oma-backend

Backend specialist for APIs, databases, authentication with clean architecture (Repository/Service/Router pattern). Use for API, endpoint, REST, database, server, migration, and auth work.

Quality

77%

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 ./benchmarks/runs/oma/.agents/skills/oma-backend/SKILL.md

Quality

Content

63%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 well-structured with a clear workflow and mostly efficient prose, but it leans on high-level guidance over executable code and references bundle files that are not actually present in the skill. Tightening the inline rules and shipping the referenced resources would raise the score.

Suggestions

Provide at least one copy-paste router/service/repository code skeleton in the body or a bundled snippet file so the guidance is executable, not just descriptive.

Create the referenced resources/ files (execution-protocol.md, checklist.md, orm-reference.md, examples.md, error-playbook.md) or remove the references to avoid broken navigation.

Drop the parenthetical glosses on DRY and KISS — Claude already knows these — and move the 13 Core Rules into a bundled reference file to keep the overview lean.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and reference-style, assuming Claude knows the stack patterns, but it over-explains DRY ("Don't Repeat Yourself") and KISS ("Keep it simple and clear") — concepts Claude already knows — which keeps it from a 5.	4 / 5
Actionability	It gives concrete architectural rules and named layer responsibilities, but code examples are limited to two ripgrep commands with no executable router/service/repository scaffolding; guidance stays high-level relative to a code-generation skill.	3 / 5
Workflow Clarity	A clear PREPARE→ACQUIRE→ACT→VERIFY→FINALIZE sequence exists with an explicit VERIFY checkpoint and a failure/recovery section, but the validate→fix→revalidate loop is implicit rather than fully spelled out.	4 / 5
Progressive Disclosure	References to resources/.md and ../_shared/core/.md are signaled, but the referenced bundle files are absent (references/, scripts/, assets/ all missing), and substantial content (13 Core Rules, full Stack-Specific Reference) is inlined rather than split out.	3 / 5
	Total	14 / 20 Passed

Description

91%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: it is specific, uses natural trigger terms, and explicitly covers both what the skill does and when to use it. The only weakness is slight overlap risk with a sibling database specialist and reliance on a pattern name rather than enumerated actions.

Dimension	Reasoning	Score
Specificity	The description names several concrete capabilities (APIs, databases, authentication) plus the Repository/Service/Router pattern, but relies on the pattern name rather than enumerating multiple distinct backend actions, leaving minor coverage gaps.	4 / 5
Completeness	It explicitly answers both what ("Backend specialist for APIs, databases, authentication with clean architecture") and when ("Use for API, endpoint, REST, database, server, migration, and auth work") with concrete triggers.	5 / 5
Trigger Term Quality	It provides comprehensive natural trigger terms a user would say — "API, endpoint, REST, database, server, migration, and auth work" — covering synonyms and common phrasings.	5 / 5
Distinctiveness Conflict Risk	The backend/server niche is clearly distinct from frontend and mobile, with specific triggers; minor overlap risk exists with a dedicated database skill, keeping it just below 5.	4 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: first-fluke/oh-my-agent
Path: benchmarks/runs/oma/.agents/skills/oma-backend/SKILL.md
Commit: 032c988

Reviewed: 2 days 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.