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

56%

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

61%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 body is a strong, concrete rulebook with real code examples, clear naming and structure standards, and an enforceable validation checklist. Its weaknesses are redundancy (duplicated sections and boilerplate filler), the absence of a sequenced implementation workflow with feedback loops, and no use of reference files for secondary detail.

Suggestions

Remove the duplicated 'When to Use' section, the boilerplate 'This skill is applicable...' paragraph, and the verbatim repeat of the frontmatter persona to tighten token usage.

Add a short sequenced workflow (assess BFRI → implement layer by layer → write tests → run the validation checklist) with an explicit validate-and-fix loop for migrations and refactors, which currently cap workflow clarity at 3.

Move secondary detail (BFRI scoring tables, skill-integration list, anti-pattern catalog) into a references/ file so SKILL.md stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The rule sections are lean (tables, short snippets), but the body repeats the frontmatter description verbatim, contains a duplicated 'When to Use' section, and ends with boilerplate filler ('This skill is applicable to execute the workflow or actions described in the overview') and generic Limitations text.	3 / 5
Actionability	Concrete, mostly executable guidance throughout — BaseController subclass, asyncErrorWrapper wrapping, z.object().parse(req.body), constructor DI, unifiedConfig usage, plus a strict naming table and canonical directory tree — with minor gaps such as an undeclared this.userService and a test example referencing an undefined user.	4 / 5
Workflow Clarity	There is a rough process (BFRI assessment → doctrine → final Operator Validation Checklist) but the core guidance is a rule catalog rather than a sequenced workflow, with no validate→fix→retry feedback loops or explicit step ordering.	3 / 5
Progressive Disclosure	A single-file skill with 13 clearly numbered, well-signaled sections and no buried references; at ~340 lines some material (BFRI detail, integration list, anti-patterns) could be split into reference files, keeping it at 'good structure with minor organization gaps'.	4 / 5
	Total	14 / 20 Passed

Description

51%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 has strong trigger terms and an explicit 'Use when' clause, but it opens with second-person persona fluff and never states concrete capabilities. Rewriting it in third person with 2-3 concrete actions would lift both specificity and completeness.

Suggestions

Replace the second-person persona sentence ('You are a senior backend engineer...') with third-person concrete capabilities, e.g. 'Enforces layered architecture (routes → controllers → services → repositories), Zod input validation, BaseController error handling, and Sentry observability in Node.js/Express backends.'

State what the skill does before the trigger clause so the 'what' is explicit rather than implied by persona, and add natural synonyms such as 'API endpoints' and 'backend' to the trigger list.

Dimension	Reasoning	Score
Specificity	The description is pure abstract persona language ('operating production-grade services under strict architectural and reliability constraints') with no concrete actions named; the rubric's second-person penalty ('You are a senior backend engineer') drops it from an already action-free 2 to 1.	1 / 5
Completeness	The 'when' is explicit ('Use when routes, controllers...') but the 'what' is only a vague persona statement that never says what the skill actually does, placing it between anchor 2 (vague/missing what) and anchor 4 (both clearly present).	3 / 5
Trigger Term Quality	'routes, controllers, services, repositories, express middleware, or prisma database access' are natural terms a developer would say, but common variations like 'API', 'endpoints', 'backend', or 'Node' are missing, matching 'good keyword coverage; a few natural terms missing'.	4 / 5
Distinctiveness Conflict Risk	Triggers are scoped to a clear backend niche (Express middleware, Prisma, layered backend code) with minimal conflict risk, though it could still overlap with generic coding-standards skills.	4 / 5
	Total	12 / 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/agentic-awesome-skills
Path: skills/backend-dev-guidelines/SKILL.md
Commit: 7b534bc

Reviewed: 15 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.