Query and write Supabase data with better-supabase's typed repositories, Results and codegen. Use when code imports better-supabase, when adding a table, query or mutation, when a Supabase type is out of date, or after upgrading better-supabase.
Build HTTP APIs, Edge Functions and MCP servers on Supabase with better-supabase adapters. Use when adding a route, REST resource, oRPC procedure, Edge Function, MCP tool, AI chat route, knowledge or memory, stored agent, MCP connector, eve agent, Chat SDK…
Implement, configure, and customize Streamdown — a streaming-optimized React Markdown renderer with syntax highlighting, Mermaid diagrams, math rendering, and CJK support. Use when working with Streamdown setup, configuration, plugins, styling, security, or…
CSV (RFC 4180): read and write comma-separated values files and the text/csv media type. Covers RFC 4180 Common Format and MIME Type for Comma-Separated Values (CSV) Files. Use when reading or writing CSV. Triggers: CSV, RFC 4180.
EN 16931: the semantic data model of the core elements of an electronic invoice. Covers EN 16931-1:2017+A1:2019. Use when mapping a core invoice. Triggers: EN 16931, e-invoicing.
GDPR: Regulation (EU) 2016/679 protects natural persons when personal data is processed. Covers Regulation (EU) 2016/679. Use when applying the General Data Protection Regulation. Triggers: GDPR, 2016/679.
iCalendar (RFC 5545): read and write calendar events, to-dos and recurrence rules, plus jCal and JSCalendar. Covers RFC 5545 Internet Calendaring and Scheduling Core Object Specification (iCalendar), RFC 7265 jCal: The JSON Format for iCalendar, RFC 8984…
JSON-RPC: JSON-RPC is a stateless, light-weight remote procedure call (RPC) protocol. Covers JSON-RPC 2.0. Use when calling procedures over JSON-RPC 2.0. Triggers: JSON-RPC, jsonrpc.
Evaluate LLMs on your own tasks against any OpenAI-compatible endpoint (local llama.cpp/Ollama, self-hosted vLLM/SGLang behind LiteLLM or llama-swap, or a cloud API). Use when choosing between models or endpoints, building a golden set from real prompts, A/B…
Metrics, tracing, logging, cost tracking and alerting for LLM serving and LLM apps. Use when instrumenting or debugging vLLM, SGLang, llama.cpp server, TGI or llama-swap /metrics endpoints; scraping them with Prometheus and building Grafana dashboards (TTFT,…
MCP Apps 2026-01-26: build and review interactive UI for MCP servers and hosts with the io.modelcontextprotocol/ui extension. Use when adding a ui:// HTML resource (text/html;profile=mcp-app) to an MCP tool, rendering MCP Apps views in a host, or reviewing…
OWASP API Security Top 10 2023: review HTTP, GraphQL and RPC APIs against API1:2023 to API10:2023, with upgrades from the legacy 2019 edition (no preview). Walks each risk's vulnerability checks, attack scenarios and prevention: broken object level…
OWASP ASVS 5.0.0: scope and verify security requirements from the OWASP Application Security Verification Standard by level, and cite them with versioned ids. Use when turning ASVS into security requirements for a web app or API, scoping an ASVS L1, L2 or L3…
OWASP LLM Top 10: review LLM-powered apps against the OWASP Top 10 for LLM Applications 2026 (LLM01:2026 to LLM10:2026, current), with the 2025 edition supported and v1.1 (2023) legacy; no preview. Use when designing, threat modelling or reviewing a chatbot,…
Peppol BIS Billing 3.0: send and validate Peppol invoices and credit notes based on EN 16931. Covers Peppol BIS Billing 3.0. Use when sending a Peppol invoice. Triggers: Peppol BIS.
Add vector search to PostgreSQL with pgvector, run beside a self-hosted LLM stack for RAG. Use for CREATE EXTENSION vector, pgvector/pgvector Docker images, vector/halfvec/bit/sparsevec columns, HNSW vs IVFFlat indexes, hnsw.ef_search, iterative scans,…
PostHog AI Observability (formerly LLM analytics): traces, cost, latency and evaluations built on $ai_generation events. Use to send traces from vLLM, llama.cpp, SGLang, Ollama or LiteLLM into PostHog, wrap OpenAI clients, export OTLP, set privacy_mode, price…
Push API: The Push API enables sending of a push message to a web application via a push service . Covers Push API (track). Use when subscribing to or delivering a web push message. Triggers: Push API, pushManager, RFC 8030.
Force LLM output to match a JSON schema, regex, choice list or grammar with guided decoding on vLLM, SGLang, TensorRT-LLM, llama.cpp, Ollama, TensorFold and ExLlamaV3/TabbyAPI. Per-engine flags and request shapes (response_format json_schema,…
IANA Time Zone Database: use tz identifiers and data correctly, as maintained under RFC 6557. Covers RFC 6557 Procedures for Maintaining the Time Zone Database. Use when using the IANA time zone database. Triggers: time zone, RFC 6557, tzdb.
UBL 2.4: exchange business documents such as orders and invoices in OASIS Universal Business Language XML. Covers UBL 2.4. Use when exchanging business documents. Triggers: UBL, Universal Business Language.
Operate Vercel AI Gateway (ai-gateway.vercel.sh), a hosted OpenAI-, Anthropic- and AI SDK-compatible endpoint with model fallbacks, provider routing, BYOK, budgets, logs and zero data retention. Use when the user mentions AI Gateway on Vercel,…
Web Cryptography API: This specification describes a JavaScript API for performing basic cryptographic operations in web applications, such as hashing, signature generation and verification, and encryption and decryption. Covers Web Cryptography API Level 1,…
Create a new repo or bring an existing one up to the ScaleDock standard (latest Node supported by Vercel, latest pnpm and TypeScript, Next.js or Expo, Supabase with better-supabase, PermDock, oRPC, MCP, CLI, Fumadocs, Vercel). Use when scaffolding a new…
WebMCP: expose web page tools to AI agents via document.modelContext, following the W3C Web Machine Learning Community Group draft (Draft Community Group Report, build posture), and upgrade code from the legacy navigator.modelContext drafts. Use when adding,…
Read and check the caller in better-supabase apps, including sessions, typed claims, user profiles, OAuth clients and agents acting for a user, scopes, ended sessions and authorization providers. Use when code reads auth, session or claims, when adding a…
Vercel AI Gateway guidance for setup, model discovery, authentication, routing, fallbacks, virtual models, evaluation models, BYOK, budgets, spend reporting, observability, compatible APIs, and coding-agent configuration. Use when adding AI Gateway to an app,…
Answer questions about the AI SDK and help build AI-powered features. Use when developers: (1) Ask about AI SDK functions like generateText, streamText, ToolLoopAgent, embed, or tools, (2) Want to build AI agents, chatbots, RAG systems, or text generation…
Test Supabase RLS policies, APIs and SQL against the local stack with better-supabase/testing, typed seeds and pgTAP. Use when writing or fixing tests that touch the database, policies, auth, OAuth or agent scopes, or Temporal time values.
ReUI design and component rules for React apps on shadcn/ui and Tailwind. Use for any UI work in a project with @reui in components.json or a components/reui folder, and in any shadcn project that asks for data grids, kanban boards, dashboards or full pages:…
EN 301 549: apply the European accessibility requirements for ICT products and services, including web, documents and software. Covers EN 301 549 V4.1.1, EN 301 549 V3.2.1 (supported). Use when applying European ICT accessibility requirements. Triggers: EN…
Section 508: apply the Revised 508 Standards for accessible ICT in US federal agencies. Covers Revised 508 Standards. Use when applying the Revised 508 Standards. Triggers: Section 508.
W3C WebAuthn Level 3: build and verify passkey registration and authentication for relying parties, following the § 7.1 and § 7.2 verification steps. Use when adding, reviewing or upgrading passkeys or security keys on a website or server:…
Audit and reduce Next.js browser initial-load work. Use for slow route startup, oversized client bundles, duplicate browser dependencies, or features that can wait for interaction.
RateLimit headers: advertise HTTP API quotas, handle 429 with the IETF RateLimit and RateLimit-Policy header fields (draft-11 of draft-ietf-httpapi-ratelimit-headers), Retry-After (RFC 9110) and 429 Too Many Requests (RFC 6585). Use when adding rate limiting…
Build or review a ScaleDock HTTP API that follows HTTP Semantics (RFC 9110, RFC 9111), OpenAPI 3.2, JSON Schema 2020-12, OpenAPI Overlay, RFC 9457 Problem Details, the RateLimit header fields and Standard Schema, with PermDock guarding every procedure and…
Build or harden a ScaleDock MCP server that follows the MCP base protocol and authorization spec, OAuth 2.1, JWT verification and Problem Details, with PermDock deciding every tool call. Use when adding an MCP surface, protecting MCP tools, wiring Protected…