KyaniteLabs

Production-readiness diagnostics and guided remediation for AI-built apps using CheckYourself. Use when the user asks for a pre-launch audit, production readiness score, evidence-backed findings register, safest first fix batch, learning plan, optional dashboard, or a read-only reality check before shipping a repository, app, website, agent, MCP server, or AI-generated project.

Use this capability whenever the user asks for a production-ready plan, full-stack review, hardening audit, launch checklist, architecture critique, or multi-layer implementation. Trigger even when the user only says “make it production ready”, “ship this”, “harden it”, “review this stack”, or “what am I missing”.

Use this capability when defining, refining, or reviewing a feature before implementation. Trigger on requirements, user stories, acceptance criteria, OpenAPI, AsyncAPI, JSON Schema, contracts, ADRs, RFCs, roadmap items, or “turn this idea into buildable work”.

Use this capability for UI architecture, frontend performance, accessibility, routing guards, forms, client state, design-system integration, browser security boundaries, and user-facing AI interfaces. Trigger on React, Vue, Angular, Svelte, components, UI, a11y, WCAG, Core Web Vitals, forms, routing, lazy loading, bundle size, hydration, or client errors.

Use this capability for REST, GraphQL, gRPC, webhooks, background jobs, service-layer design, middleware, validation, idempotency, pagination, API versioning, error handling, and backend business rules. Trigger on API, endpoint, controller, service, webhook, job, queue, validation, middleware, status code, OpenAPI, GraphQL, gRPC, or business logic.

Use this capability for database schema design, SQL/NoSQL selection, migrations, indexing, query review, connection pooling, backups, object storage, event storage, data retention, and data lifecycle planning. Trigger on database, schema, migration, index, SQL, PostgreSQL, MySQL, MongoDB, Redis, S3, ORM, transaction, backup, retention, or data model.

Use this capability for login, signup, session management, OAuth/OIDC, SSO, JWT, cookies, MFA, RBAC, ABAC, ReBAC, permission checks, service identities, and access reviews. Trigger on auth, login, signup, token, JWT, OAuth, OIDC, SSO, session, cookie, role, permission, MFA, 2FA, tenant access, or service account.

Use this capability whenever multi-tenancy, tenant isolation, Row-Level Security, shared-schema SaaS, organization-scoped data, tenant_id, database policies, cross-tenant access, or tenant-aware caching appears. Trigger even if the user only says “orgs”, “workspaces”, “teams”, “customers”, or “B2B SaaS”.

Imagery, illustration, and iconography direction for web UI. Use for hero images, photo treatment, illustration style, icon sets, favicons, OG/social cards, decorative graphics, image-shaped holes, and removing generic AI imagery.

OKLCH color-system guidance for cohesive palettes and contrast-safe tokens. Use when choosing colors, generating ramps, fixing muddy palettes, creating semantic state colors, checking WCAG contrast, or defining theme variables.

State matrix for interactive UI. Use when building or reviewing buttons, links, inputs, tabs, toggles, menus, cards, or controls that need hover, focus, active, disabled, loading, selected, error, keyboard, or ARIA states.

Honest, Tufte-informed web data visualization. Use for charts, dashboards, metrics, KPI tiles, sparklines, chart accessibility, chartjunk removal, genre choice, lie-factor checks, direct labels, data tables, and themed SVG/HTML.

Design-system interview before new frontend builds or redesigns. Use for vague site/app/landing/dashboard requests, generic-looking UI, direction-setting, aesthetic choices, type/color/density decisions, and DESIGN-SYSTEM.md tokens.

Empty, loading, and error-state design. Use for first-run screens, zero results, empty lists/tables/dashboards, loading skeletons, offline/permission errors, retries, layout stability, and state copy.

Form UX and accessibility pass. Use for forms, inputs, checkout, signup/login, validation, labels, autocomplete, mobile keyboards, inline errors, required fields, disabled submits, and field-level accessibility.

Humanize prose by removing LLM tells. Use for landing copy, docs, READMEs, emails, UI microcopy, release notes, social posts, or requests like humanize, less robotic, remove AI tells, punch up, or make this sound human.

Use Kinocut for guarded video editing, source-backed planning, FFmpeg operations, media analysis, subtitles, audio workflows, Hyperframes rendering, repurposing packages, and release checkpoints through an MCP server, Python client, or CLI. Trigger when an agent needs to inspect, plan, edit, render, validate, or package local media safely.

Use the current Kinocut tools to turn one local video path into a short platform-ready clip package with manifests, review artifacts, and human approval gates.

Compatibility skill for the former mcp-video name. Use Kinocut for guarded local video inspection, editing, rendering, and verification.

Review code for quality, security, and adherence to project conventions

Generate creative p5.js sketches by exploring a parameter space of visual seeds

Sample harness skill

Use Epoch for time estimation, business-day math, PERT/COCOMO/Monte Carlo forecasting, token cost comparison, schedule risk, and estimate-vs-actual feedback. Trigger when an agent needs realistic duration, deadline, model-cost, or planning calibration instead of a vibes-based guess.

Use DialectOS for Spanish dialect translation, localization QA, i18n locale-file validation, glossary enforcement, register/formality checks, gender-neutral language, and launch certification across regional Spanish variants through MCP or CLI.

Use OpenGlaze for ceramic glaze recipe analysis, UMF calculation, CTE estimation, batch scaling, material substitution research, and self-hosted pottery studio workflows. Trigger when an agent needs computational glaze chemistry help with real recipe strings.

Use Elixis for local-first pattern synthesis from source material into identity, brand voice, design-system direction, naming research, Source Corpus ingestion, and Market Kit outputs through CLI, HTTP API, or MCP tools.

Use Innerscape for personal-growth OS workflows: journaling, emotional check-ins, habits, goals, tasks, sleep logs, decluttering, capture inboxes, reviews, and gentle self-awareness planning. Trigger when an agent needs to help with reflective organization without overstepping into diagnosis or life automation.

Find the right public Kinocut installation, workflow, receipt, or safety documentation without touching media or running commands.