layers

Alpine.js adapter for @stainless-code/alpine-layers; plugin magics, x-layer-outlet, layerStack data, and JS hooks for typed layer stacks

Angular adapter for @stainless-code/angular-layers (signals + DI + imperative renderStack); use when wiring provideLayerClient, renderStack/useStackHandles, useLayerGroup, useMutationFlow, or createStackHook

UI-agnostic layer stack engine for @stainless-code/layers. Use for opening layers imperatively from anywhere, ordered named stacks, typed await or fire-and-forget calls, lifecycle control, blockers, validation, singleton updates, serial or nested layers, multi-stack orchestration, or building a library/framework adapter.

Lit adapter for @stainless-code/lit-layers; open UI from anywhere and manage ordered, named stacks with typed or fire-and-forget `open` via Reactive Controllers and custom elements

Preact adapter for @stainless-code/preact-layers — use for awaitable confirm flows, singleton toasts, nested drawers, stack subscriptions, and custom layer hosts

React adapter for @stainless-code/react-layers; open UI from anywhere and manage ordered, named stacks with typed or fire-and-forget `open`

SolidJS adapter for @stainless-code/solid-layers; open UI from anywhere and manage ordered, named stacks with typed or fire-and-forget `open`

Svelte bindings for @stainless-code/svelte-layers (runes + stores). Use to open overlay UI imperatively from anywhere, manage ordered named stacks, choose the Svelte 5.7+ runes or Svelte 3+ stores entry, and wire layer context or stack outlets.

Vue adapter for @stainless-code/vue-layers; open UI from anywhere and manage ordered, named stacks with typed or fire-and-forget `open`

Bring a branch to pristine, maximum production readiness without changing PR intent — spawn parallel Task subagents (never inline review), fix in-bounds findings, loop autonomously until clean or pass cap, then report once. Use after a tracer-bullet commit (lite), before PR is done (full), on "harden", "harden-pr", "pristine", "review until clean", or "production-ready pass". Invoking this skill authorizes one harden commit at cycle end.

Which user-only agent workflow to run — grilling, docs-aware grilling, teach, or meta authoring help.

minimum-diff — change only what was requested; recommend before implementing when asked.

Layers repo hybrid deltas for .agents/ — tiers, rule-skill pairing, repo exemplars. Use when creating or reviewing rules/skills in this repo. Read writing-great-skills first for skill vocabulary and authoring principles.

Repo-wide docs lifecycle — plans, audits, research, README surfaces. Use when authoring or editing any docs/**, README, or other doc-bearing folder.

Keep apps/docs in sync with merged product changes. On each run, audit recently merged PRs against docs content, update only drifted pages, verify with blume build, and open or update a blume/* PR — or report a clean no-op.

Voice, tone, and format for the public Layers docs (`apps/docs`, built with Blume). Use when authoring or editing apps/docs prose — landing, guides, concepts, adapters, reference — or deciding headline grammar, benefit framing, the experimental disclaimer wording, or overlay-vs-layer usage.

Architectural exploration — seam decisions, core/adapter isolation, zero-dep core gate. Plan under docs/plans/. Use when improving architecture, consolidating modules, or enforcing import boundaries.

The product north-star — four tenets (open & agnostic, composable primitives, production-grade, predictable & type-safe) distilled from TanStack's ethos/tenets. Use when making a design, API, or architecture decision, evaluating a trade-off, justifying a feature, or writing/reviewing a docs/plans entry.

Full tier assignments, pairing conventions, and authoring checklist for .agents/ rules and skills. Use when creating or reviewing a rule or skill, deciding Tier 1 vs 2 vs 3, or auditing attachment cost.

Prose depth for comments, JSDoc, and docs — concise comments, no brittle anchors, preserve existing source comments.

Diagnose hard bugs and regressions. Use when the user says diagnose or debug this, or reports something broken, throwing, failing, or slow.

Docs lifecycle sweep — Tier-B classification with evidence for stale docs. Use when the user wants a docs lifecycle sweep / janitor pass, or to promote/lift/retire a specific doc.

Build and sharpen the project's domain terminology inline or via a batch glossary scan. Use when pinning down ubiquitous language, recording a domain decision, grill-with-docs crystallises a term, or refreshing docs/glossary.md.

A relentless interview to sharpen a plan or design before coding.

Grill a plan or design and update repo docs as decisions crystallise. Invokes grilling + domain-modeling inline.

Relentlessly grill plans until shared understanding. Use when stress-testing a design or another skill delegates grilling.

STOP and fact-check PR review comments before applying or dismissing reviewer or bot feedback. Use on CodeRabbit, Copilot, Cursor bot, dependabot, or human reviewer comments.

Test-driven development with vertical tracer-bullet slices. Use when the user wants TDD or red-green-refactor on a vertical slice.

Structured multi-session teaching — missions, lessons, retrieval practice.

Per-file verification checklist — lint-staged and package.json scripts after each milestone.