Cloudflare D1 SQLite database with Workers, Drizzle ORM, migrations
56
48%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/cloudflare-d1/SKILL.mdQuality
Discovery
40%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
The description reads more like a tag list than a proper skill description—it names specific technologies which helps with distinctiveness, but fails to describe concrete actions or provide any 'use when' guidance. The lack of explicit trigger conditions and actionable capability descriptions significantly limits Claude's ability to know what this skill does and when to apply it.
Suggestions
Add explicit actions like 'Creates and manages Cloudflare D1 SQLite databases, writes Drizzle ORM schemas, generates and runs migrations, configures Worker bindings'.
Add a 'Use when...' clause such as 'Use when the user needs to set up or query a D1 database, create Drizzle schemas, run database migrations, or configure Cloudflare Workers with database bindings'.
Include additional natural trigger terms like 'edge database', 'SQL queries', 'database schema', 'wrangler.toml', or 'serverless database'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Cloudflare D1 SQLite database) and some associated technologies (Workers, Drizzle ORM, migrations), but doesn't list concrete actions like 'create tables', 'write queries', 'run migrations', or 'configure bindings'. | 2 / 3 |
Completeness | Lists technologies (the 'what' is weak—it's more of a keyword list than a capability description) and completely lacks a 'when' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Includes relevant keywords like 'Cloudflare D1', 'SQLite', 'Workers', 'Drizzle ORM', and 'migrations' that users might mention, but misses common variations like 'database schema', 'SQL queries', 'wrangler', 'bindings', or 'edge database'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of Cloudflare D1, Workers, and Drizzle ORM is a very specific technology stack that is unlikely to conflict with other skills. This is a clear niche. | 3 / 3 |
Total | 8 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable with excellent, executable code examples covering the full D1 + Drizzle stack. However, it suffers from being a monolithic document that should leverage progressive disclosure by splitting detailed query patterns, full CRUD examples, and CLI references into separate files. The workflow clarity could be improved with explicit validation checkpoints, especially around migration generation and production deployment.
Suggestions
Split into multiple files: move Query Patterns, Worker Implementation, Testing, and CLI Reference into separate referenced documents (e.g., QUERIES.md, WORKER.md, TESTING.md, CLI.md) to reduce the main skill to an overview with navigation links.
Add explicit validation checkpoints to the migration workflow, e.g., 'Review generated SQL in drizzle/0000_initial.sql before applying' and 'Run --dry-run before --remote'.
Remove the component table and introductory paragraph - Claude already knows what D1, Workers, and Drizzle are. Start directly with Project Setup.
Add a numbered end-to-end quickstart workflow (1. Create project → 2. Define schema → 3. Generate migration → 4. Verify SQL → 5. Apply locally → 6. Test → 7. Deploy) at the top for fast orientation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~400+ lines) with extensive inline code examples that could be split into reference files. The introductory text and component table add some unnecessary context, but most code examples earn their place. However, the full CRUD Worker implementation and extensive query patterns could be in separate reference files. | 2 / 3 |
Actionability | Excellent actionability throughout - every section provides fully executable code, specific CLI commands with expected outputs, and copy-paste ready examples covering setup, schema, migrations, worker implementation, queries, testing, and deployment. | 3 / 3 |
Workflow Clarity | The migration workflow includes a dry-run step for production, which is good. However, there's no explicit validation checkpoint between generating migrations and applying them (e.g., reviewing the generated SQL), and the overall setup flow lacks numbered sequential steps with verification points. The multi-environment deployment also lacks a validate-before-promote workflow. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of content with no references to external files. The query patterns, full CRUD implementation, testing setup, multi-environment config, and CLI reference could all be separate reference documents. Everything is inline in one massive file, making it hard to navigate and consuming excessive context window. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (662 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
d4ddb03
Table of Contents
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.