CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

neon-postgres

Guides and best practices for working with Neon Serverless Postgres. Covers setup, connection methods, branching, autoscaling, scale-to-zero, read replicas, connection pooling, Neon Auth, and the Neon CLI, MCP server, REST API, TypeScript SDK, and Python SDK. Use when users ask about "Neon setup", "connect to Neon", "Neon project", "DATABASE_URL", "serverless Postgres", "Neon CLI", "neon", "Neon MCP", "Neon Auth", "@neondatabase/serverless", "@neondatabase/neon-js", "scale to zero", "Neon autoscaling", "Neon read replica", or "Neon connection pooling".

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured index-style skill: executable commands and complete code examples for the common setup and connection cases, a numbered setup flow with resume support, and clean one-level-deep disclosure to the official docs plus a verified local reference file. The main improvement opportunities are tightening a few verbose spots and adding an explicit connection-verification step to the setup workflow.

Suggestions

Trim the repeated choose-connection.md URL (appears three times: in Setup Flow step 3, the Connection Methods section, and the Neon Auth section) to a single canonical mention, and condense the marketing-style opening paragraph — both would lift the conciseness dimension from 4 to 5.

Add an explicit verification checkpoint at the end of the Setup Flow (e.g., run a trivial test query against DATABASE_URL or confirm the connection string resolves) so the workflow closes the loop the way the Resume Support section opens it.

Consider compressing the ~50-line neon.ts section by removing line-by-line code comments and keeping only the config skeleton, or moving the full annotated example into a reference file in the same style as references/neon-sdk.md.

DimensionReasoningScore

Conciseness

The body is largely lean — a disciplined repeating pattern of "Use this for ... / Key points / Link:" with complete code blocks and no tutorials on concepts Claude already knows. Minor trims are possible: the marketing-style intro ("Neon is a serverless Postgres platform that separates compute and storage..."), the ~50-line neon.ts section with heavily commented config, and the choose-connection.md URL repeated three times. That places it at anchor 4 ('efficient; minor instances of over-explanation that could be trimmed') — above anchor 3's noticeable padding, below anchor 5 where every token earns its place.

4 / 5

Actionability

Guidance is fully executable: concrete commands ("npx -y neon@latest init --agent <agent-name>", "npx skills add neondatabase/agent-skills --skill neon-postgres-branches", "neon config plan/apply"), copy-paste-ready TypeScript for both runtime patterns (module-scope pg Pool with attachDatabasePool for Vercel Fluid, neon-http serverless driver for Netlify), doc-fetching techniques (append .md / Accept: text/markdown), and a docs index for URL discovery. Placeholders like <agent-name> are justified with an explicit list of supported values. This matches anchor 5 ('fully executable; copy-paste ready; specific examples cover the common cases').

5 / 5

Workflow Clarity

The Getting Started section has a clear numbered 6-step Setup Flow with a pre-flight "Check Status Quo" inspection, resume logic ("check what's already configured ... and continue from the next incomplete step"), and a safety checkpoint ("Read the file first before modifying to avoid overwriting existing values" for .env). No destructive/batch cap applies. It falls just short of anchor 5 because there is no explicit post-setup verification (e.g., testing the connection with a query) — a minor checkpoint gap that lands it at anchor 4 rather than 5.

4 / 5

Progressive Disclosure

The body is exactly an overview-plus-navigation document: every topic section is a short "Use this for ..." pointer with a one-level-deep link to the authoritative Neon doc page, plus a docs index (llms.txt) for undiscovered pages and "Don't guess URLs" guidance. The single bundle file references/neon-sdk.md exists on disk and matches its in-body citation, and the sibling neon-postgres-branches skill is signaled with both a fetch URL and an install command. This matches anchor 5 ('clear overview with well-signaled one-level-deep references; easy navigation'); there is no inlined bulk content that belongs in a separate file and no nested references.

5 / 5

Total

18

/

20

Passed

Description

91%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: explicit what-and-when structure with an unusually thorough list of natural trigger terms including package names and synonyms. The only deductions are the mildly buzzword framing ('Guides and best practices for working with') and two semi-generic triggers ("DATABASE_URL", "serverless Postgres") that create minor overlap risk with generic Postgres skills.

DimensionReasoningScore

Specificity

"Covers setup, connection methods, branching, autoscaling, scale-to-zero, read replicas, connection pooling, Neon Auth, and the Neon CLI, MCP server, REST API, TypeScript SDK, and Python SDK" names many concrete capability areas with near-comprehensive coverage. However, the framing "Guides and best practices for working with" is vague buzzword-flavored ('best practices') and the listed items are topics rather than concrete actions, so it fits anchor 4 ('several specific actions; minor gaps') rather than the fully action-verb anchor 5. It is clearly above anchor 3, which requires only 1-2 concrete actions.

4 / 5

Completeness

It explicitly answers 'what' (the enumerated capability areas) and 'when' ("Use when users ask about ..." with concrete trigger phrases). This is a direct match for anchor 5's pattern ('clearly and explicitly answers both what AND when with concrete trigger phrases'). Anchor 4 would require a less explicit 'when' clause, which does not apply.

5 / 5

Trigger Term Quality

"Use when users ask about 'Neon setup', 'connect to Neon', 'Neon project', 'DATABASE_URL', 'serverless Postgres', 'Neon CLI', 'neon', 'Neon MCP', 'Neon Auth', '@neondatabase/serverless', '@neondatabase/neon-js', 'scale to zero', 'Neon autoscaling', 'Neon read replica', or 'Neon connection pooling'" — this is comprehensive natural-term coverage including synonyms ('scale to zero' alongside 'Neon autoscaling'), lowercase brand ('neon'), and package names (the SDK equivalent of file extensions), matching anchor 5 exactly. Anchor 4 would still be missing some natural terms, which is not the case here.

5 / 5

Distinctiveness Conflict Risk

The skill occupies a clear niche (the Neon platform) with 13 of 15 triggers being Neon-branded, but "DATABASE_URL" and "serverless Postgres" are semi-generic terms that could also fire for ordinary Postgres or general database-connection tasks — anchor 4's 'minor overlap risk with closely related skills'. It is well above anchor 3 (which would allow broad overlap) but the two generic triggers keep it from anchor 5's 'minimal conflict risk'.

4 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Mirxa27/arabclue-platform

Path

.agents/skills/neon-postgres/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.