ScaleDockHQ

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…

Start with what the skill does, because the install picker shows only the first 57 characters. Then say when an agent should use it, with the trigger phrases or situations (for example "Use when working on X, or when the user asks to Y").

Global Privacy Control (GPC) WD 2026-09-24: honor, send and detect the W3C Sec-GPC: 1 do-not-sell-or-share signal, navigator.globalPrivacyControl and the /.well-known/gpc.json support resource. Targets GPC Working Draft 2026-09-24 (posture build; the Editor's…

Agent Network Protocol (ANP) 1.2: identify, authenticate, describe, discover and negotiate with agents using the community ANP specifications (track posture): did:wba DIDs with e1_ Ed25519 key-fingerprint paths, eddsa-jcs-2022 DID Document proofs, key…

Open Agentic Schema Framework (OASF): describe AI agents, their skills and domains in standard records. Covers OASF 1.1.0, OASF 1.2 (track preview). Use when describing agent capabilities with OASF. Triggers: OASF.

IETF aipref AI usage preferences: publish and read Content-Usage statements (train-ai, ai-use, search) in the HTTP Content-Usage header and the robots.txt Content-Usage rule, following draft-ietf-aipref-vocab-08 and draft-ietf-aipref-attach-05 (working group…

DNS-AID (DNS for AI Discovery): publish and discover AI agents in DNS with SVCB records, following draft-mozleywilliams-dnsop-dnsaid-02 (individual Internet-Draft for dnsop, name posture): an agent SVCB RRset at its primary owner name, one record per agent…

Machine Payments Protocol (MPP): add and consume HTTP 402 payments with the "Payment" HTTP authentication scheme of draft-httpauth-payment-01 (individual Internet-Draft, build posture): WWW-Authenticate Payment challenges with id, realm, method, intent and…

Install and operate AIBrix v0.7.0 on Kubernetes, the vLLM project's control plane for LLM serving, with an Envoy gateway and LLM-aware routing, PodAutoscaler, LoRA ModelAdapter, StormService prefill/decode and multi-node, and KVCache offload. Use for…

Aider, the terminal AI pair-programming tool (aider-chat, `aider`), pointed at self-hosted or gateway models through LiteLLM-style model names. Use to install or upgrade aider, set OPENAI_API_BASE with the `openai/` prefix, `ollama_chat/` or…

Set up, verify and operate AMD Instinct GPUs (MI300X, MI325X, MI350X, MI355X, MI250, MI210) with ROCm 10.x for LLM inference. Use for amdgpu driver and ROCm install, gfx942/gfx950 targets, /dev/kfd and render group errors, amd-smi (rocm-smi removed),…

Set up, size and operate AMD Ryzen AI Max (Strix Halo, gfx1151, Radeon 8060S, up to 128 GB unified memory) for local LLM inference on Linux or Windows. Use for GTT/TTM unified-memory limits (ttm.pages_limit, amdgpu.gttsize, amd-ttm), BIOS UMA carveout, Vulkan…

Use the Claude API directly (api.anthropic.com) - keys, workspaces, Messages API, OpenAI SDK compatibility, streaming, tools, structured outputs, Message Batches, prompt caching, Files, rate-limit tiers, spend limits, ZDR, key revocation. Use for…

Anthropic Python and TypeScript SDKs pointed at self-hosted endpoints. Use to set base_url/baseURL, ANTHROPIC_AUTH_TOKEN vs ANTHROPIC_API_KEY for vLLM, llama.cpp, Ollama, LiteLLM or llama-swap Messages routes, map model names, stream, call tools, or fix 404…

AnythingLLM, all-in-one chat and RAG app with workspaces, agents and MCP (Desktop or Docker). Use to point it at vLLM, llama.cpp, Ollama, LiteLLM or llama-swap with the Generic OpenAI, Ollama or LiteLLM provider, keep keys in the server .env, set context…

Install, serve and tune Aphrodite Engine (now branded Sonar), the vLLM-derived LLM inference server with OpenAI, Anthropic and Kobold APIs. Use for the aphrodite CLI, aphrodite serve, aphrodite-engine pip package, sonar.dphn.ai, port 2242, quantization (exl3,…

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…

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…

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…

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.

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,…

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,…

Vercel environment variable expert guidance. Use when working with .env files, vercel env commands, Secret or Config variable types, OIDC tokens, or managing environment-specific configuration.

Adds PermDock authorization to a TypeScript app, from definitions to the first guard. Use when installing permdock, adding permissions, roles, plans, RBAC or access control, writing definePermissions, definePolicy or createPermDock, guarding a route, Server…

Resolves PermDock subjects from access tokens, API keys and share links. Use when verifying OAuth or OIDC access tokens with subjectFromJwt or an introspection response with subjectFromIntrospection, issuing personal access tokens, API keys, service accounts…

Enforces PermDock permissions in database queries and Postgres row-level security. Use when listing rows with permdock.where() and filter(), compiling conditions with toWhere from permdock/drizzle, permdock/prisma or permdock/kysely, guarding Convex functions…

Models tenants, memberships, contacts and support sessions in PermDock. Use when declaring named scopes (organizations, workspaces, customers inside an organization), loading memberships through a MembershipSource, putting a role on one scope, keeping an…

Use when working in a project that depends on @prisma/orm-postgres, @prisma/orm-sqlite, or @prisma/orm-mongo (Prisma 8, formerly Prisma Next): editing contract.prisma or a contract.ts builder, running `prisma contract emit`, planning or applying migrations,…

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…

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…

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.

Run and consume LLMs in the cloud - pick a tier, provision, deploy, connect to one gateway endpoint, secure, set budgets, benchmark, scale, update and tear down. Covers frontier APIs (OpenAI, Anthropic Claude, Google Gemini), managed open-model APIs (Together…

Fine-tune open-weight LLMs locally (NVIDIA DGX Spark unified memory, consumer RTX GPUs) or on rented cloud GPUs. Covers deciding whether to fine-tune vs prompting or RAG, dataset prep (chat templates, messages JSONL, ShareGPT/Alpaca, preference pairs, dedup,…

Connect coding agents, IDE extensions, chat UIs and SDK apps to any OpenAI- or Anthropic-compatible LLM endpoint (local engine, self-hosted server, gateway such as LiteLLM, or cloud API). Use when configuring Claude Code (ANTHROPIC_BASE_URL,…

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…

Put one OpenAI- and Anthropic-compatible endpoint in front of many local and cloud LLM providers. Use when choosing an LLM gateway (LiteLLM proxy, OpenRouter, Portkey, Envoy AI Gateway / Agent Router, Kong AI Gateway, Cloudflare AI Gateway), installing the…

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,…

Run LLMs locally on a laptop or desktop (macOS, Windows, Linux) with Ollama, LM Studio, llama.cpp (llama-server) or MLX (mlx-lm). Use when the user wants to install a local runtime, pick and size a model or GGUF/MLX quant for their RAM or VRAM (weights + KV…

Produce quantized LLM checkpoints and publish them. Covers GGUF (llama.cpp convert_hf_to_gguf.py, llama-quantize, llama-imatrix; Q4_K_M, Q8_0, IQ4_XS), EXL3 (ExLlamaV3 convert.py, TabbyAPI), AWQ / GPTQ / FP8 / NVFP4 with LLM Compressor (oneshot,…