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

69%

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

Quality

Content

60%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, validation checkpoint, and a clean reference map, but it over-explains well-known principles (DRY/SOLID/KISS) and lacks executable code examples for its core architecture layers. Referenced resource files are also absent from the bundle.

Suggestions

Replace the Guardrails DRY/SOLID/KISS definitions with project-specific rules only, since Claude already knows these principles; keep the line about where business logic vs data access belongs.

Add at least one copy-paste-ready code sketch of the Router→Service→Repository→Models flow in the project's detected stack to lift actionability.

Either ship the referenced resources/ and ../_shared/ files in the bundle or mark them as externally injected so the References section points to real, navigable paths.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and skips basic concept tutorials, but the Guardrails section defines DRY, SOLID, Single Responsibility, Dependency Inversion, and KISS — concepts Claude already knows — and the SSL-primitive Actions table adds abstract jargon tokens, so it could be tightened rather than earning a 4.	3 / 5
Actionability	Concrete directives exist ("JWT + Argon2id", "Parameterized queries only", two `rg` discovery commands, the Router→Service→Repository→Models diagram), but there are no executable code examples or templates for the core layers, leaving guidance incomplete rather than mostly executable.	3 / 5
Workflow Clarity	A clear sequence is present (Entry, PREPARE/ACQUIRE/ACT/VERIFY/FINALIZE scenes, Transitions, Failure and recovery, Exit) with a VERIFY checkpoint and a feedback loop ("If verification fails, fix root cause before handoff"), but the validation gate is somewhat implicit rather than an explicit validate-then-proceed step, so it sits at 4 not 5.	4 / 5
Progressive Disclosure	A dedicated References section lists one-level-deep, clearly signaled pointers (resources/execution-protocol.md, orm-reference.md, checklist.md, ../_shared/core/*), and overview content is reasonably inline; however the referenced bundle files do not actually exist in the skill bundle, a minor organization/reliability gap that prevents a 5.	4 / 5
	Total	14 / 20 Passed

Description

78%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.

A strong, third-person description that clearly states both capability and activation triggers with good keyword coverage. Its main weakness is framing capabilities as a role ("specialist for") instead of enumerating concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain ("APIs, databases, authentication") and a concrete architecture pattern ("Repository/Service/Router pattern"), but uses a role statement ("Backend specialist for") rather than listing concrete actions like implement endpoints or write migrations; not comprehensive enough for a 4.	3 / 5
Completeness	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 trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	"Use for API, endpoint, REST, database, server, migration, and auth work" gives good natural-keyword coverage with synonyms (API/endpoint/REST), though a few natural terms (GraphQL, backend-as-a-phrase beyond the role) are absent, stopping short of a 5.	4 / 5
Distinctiveness Conflict Risk	The Repository/Service/Router niche is mostly distinct, but the "database" and "migration" triggers overlap with a sibling DB skill (oma-db is referenced in the body), so minor overlap risk keeps it at 4 rather than 5.	4 / 5
	Total	16 / 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: .agents/skills/oma-backend/SKILL.md
Commit: 7721120

Reviewed: 5 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.