tdg-personal/backend-patterns
Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.
34
43%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
32%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 identifies a reasonable domain and names specific technologies, which helps with targeting. However, it lacks concrete actions (verbs describing what the skill does), has no 'Use when...' clause to guide skill selection, and uses category-level terms rather than specific capabilities. The description reads more like a topic list than an actionable skill selector.
Suggestions
Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user asks about building REST APIs, optimizing database queries, structuring Express middleware, or setting up Next.js API routes.'
Replace abstract category names with concrete actions, e.g., 'Designs RESTful and GraphQL APIs, optimizes database queries and indexing, structures Express middleware pipelines, and implements authentication flows.'
Include additional natural trigger terms users might say, such as 'REST', 'GraphQL', 'middleware', 'SQL queries', 'MongoDB', 'server performance', or 'endpoint design'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (backend development) and lists several areas like 'API design', 'database optimization', and 'server-side best practices', but these are still fairly high-level categories rather than concrete actions. It doesn't specify what actions are performed (e.g., 'designs RESTful endpoints', 'optimizes SQL queries'). | 2 / 3 |
Completeness | Describes 'what' at a high level but completely lacks any 'when' clause or explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and since the 'what' is also somewhat vague, this scores a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords users might say like 'API design', 'Node.js', 'Express', 'Next.js API routes', and 'database optimization'. However, it misses common variations like 'REST', 'GraphQL', 'middleware', 'SQL', 'MongoDB', 'backend performance', or 'server setup'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of specific technologies (Node.js, Express, Next.js API routes) helps narrow the scope, but terms like 'backend architecture patterns' and 'best practices' are broad enough to overlap with general coding, architecture, or full-stack skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
29%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a pattern catalog that dumps extensive, well-written but verbose code examples for common backend patterns that Claude already understands. While the code is executable and actionable, the skill fails on conciseness (explaining well-known patterns at full implementation depth), workflow clarity (no sequencing or validation), and progressive disclosure (monolithic structure with no external references). It would be far more effective as a concise overview with pointers to detailed pattern files.
Suggestions
Drastically reduce inline code to brief snippets showing only project-specific conventions or non-obvious patterns, moving full implementations to separate reference files (e.g., PATTERNS_DB.md, PATTERNS_AUTH.md).
Add a workflow section that sequences how to implement a new API endpoint end-to-end (e.g., 1. Define route → 2. Add validation → 3. Implement service → 4. Test → 5. Add error handling), with explicit validation checkpoints.
Remove patterns Claude already knows well (basic JWT verification, simple rate limiting, structured logging) unless there are project-specific conventions that differ from standard implementations.
Add a quick-reference table at the top mapping common tasks to the specific pattern/file to consult, enabling progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~400+ lines, presenting extensive code examples for patterns Claude already knows well (repository pattern, middleware, JWT auth, rate limiting, logging). Most of these are standard patterns that don't need full implementations spelled out. The closing reminder ('Backend patterns enable scalable, maintainable server-side applications') is unnecessary filler. | 1 / 3 |
Actionability | All code examples are fully executable TypeScript with concrete implementations, specific types, and copy-paste ready patterns. The examples use real libraries (Supabase, jsonwebtoken, Zod) with proper imports and realistic usage patterns. | 3 / 3 |
Workflow Clarity | There are no multi-step workflows, sequenced processes, or validation checkpoints. The skill is a catalog of isolated patterns without guidance on how to compose them, in what order to implement them, or how to validate that implementations are correct. For a skill covering database operations and destructive changes, this lack of validation steps is a significant gap. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of code examples with no references to external files and no layered organization. All patterns are dumped inline at the same level of detail, with no separation between quick-reference material and deep-dive content. Content covering 10+ distinct topics should be split across files. | 1 / 3 |
Total | 6 / 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 (599 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 | |
Reviewed
Table of Contents