Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility", "a11y audit", "WCAG compliance", "screen reader support", "keyboard navigation", or "make accessible".
Use this skill when designing, generating an MVP blueprint for, auditing, refactoring, or explaining an agentic harness for any domain. Covers provider-neutral agent architecture for OpenAI, Anthropic, and OpenAI-compatible APIs: agent loops, tool design, permissions, system prompts, planning, goals, context…
Use when running a structured closeout code review for local changes, branch diffs, commit diffs, final QA after non-trivial edits, second-model review, or an explicit autoreview request. Provides the project-local .agents/skills/autoreview/scripts/autoreview helper for bundle-driven advisory review.
Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.
Use when planning, implementing, or reviewing a browser 3D/game runtime surface inside Universo published applications, especially PlayCanvas canvas widgets, Colyseus realtime clients, game HUDs, lazy-loaded engine widgets, input ownership, game loops, cleanup, or Playwright proof in apps-template-mui. Requires the…
Use when planning, implementing, or QA-reviewing MMOOMM realtime multiplayer with Colyseus rooms, server-authoritative simulation, room authentication, Schema state, fixed tick processing, client interpolation or reconciliation, reconnection, or MVP scaling. Applies to @universo-react/colyseus-server wrapping…
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library.
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. For systems venues (OSDI, NSDI, ASPLOS, SOSP), use systems-paper-writing instead.
Use when planning, implementing, or reviewing MUI runtime screens, apps-template MUI dashboards, metahub template metadata, CRUD dialogs, DataGrid/table/card displays, relation builders, resource-source fields, or UI E2E flows. Enforces user-friendly runtime UI contracts: no raw user-facing IDs, no raw JSON/object…
Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best practices. Use when creating Node.js servers, REST APIs, GraphQL backends, or microservices architectures.
Build production-ready Express.js servers with middleware, authentication, routing, and database integration. Use when creating REST APIs, managing requests/responses, implementing middleware chains, and handling server logic.
Universo-specific complement to the OntoIndex code-intelligence tool. Use alongside the generated .claude/skills/ontoindex/ skills when querying the code graph in this monorepo. Adds the three things those generated skills do NOT cover — the namespace-collision caveat (this is code intelligence over source, NOT…
Use when working with the PlayCanvas Editor API, realtime sync protocols, WebSocket endpoints, ShareDB, Operational Transformation (OT), or document collections.
Use when working with the PlayCanvas Editor asset import pipeline, texture conversion, model ingestion, audio files, materials, or asset metadata attributes.
Use when planning, implementing, or reviewing work that touches PlayCanvas Editor authoring, the Editor/Engine boundary, vendored upstream artifacts, Editor boot contract, or Editor package routing. Applies to @universo-react/playcanvas-editor-frontend vendoring playcanvas/editor v2.30.4 with [email protected]; does…
Use when working with the PlayCanvas Editor interface panels, inspectors, toolbar actions, layout configurations, PCUI components, viewport settings, or keyboard shortcuts.
Use when working with the PlayCanvas Editor scene graph, Entity Component System (ECS), entity hierarchy, templates, prefabs, or scene setting configurations.
★not rated 22 2d agoA36 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: