Core Idea
The author's design philosophy, what sets this apart from peer projects, and quick notes on the key workflows. Skill names mentioned in the text auto-link to their detail pages.
This skillset provides Agent Skills for Neon Serverless Postgres and related services, enabling agents to operate Neon more accurately via auto-discovered SKILL.md instructions.
Install via npx skills add or plugin; use natural-language prompts like "Why is my Neon bill so high?" to let the agent auto-load the right skill.
Skill Relationships
Skill → Skill usage relationships, with cross-layer references. Same color blocks indicate the same skill form.
Skill Composition
Each skill is designed for a specific kind of caller — some only fire when you name them, others load automatically when the model judges them relevant. The split below summarises both modes at a glance.
These skills only fire when you call them by name. The agent will not load them on its own — they stay inert until invoked.
These skills are loaded automatically by the agent when it judges the context relevant. You usually don't need to call them yourself.
Skill List
Instantly provisions temporary Postgres databases for dev, demos, and tests with no account needed via REST API, CLI, SDK, or Vite plugin. Parses connection string and writes to .env. Delivers zero-setup DBs expiring in 72h unless claimed, boosting prototyping speed.
Neon skill is the entry point for Neon's serverless backend suite (Postgres, Auth, Functions, Object Storage, AI Gateway). It routes to peer skills, fetches docs, and guides branch-first setup via CLI. Value: fast onboarding, correct skill use, isolated dev branches.
The Neon AI Gateway skill helps users route LLM calls through Neon's built-in inference gateway using one credential across multiple providers. It configures neon.ts, deploys via CLI, and wires AI SDK or Mastra. Value: unified API, branch-scoped isolation, no provider key management, and easy model switching.
Helps users define, run locally, deploy, and manage Neon Functions — long-running Node.js HTTP handlers next to Neon Postgres. Uses neon CLI and neon.ts to deliver deployed functions with invocation URLs and local dev loops. Value: stateful, branch-isolated, low-latency backend primitives beyond serverless limits.
Helps users store and serve files that branch with Neon Postgres via S3-compatible object storage. Uses neon CLI and IaC config to provision buckets, injects AWS env vars, and provides Files SDK or AWS S3 client flows. Value: branch-synced files and DB rows, safe throwaway environments, no extra provider.
Guides users through any Neon serverless Postgres task: setup, connection, branching, auth, and SDK/API usage. Fetches official docs as markdown to verify, inspects env, runs Neon CLI/MCP init, and configures drivers/ORM. Delivers a working connection, feature config, or accurate doc answer, boosting dev efficiency on serverless Postgres.
Guides creation and management of Neon Postgres branches via CLI or MCP. Decides normal vs schema-only type, executes branch creation, reset, and lifecycle hygiene. Delivers isolated, compliant DB branches for migration testing and dev workflows.
Guides diagnosis and fixing of app-side query patterns causing excessive Postgres egress. Uses pg_stat_statements to find heavy queries, analyzes code, applies fixes (column selection, pagination, caching, SQL aggregation, JOIN split), and codifies Neon compute savings via neon.ts. Reduces data transfer cost and bill.
Scores an eval diff against a rubric by reading the diff, rubric, and fixture app, answering P1-P5 detection/fix questions, and appending a row to results.csv. Produces structured eval scoring for change validation.
