backend-dev-guidelines

You are a senior backend engineer operating production-grade services under strict architectural and reliability constraints. Use when routes, controllers, services, repositories, express middleware, or prisma database access.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/backend-dev-guidelines/SKILL.md

Quality

Content

71%Weight 40%Scale 1-5

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

The content is a well-structured, actionable standards document with lean code examples and clear rules, scoring high on conciseness, actionability, and workflow clarity. Its single weakness is progressive disclosure: everything is packed into one monolithic file with no bundle references to split out detailed material.

Suggestions

Move detailed or reference-heavy material (e.g., full BFRI worked examples, extended code patterns, naming/anti-pattern catalog) into references/ files and link to them from SKILL.md to improve progressive disclosure.

Remove the duplicated 'When to Use' block (it appears in both section 1's subsection and the trailing 'When to Use') to tighten conciseness toward level 5.

Add an explicit error-recovery/feedback loop (e.g., 'on Sentry capture failure or validation error, fix and re-run checklist') to push workflow clarity to level 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean — rules, tables, and short executable code blocks with almost no explanation of concepts Claude already knows (no 'what is Express/Prisma/Sentry' padding); minor redundancy (a duplicated 'When to Use' section and anti-patterns echoed in the checklist) keeps it just below level 5.	4 / 5
Actionability	Concrete, executable guidance throughout — layered-architecture code, BaseController pattern, Zod parse, asyncErrorWrapper, DI constructor, naming conventions and directory layout — with only minor gaps (BaseController's internal helpers are referenced but not shown).	4 / 5
Workflow Clarity	A clear pre-implementation sequence exists via the BFRI scoring flow plus a final Operator Validation Checklist; because this is a standards/guidelines skill rather than a destructive batch operation, the missing validate→fix→retry feedback loop does not trigger the level-3 cap, though no explicit error-recovery loop is shown.	4 / 5
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the entire skill is a single monolithic SKILL.md with 13 inlined sections; section structure is good, but content that could plausibly live in separate references (detailed conventions, extended examples) is all inline with no external navigation.	3 / 5
	Total	15 / 20 Passed

Description

70%Weight 40%Scale 1-5

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 is strong and explicit on both scope and triggers, with concrete technical keywords that a backend developer would naturally say. Its main weakness is framing the capability as a role/constraint statement rather than a list of concrete actions, which keeps specificity and completeness just below the top level.

Suggestions

Lead the description with concrete verbs/actions (e.g., 'Enforce layered architecture, validate input with Zod, route errors to Sentry') before the role framing, to lift specificity toward level 4-5.

Add a few natural synonyms or file/tech markers (e.g., 'Node.js', 'TypeScript', 'REST endpoints', 'schemas') to broaden trigger-term coverage toward level 5.

Tighten the 'what' so it reads as capability enumeration rather than a persona statement, making both halves of completeness fully explicit.

Dimension	Reasoning	Score
Specificity	Names the backend domain and several concrete components (routes, controllers, services, repositories, middleware, prisma) but frames the 'what' as a role/constraint statement ('senior backend engineer operating production-grade services') rather than enumerating concrete actions, so it falls short of the multi-action listing at level 4.	3 / 5
Completeness	Both 'what' (senior backend engineer operating production-grade services under architectural/reliability constraints) and 'when' (Use when routes, controllers, services, repositories, express middleware, or prisma database access) are present and explicit; the 'what' could be more action-concrete to reach level 5.	4 / 5
Trigger Term Quality	The 'Use when' clause lists natural technical terms a backend developer would actually say — routes, controllers, services, repositories, express middleware, prisma database access — giving good keyword coverage, though a few synonyms or variations are missing.	4 / 5
Distinctiveness Conflict Risk	The Node.js/Express/Prisma layered-architecture niche with specific trigger terms is mostly distinct with only minor overlap risk against broader backend skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/antigravity-awesome-skills
Path: skills/backend-dev-guidelines/SKILL.md
Commit: 1f67c44

Reviewed: about 16 hours ago

Table of Contents

Discovery Implementation Validation

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.