CtrlK
BlogDocsLog inGet started
Tessl Logo

backend-patterns

Backend architecture patterns, API design, database optimization, and server-side best practices for Node.js, Express, and Next.js API routes.

30

Quality

23%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./docs/zh-TW/skills/backend-patterns/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

14%

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

This skill is an extensive catalog of common backend patterns that Claude already knows well, making it largely redundant. It lacks workflow sequencing, validation checkpoints, and progressive disclosure—everything is presented as a flat, verbose reference. The content would benefit enormously from being trimmed to project-specific conventions and patterns that deviate from standard practices.

Suggestions

Drastically reduce content to only project-specific conventions, non-obvious patterns, or deviations from standard practices—remove generic patterns like basic REST conventions, JWT verification, and exponential backoff that Claude already knows.

Add a workflow section that sequences when and how to apply these patterns (e.g., 'When adding a new API endpoint: 1. Define route → 2. Add validation → 3. Implement service layer → 4. Test with curl command → 5. Verify error handling').

Split content into a concise SKILL.md overview with links to separate files for each pattern category (e.g., CACHING.md, AUTH.md, ERROR_HANDLING.md) to improve progressive disclosure.

Add validation/verification steps for destructive or stateful operations like database transactions and cache invalidation (e.g., 'After creating the RPC function, verify with: SELECT create_market_with_position(...)').

DimensionReasoningScore

Conciseness

This is extremely verbose at ~400+ lines, covering many patterns (repository, service layer, middleware, caching, auth, rate limiting, queues, logging) with full code examples for each. Much of this is standard knowledge Claude already possesses—basic REST conventions, N+1 query prevention, JWT verification, exponential backoff, and RBAC are well-known patterns that don't need to be taught. The skill reads like a textbook chapter rather than a concise reference adding novel information.

1 / 3

Actionability

The code examples are mostly complete and executable TypeScript, which is good. However, they are generic patterns not tied to a specific project's actual codebase, file paths, or configuration. They serve more as illustrative templates than copy-paste-ready instructions for a concrete task. There's no guidance on when to apply which pattern or how to integrate them into an existing project structure.

2 / 3

Workflow Clarity

There is no sequenced workflow or multi-step process described. The skill is a catalog of isolated patterns with no guidance on order of implementation, validation checkpoints, or decision trees for choosing between patterns. For patterns involving destructive operations (database transactions, cache invalidation), there are no verification steps.

1 / 3

Progressive Disclosure

The entire content is a monolithic wall of code examples with no references to external files, no layered organization, and no navigation aids. All patterns are dumped inline at the same level of detail. There's no quick-start overview or separation of basic vs. advanced content.

1 / 3

Total

5

/

12

Passed

Description

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 (listing categories rather than specific capabilities), misses a 'Use when...' clause entirely, and uses somewhat broad terminology that could overlap with other backend or full-stack skills.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks about designing REST APIs, optimizing database queries, structuring Express middleware, or building Next.js API routes.'

Replace high-level categories with concrete actions, e.g., 'Designs RESTful and GraphQL APIs, optimizes SQL/NoSQL queries, structures Express middleware pipelines, and implements authentication patterns.'

Include more natural trigger terms users would say, such as 'REST', 'GraphQL', 'SQL', 'MongoDB', 'middleware', 'endpoints', 'server performance', '.js backend'.

DimensionReasoningScore

Specificity

Names the domain (backend development) and some 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 list specific actions like 'design RESTful endpoints', 'write database queries', or 'configure middleware'.

2 / 3

Completeness

Describes 'what' at a high level (backend architecture, API design, etc.) 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', 'database optimization', 'Node.js', 'Express', and 'Next.js API routes'. However, it misses common variations like 'REST', 'GraphQL', 'SQL', 'MongoDB', 'middleware', 'authentication', 'endpoints', or 'server' that users would naturally use.

2 / 3

Distinctiveness Conflict Risk

The mention of specific technologies (Node.js, Express, Next.js API routes) helps narrow the scope, but 'backend architecture patterns' and 'server-side best practices' are broad enough to overlap with general coding skills, DevOps skills, or framework-specific skills.

2 / 3

Total

7

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (588 lines); consider splitting into references/ and linking

Warning

Total

10

/

11

Passed

Repository
affaan-m/everything-claude-code
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.