CtrlK
BlogDocsLog inGet started
Tessl Logo

backend-dev-guidelines

Comprehensive backend development guide for Node.js/Express/TypeScript microservices. Use when creating routes, controllers, services, repositories, middleware, or working with Express APIs, Prisma database access, Sentry error tracking, Zod validation, unifiedConfig, dependency injection, or async patterns. Covers layered architecture (routes → controllers → services → repositories), BaseController pattern, error handling, performance monitoring, testing strategies, and migration from legacy patterns.

68

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is backend-dev-guidelines in diet103/claude-code-infrastructure-showcase

SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-3

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

Actionable and well-organized with strong code examples, but it spends tokens restating knowledge Claude already has and its progressive-disclosure references point to files that do not exist. Workflows use checklists without explicit validation feedback loops.

Suggestions

Remove or relocate the HTTP Status Codes table and Common Imports section — Claude already knows these; keep only stack-specific conventions (e.g., instrument.ts as first import, unifiedConfig paths).

Create the referenced bundle files (architecture-overview.md, routing-and-controllers.md, etc.) under references/ so the Navigation Guide and Resource Files links resolve, or remove the dangling links.

Add explicit validation feedback loops to the checklists (e.g., "run unit + integration tests; if failing, fix and re-run before marking complete") to lift workflow clarity.

DimensionReasoningScore

Conciseness

Mostly efficient with good code snippets, but the "HTTP Status Codes" table and "Common Imports" section restate concepts Claude already knows, and "Anti-Patterns to Avoid" duplicates the Core Principles; not level 3 because some tokens do not earn their place.

2 / 3

Actionability

Provides concrete, copy-paste-ready TypeScript for each rule (BaseController extension, Sentry capture, unifiedConfig, Zod parse, repository usage, tests) plus concrete checklists; not level 2 because the examples are executable rather than pseudocode.

3 / 3

Workflow Clarity

The New Backend Feature and New Microservice checklists give a sequence, but there are no explicit validate→fix→retry feedback loops; not level 3 because checkpoints are implicit rather than enforced validation steps.

2 / 3

Progressive Disclosure

Navigation Guide and Resource Files sections describe well-signaled one-level-deep references to 11 files, but no references/ directory or referenced .md files exist on disk, so the disclosure is structurally well-designed yet broken in practice; not level 3 because the linked bundle is missing.

2 / 3

Total

9

/

12

Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that clearly states capabilities and provides an explicit Use-when trigger with concrete, natural keywords. It is distinguishable from generic skills via its specific named tooling.

DimensionReasoningScore

Specificity

Lists multiple concrete actions and domains — "creating routes, controllers, services, repositories, middleware", "Prisma database access, Sentry error tracking, Zod validation", "BaseController pattern, error handling, performance monitoring, testing strategies" — matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ("Comprehensive backend development guide for Node.js/Express/TypeScript microservices") and when ("Use when creating routes, controllers, services, repositories, middleware..."), with an explicit Use-when trigger clause.

3 / 3

Trigger Term Quality

Covers natural terms a backend developer would actually say — routes, controllers, services, middleware, Express APIs, Prisma, Sentry, Zod, async patterns — with good breadth; not the level below because it goes well beyond a single keyword to many common variations.

3 / 3

Distinctiveness Conflict Risk

The named stack (Prisma, Sentry, Zod, unifiedConfig, BaseController, layered architecture) carves a clear niche unlikely to trigger for unrelated skills; it is more specific than the level-2 anchor that could still overlap.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 24 missing

Warning

Total

15

/

16

Passed

Repository
diet103/claude-code-infrastructure-showcase
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.