Neon Drizzle Stinger logo

Neon Drizzle Stinger

Organization
legioncodeinc
neon-drizzle-stinger

Neon Postgres and Drizzle ORM on SvelteKit/Vercel: connections, schema, migrations, branching, query patterns, pgvector, RLS, and migrating off Supabase. Use for any Neon or Drizzle task.

Overview

Publisherlegioncodeinc
Repositoryvibe-coding-tools
Skill nameneon-drizzle-stinger
Stars
94
Forks
44
Bundled files
14
LicenseAGPL-3.0-or-later
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 14 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by legioncodeinc on GitHub. Read the source before you install it.

Installation

Install the Neon Drizzle Stinger AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/legioncodeinc/vibe-coding-tools/tree/main/plugins/data-and-ai-tools/skills/neon-drizzle-stinger
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/legioncodeinc/vibe-coding-tools.git /tmp/vibe-coding-tools
mkdir -p .claude/skills
cp -r /tmp/vibe-coding-tools/plugins/data-and-ai-tools/skills/neon-drizzle-stinger .claude/skills/neon-drizzle-stinger
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Neon Drizzle Stinger in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Neon Drizzle Stinger on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Neon Drizzle Stinger is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Neon Drizzle Stinger

You are equipping neon-drizzle-wasp-drone for a stack migrating off Supabase onto Neon Postgres with Drizzle ORM, on SvelteKit (Svelte 5) deployed to Vercel. Migration guidance carries equal weight with greenfield guidance here, this skill assumes an existing Supabase app as often as it assumes a blank slate.

Every fact in this skill traces to the source research archive (not shipped; the shipped distillation summarizes it), fetched 2026-08-14. Where the research is thin or conflicting, the distillation says so plainly. Do not extend a claim past what its citation supports.

When to use this skill

  • Choosing or wiring a Neon connection string, driver, or pooling strategy, especially "which driver on Vercel"
  • Designing a Drizzle schema, relations, or an index strategy against Neon
  • Running or reviewing a Drizzle Kit migration (generate/migrate/push), or setting up Neon's branch-per-PR CI workflow
  • Building RAG/AI features with pgvector on Neon
  • Deciding whether Row Level Security is needed, or enforcing authorization in SvelteKit server code instead
  • Migrating an existing Supabase app's database, auth, and RLS policies to Neon, Drizzle, and WorkOS
  • Diagnosing a connection-cap error, an unexpected Neon bill, or a cold-start latency complaint

When not to use this skill

  • Generic Postgres schema/indexing/partitioning theory not specific to Neon or Drizzle, that's db-stinger, which this skill's migration guide (03) explicitly defers to for expand-backfill-contract mechanics
  • WorkOS/AuthKit implementation depth beyond the database-migration touchpoints in guide 06, that's workos-stinger and auth-stinger
  • Svelte component architecture, routing, or UI concerns unrelated to the data layer, that's website-stinger
  • Security audit of RLS/PII/encryption-at-rest as a formal review, that's security-stinger; this skill designs the authorization approach, that skill audits it

Procedure

  1. Classify the task: greenfield Neon+Drizzle setup, ongoing schema/migration work, a Supabase-to-Neon migration, or a performance/cost investigation. Each routes to a different guide below.
  2. Read the inputs first: existing schema.ts/relations.ts, drizzle.config.ts, the SvelteKit db client module, package.json for Drizzle/Neon package versions, and (for a migration) the Supabase project's current schema and RLS policies. Never assume the stack's shape, read it.
  3. Pick the connection pattern before writing any code. Walk guides/01-connection-and-drivers.md and references/connection-pattern-decision-matrix.md, pooled vs direct, and which driver on which runtime, are two separate decisions and the most common source of a wrong answer here.
  4. For schema and relations, walk guides/02-schema-design-with-drizzle.md and start from references/schema-example.ts.
  5. For any migration, walk guides/03-migrations-and-branching.md. Never approve drizzle-kit push (especially --force) against a database holding real data, that is a Ship Gate finding, not a style note.
  6. For queries, walk guides/04-query-patterns.md.
  7. For SvelteKit/Vercel wiring, walk guides/05-sveltekit-vercel-integration.md and references/sveltekit-db-singleton.md, the database client is server-only code, always.
  8. For a Supabase migration, walk guides/06-supabase-migration.md and references/supabase-to-neon-translation-table.md in full before touching production data. Flag explicitly to the user that Storage and Realtime have no Neon-native replacement, do not let that gap go unstated.
  9. For authorization, walk guides/07-authorization-without-rls.md before assuming RLS is required, it is only mandatory if the app adopts Neon's Data API for client-side queries.
  10. For cost, limits, or a production connection failure, walk guides/08-performance-and-cost.md.

References map

  • references/research/distilled-neon-drizzle.md, load when a claim needs its citation traced, or a conflict/gap needs checking before you state something as fact
  • Source research archive (not shipped with the plugin): the shipped distillation summarizes it; do not require it.
  • references/schema-example.ts, load when scaffolding a new table set
  • references/migration-workflow-commands.md, load when running or explaining any drizzle-kit command
  • references/connection-pattern-decision-matrix.md, load when choosing a driver/pooling strategy for a specific route
  • references/sveltekit-db-singleton.md, load when placing or reviewing the db client module in a SvelteKit app
  • references/supabase-to-neon-translation-table.md, load when planning or executing a Supabase-to-Neon cutover

Related drones and stingers

  • db-wasp-drone - Postgres-first architecture engineer; hand off generic schema/indexing/partitioning/pooling theory not specific to Neon or Drizzle.
  • db-stinger - Provider-agnostic Postgres architecture: expand-backfill-contract mechanics, lock classes, indexing decision trees. This skill's migration guide cites it directly rather than re-deriving locking theory.
  • website-stinger - SvelteKit/Svelte 5 application concerns beyond the data layer: routing, components, UI state.
  • workos-stinger - Deeper WorkOS/AuthKit implementation guidance beyond the database-migration touchpoints covered in guide 06.
  • security-stinger - Formal audit of RLS policies, PII handling, and encryption-at-rest; this skill designs the authorization approach, that skill audits it.

Critical Directive

  • You must read all files and context contained within your skill.
  • In the event your core knowledge does not provide sufficient guidance you must make every attempt to search the internet, related knowledge base documentation files, and other available resources to supplement your knowledge prior to proceeding with your task.
  • Additional related skills can be found here:
    • db-stinger - Provider-agnostic Postgres architecture and migration-safety mechanics this skill builds on.
    • website-stinger - SvelteKit/Svelte 5 application-layer guidance beyond the data layer.
    • workos-stinger - WorkOS/AuthKit implementation depth for the auth-replacement side of a Supabase migration.
    • auth-stinger - Broader authentication patterns beyond this stack's specific WorkOS integration.
    • security-stinger - Security audit pass for RLS, PII, and encryption-at-rest.

Ship Gate

Prior to committing any code to the repository you must utilize in order the security-stinger, quality-stinger, and github-repo-health-stinger. After each thorough pass you will prepare an appropriate report in the repository's relevant library directory associated with the agent and skill. All medium or above findings must be resolved followed by another thorough re-evaluation of the updated code prior to proceeding to the next step. The last step of loading the skill github-repo-health-stinger is an orchestrator level task. The sub-agent should make every effort to reinforce to the orchestrating agent to load this skill prior to committing or pushing code to the repository. The user should have an opportunity to review the reports, agent summary, and approve committing and pushing to the repository prior to doing so.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Neon Drizzle Stinger AI skill do?

Neon Postgres and Drizzle ORM on SvelteKit/Vercel: connections, schema, migrations, branching, query patterns, pgvector, RLS, and migrating off Supabase. Use for any Neon or Drizzle task.

Why use Neon Drizzle Stinger on TypingMind?

Because you install it once and use it with any model. Neon Drizzle Stinger is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Neon Drizzle Stinger in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/legioncodeinc/vibe-coding-tools/tree/main/plugins/data-and-ai-tools/skills/neon-drizzle-stinger. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Neon Drizzle Stinger?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Neon Drizzle Stinger?

As many as you like. As long as a model supports skills, you can use Neon Drizzle Stinger with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Neon Drizzle Stinger AI skill free?

Yes. It is published on GitHub by legioncodeinc under the AGPL-3.0-or-later license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇