neon-vercel-postgres
Set up serverless Postgres with Neon or Vercel Postgres for Cloudflare Workers/Edge. Includes connection pooling, git-like branching, and Drizzle ORM integration. Use when: setting up edge Postgres, troubleshooting "TCP not supported", connection pool exhausted, SSL config errors, or Node v20 transaction issues.
Install with Tessl CLI
npx tessl i github:jezweb/claude-skills --skill neon-vercel-postgres90
Does it follow best practices?
Validation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It clearly specifies the domain (serverless Postgres for edge environments), lists concrete capabilities, and provides an explicit 'Use when:' clause with both setup scenarios and specific error messages users would encounter. The inclusion of actual error strings as triggers is particularly effective for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Set up serverless Postgres', 'connection pooling', 'git-like branching', and 'Drizzle ORM integration'. Names specific platforms (Neon, Vercel Postgres, Cloudflare Workers/Edge). | 3 / 3 |
Completeness | Clearly answers both what (set up serverless Postgres with specific features) AND when (explicit 'Use when:' clause with specific triggers including setup scenarios and common error conditions). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'edge Postgres', 'TCP not supported', 'connection pool exhausted', 'SSL config errors', 'Node v20 transaction issues'. These are specific error messages and scenarios users would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: serverless/edge Postgres specifically for Cloudflare Workers. The specific error messages ('TCP not supported', 'connection pool exhausted') and platform names (Neon, Vercel Postgres) make it unlikely to conflict with general database skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, production-ready skill with exceptional actionability and workflow clarity. The 19 documented issues with prevention strategies demonstrate deep domain expertise. The main weakness is verbosity - the skill could be 30-40% shorter by removing explanatory text Claude doesn't need (e.g., 'Why this matters' sections, explanations of SQL injection basics) while preserving all actionable content.
Suggestions
Remove 'Why this matters' and 'Key Points' explanatory sections that explain concepts Claude already knows (SQL injection, what pooling does, why SSL matters)
Consolidate the Quick Start and Step 1-3 of the 7-step process which have significant overlap
Move the extensive Known Issues section to a separate reference file (references/known-issues.md) and keep only the top 5 most common issues inline
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | While the skill is comprehensive and well-organized, it's quite verbose at ~800+ lines. Some sections explain concepts Claude would know (e.g., what template tags do, why SQL injection is bad) and could be tightened. The 'Why this matters' explanations add bulk without proportional value. | 2 / 3 |
Actionability | Excellent actionability with fully executable code examples throughout. Every pattern includes copy-paste ready TypeScript/bash code, specific package versions, and complete configuration files. The 7-step setup process provides concrete, executable guidance at each stage. | 3 / 3 |
Workflow Clarity | Outstanding workflow clarity with explicit validation checkpoints. The 7-step setup process is clearly sequenced, the troubleshooting section provides error-to-solution mappings, and the complete setup checklist at the end serves as a verification checkpoint. Destructive operations (migrations, branch deletion) include proper warnings. | 3 / 3 |
Progressive Disclosure | Well-structured with clear navigation. Quick Start provides immediate value, detailed 7-step process follows, and advanced topics are appropriately separated. References to external files (references/, scripts/, assets/) are clearly signaled with 'When Claude should load these' guidance. No deeply nested references. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
75%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 12 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1181 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 12 / 16 Passed | |
- 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.