviewing or refactoring existing Rust code that carries an alien mental model — OO/enterprise ceremony from Java/C#, garbage-collected object graphs, exception-style control flow, or imperative loops ported onto the borrow checker. It is the adversarial, architecture-level counterpart to greenfield idiom advice — it names the paradigm the code betrays and prescribes the deep refactor that collapses it, up to deleting whole layers (single-impl DI traits, Deref inheritance, Manager/Service structs, reflexive builders, Rc<RefCell> webs, clone-until-it-compiles, bool/String state machines, sentinel returns, catch_unwind try/catch, reflexive Box<dyn>, blocking calls inside async, fire-and-forget spawns). Every rule is grounded in the codex-rs production workspace (openai/codex) — the prescriptions are what that codebase actually does and lint-enforces. Applies whenever the work is "make this Rust actually Rust", "flatten this architecture", or a pedantic review of code fighting the language.