Kind: skill

Use when you need to implement TTS (text-to-speech) or STT (speech-to-text) integrations in Nuxt 3/Nitro applications, including Deepgram streaming STT via WebSocket, ElevenLabs TTS, browser MediaRecorder, and audio settings management. Expert-level programming and pattern management.

Use when you need to implement a typst template from an image or pdf reference iteratively. Expert-level programming and pattern management.

Use when you need to implement UnaUI (@una-ui/nuxt) in Nuxt 3/4 — N* component usage, color tokens, slot patterns, UnoCSS-driven theming, and UnaUI module configuration.

Use when you need to implement or configure UnoCSS in Nuxt 3/4 projects — presets (wind4, icons, attributify, typography), uno.config.ts theming, dark mode, safelist, layers, and UnoCSS module integration.

Use when you need to implement VueUse composables in Nuxt 3, including auto-import configuration, composable selection, conflict handling with Nuxt built-ins, and reactive browser/state/DOM utilities. Expert-level programming and pattern management.

Create, review, or update a design spec / proposal for new features, architectural changes, or cross-package work in the skaile-dev monorepo. Use when work is too complex to jump straight into code — the spec captures the problem, design, alternatives, and approval status before implementation begins.

Use when an app is built or adopted and you suspect its design, not its conformance, is what hurts users — scans the code against the rulebook, the glossary and APP-DESIGN.md for shallow screens, overloaded concepts, hidden modes, undeclared representations and tier violations, reports evidenced candidates, then grills the one you pick. Triggers on 'what is wrong with this design', 'find design problems', 'which screens should merge', 'improve the UX of this app', 'design review of the code'.

Use when the app runs and its journeys need proving end to end in a real browser — drives every story from stories.yaml with agent-browser, screenshots each step, checks the database behind it, and writes each journey's verdict into the acceptance-criteria ledger. Triggers on 'test the app', 'e2e tests', 'browser testing', 'walk the journeys'.

Use when an app's code exists — checks it against the interaction decisions in APP-DESIGN.md entry by entry and type by type (against the rulebook's invariants alone when none is written), counts violations and exemplars per rule, and writes the ordered changes that close them. Triggers on 'check the app against APP-DESIGN.md', 'does the UI follow our patterns', 'interaction review', 'where do we still break the rules'.

Use as the last gate before a release — walks the whole running application against the brief and goals it started from and grades it on seven axes, then writes the release verdict. Triggers on 'is this ready to release', 'grade the app', 'final gate', 'release review'.

Use when a feature's slices are frozen and its code needs an adversarial review before it ships — resolves the fixed point from the trace and the spec from the feature file, runs `code-review`, and adds the security, accessibility and acceptance-criteria axes. Triggers on 'review this feature', 'code review the login feature', 'is this ready to ship'.

Use when work is starting against an existing codebase and its conventions have not been written down — scans the code for the patterns it already follows and records them as standards the build skills read. Triggers on 'discover standards', 'what conventions does this codebase use', 'analyse the codebase'.

Use when built features need a test suite that traces back to their specs — learns the project's test conventions from its existing tests, then writes unit tests and, where there is a data layer, integration tests. Triggers on 'generate tests', 'add test coverage', 'write integration tests'.

[skaile-development] Umbrella quality-gate orchestrator for the skaile-dev monorepo. Runs typecheck → test (with coverage + ratchet when the mode requires it) → audit → doc-audit → ready in sequence, early-outing on the first hard failure. Produces a consolidated health snapshot that contributors look at before opening a PR and release uses as its pre-flight check. Supports quick (diff-scoped), package (one package deep), and full (whole monorepo, mirrors test-full.yml CI lane) modes.

Pre-release readiness gate for the skaile-dev monorepo. Verifies every package has README + CLAUDE.md with required sections, tests passing, build clean, typecheck clean, CHANGELOG present, and Starlight registration for packages with docs/. Produces a blocker/warning table and exits non-zero on any hard failure. Called by release as Phase 0.

Changelog management, semantic versioning, and git tagging for skaile-dev domains and packages. Three modes: status (show current version + unreleased changes), bump (update version + CHANGELOG.md), tag (create annotated git tag).

Write or rewrite technical prose in ASD-STE100 Simplified Technical English: one statement per sentence, active voice, fixed terms. Use for report prose, 'STE', 'simplified English', 'make this unambiguous'.

Quantities as `bars` or Vega-Lite `vega` charts with tooltips, selections and cross-filter. Use for 'how much', 'distribution', 'over time', 'compare counts'.

Dependency `map` canvases, `board` moodboards (screens today vs. proposed, changes marked) `concepts` figures (UI variants per state with their linked terms), `mock` dialogs and mermaid notations (sequence, class, ER, C4, gantt, mindmap, sankey, railroad) with the notation-choice table. Use for 'what depends on what', 'who calls whom in which order', 'moodboard', 'before/after of screens', 'which UI variant', 'how do these terms relate', 'draw this as a diagram'.

Capture how code or a pipeline works from the source (trigger, steps, stores, error paths, file:line evidence) and draw levelled DFD `flow`, `lineage` and `states` diagrams. Use for 'how does X work', 'what becomes what', 'which states'.

Write report prose people read front to back: an argued answer (claim, reason, consequence), the reader's words before code names, few links, lists only after a lead sentence, examples and contrasts where they explain. Use for report prose, 'make this readable', 'too technical', 'rewrite for people'.

Dump collections, detect keys/relations/enums with detect.py, and render entities as badge-filtered trees and interactive sortable/searchable tables. Use for inventories, 'which X exist', 'how many', data sheets.

Chaptered, narrated manim explainer of a report's main concepts with a brand look, embedded as a `video` block with captions and chapters. Use only when the user asks for a video, animation or explainer.

Build one static HTML report read front to back: argued answer first, tables, trees, diagrams and charts as support. Use for 'report', 'overview page', 'data sheet', 'how does X work as a page'. Autopilot by default; 'report interactive: <question>' asks first; a pasted '# Notes on report' block revises it.