backend-dev-guidelines
Opinionated backend development standards for Node.js + Express + TypeScript microservices. Covers layered architecture, BaseController pattern, dependency injection, Prisma repositories, Zod validation, unifiedConfig, Sentry error tracking, async safety, and testing discipline.
81
77%
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 ./.agent/skills/backend-dev-guidelines/SKILL.mdQuality
Discovery
82%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 a strong, technically specific description that clearly identifies its domain and lists concrete patterns and tools. The main weakness is the absence of explicit 'Use when...' guidance, which would help Claude know exactly when to select this skill over other backend or TypeScript-related skills. The description uses appropriate third-person voice and avoids vague language.
Suggestions
Add a 'Use when...' clause specifying triggers like 'building Express APIs', 'setting up Node.js microservices', or 'implementing backend architecture patterns'
Consider adding common user phrases like 'API development', 'backend structure', or 'service layer' to capture more natural language triggers
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and patterns: 'layered architecture, BaseController pattern, dependency injection, Prisma repositories, Zod validation, unifiedConfig, Sentry error tracking, async safety, and testing discipline' - these are all concrete, specific technical concepts. | 3 / 3 |
Completeness | Clearly answers 'what does this do' with comprehensive coverage of patterns and tools, but lacks an explicit 'Use when...' clause or equivalent trigger guidance. The 'when' is only implied through the technology stack mentioned. | 2 / 3 |
Trigger Term Quality | Excellent coverage of natural terms developers would use: 'Node.js', 'Express', 'TypeScript', 'microservices', 'Prisma', 'Zod', 'Sentry', 'dependency injection' - these are all terms users would naturally mention when working in this domain. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific technology stack (Node.js + Express + TypeScript) and named patterns (BaseController, unifiedConfig, Prisma). The combination of these specific tools and the 'opinionated' framing creates a clear niche unlikely to conflict with generic coding skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured backend guidelines skill with strong actionability through concrete code examples and excellent progressive disclosure via sub-skills. The main weaknesses are moderate verbosity (BFRI section, motivational framing) and missing feedback loops in the validation workflow. The anti-patterns section and code comparisons are particularly effective.
Suggestions
Remove or significantly condense the BFRI section - the scoring formula adds complexity without clear actionable value for Claude
Add explicit recovery steps to the validation checklist (e.g., 'If BFRI < 3: document risks in PR, get architect review before proceeding')
Trim introductory framing ('You are a senior backend engineer', 'Your goal is to build...') - Claude doesn't need role-play setup
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary framing ('You are a senior backend engineer', 'This skill defines how backend code must be written') and the BFRI section adds significant overhead for a concept Claude could derive. The core patterns are well-presented but could be tighter. | 2 / 3 |
Actionability | Provides concrete, executable TypeScript code examples throughout - BaseController pattern, Zod validation, DI constructors, asyncErrorWrapper usage, and repository patterns are all copy-paste ready with clear do/don't comparisons. | 3 / 3 |
Workflow Clarity | The layered architecture flow is clear (Routes → Controllers → Services → Repositories), but the validation checklist at the end lacks explicit sequencing and feedback loops. No guidance on what to do when validation fails or how to recover from architectural violations. | 2 / 3 |
Progressive Disclosure | Excellent structure with a comprehensive overview in the main file and 11 clearly-labeled sub-skills for deep dives. References are one level deep, well-organized by topic, and the main skill stands alone while pointing to detailed modules. | 3 / 3 |
Total | 10 / 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- Dokhacgiakhoa/antigravity-ide
- Commit
332e58b
- 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.