neon

Overview of the Neon platform for apps and agents, spanning Postgres, Auth, the Data API, and the new services: Object Storage, Compute Functions, and AI Gateway. Use when "Neon" is mentioned, or when any of its individual capabilities are the trigger: "object storage" or "S3", "buckets", "serverless functions", "AI gateway", "call an LLM", "postgres", "database", or "backend".

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%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 thorough, highly actionable overview skill with concrete commands and code throughout and well-sequenced workflows that include a fail-fast validation checkpoint. Its main weakness is conciseness — repeated restatements of the env-pull behavior and dense inline config detail could be tightened or moved to referenced files.

Suggestions

Consolidate the repeated 'link and checkout pull env by default' explanation into a single statement; it currently appears in three sections (Branch-First Dev Flow, the code-block comments, and the Infrastructure as Code section).

Tighten the 'Opting out of local env vars' block (174-185), which lists four overlapping runtime-injection mechanisms; consider promoting the lower-level `fetchEnv`/`neon-env run` detail to a referenced file.

Add an explicit verify-before-proceeding step for destructive operations such as `neon set-context` and `neon config apply`/`neon deploy` to lift workflow_clarity toward a 5.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the fact that 'link' and 'checkout' pull env by default is restated across three sections (154, 159-160, 235) and the env-injection/opt-out block (174-185) is dense enough to tighten, fitting 'mostly efficient but could be tightened'.	3 / 5
Actionability	Abundant copy-paste-ready commands (`neon link`, `neon checkout <branch>`, `neon config apply`, `npx -y neon init`) and complete TypeScript `defineConfig`/`parseEnv` examples cover the common cases, matching the fully-executable anchor.	5 / 5
Workflow Clarity	Multi-step flows (Getting Started, Branch-First, config status/plan/apply) are clearly sequenced with a real fail-fast validation checkpoint on env-pull, but destructive operations like `set-context` ('replaces the file's contents entirely') and `neon config apply` lack an explicit validate-before-proceeding step, a minor validation gap.	4 / 5
Progressive Disclosure	As an index/router skill it delegates one level deep to clearly-signaled sibling skills (`neon-postgres`, `neon-functions`, `neon-object-storage`, `neon-ai-gateway`) and external docs, with good section structure; the dense inline neon.ts/parseEnv detail (50+ lines each) could arguably live in referenced files, a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

96%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, well-structured description that clearly states the platform's capabilities and provides an explicit 'Use when' clause with concrete, synonym-rich trigger terms. The only weakness is that a few generic triggers ('database', 'backend') create slight conflict risk with other backend/database skills.

Dimension	Reasoning	Score
Specificity	Enumerates concrete platform capabilities comprehensively — 'Postgres, Auth, the Data API, and the new services: Object Storage, Compute Functions, and AI Gateway' — rather than vague language, matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly answers both 'what' (overview of Neon platform services) and 'when' ('Use when...') with concrete trigger phrases, hitting the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural terms with synonyms — '"object storage" or "S3", "buckets", "serverless functions", "AI gateway", "call an LLM", "postgres", "database", or "backend"' — matching the anchor for full synonym/extension coverage.	5 / 5
Distinctiveness Conflict Risk	Neon-scoped triggers ('Neon', service names) give a clear niche, but broad generic terms like 'database', 'backend', and 'call an LLM' carry minor overlap risk with non-Neon skills, so it sits at 'mostly distinct' rather than the top.	4 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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/SKILL.md
Commit: fa04428

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.