CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-backend

Implement server APIs, authentication, and application data access. Schema modeling and query tuning use oma-db.

56

Quality

62%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/oma-backend/SKILL.md
SKILL.md
Quality
Evals
Security

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 body is a well-structured, mostly lean backend playbook with a clear sequenced workflow, validation checkpoints, and concrete numbered rules. Its main weaknesses are minor architectural-pattern redundancy and progressive-disclosure references that point to bundle files which are not actually present.

Suggestions

Ship the referenced bundle files (resources/execution-protocol.md, resources/checklist.md, resources/orm-reference.md, resources/error-playbook.md, and the ../_shared/core/* set) so the clearly-signaled references resolve to real content.

Consolidate the layered-architecture explanation so the Router→Service→Repository→Models pattern is stated once and the per-layer sections only add layer-specific rules, removing the restatement in Core Rule #1.

Add one or two copy-paste code snippets for the most common backend cases (e.g. a parameterized query and a service-scoped transaction unit-of-work) to push actionability toward fully executable.

DimensionReasoningScore

Conciseness

The body is directive and assumes Claude's competence — rules and standards rather than tutorials — with no concept-explanation padding. It loses a point because the Router→Service→Repository→Models pattern is stated in the Architecture Pattern, restated across three layer sections, and again in Core Rule #1. Efficient with minor instances of over-explanation that could be trimmed; not 5 due to that redundancy, not 3 because it is not noticeably padded.

4 / 5

Actionability

Provides concrete executable guidance: an action→SSL-primitive table, a canonical `rg` workflow, an architecture diagram, and 13 numbered rules with specifics (e.g. 'JWT + Argon2id', 'parameterized queries only', the env-fallback pattern with a `// TODO(oma-deferred)` marker). Mostly executable; not 5 because code examples are thin (only two `rg` lines) with no copy-paste snippet for common cases, not 3 because the guidance is concrete rather than pseudocode.

4 / 5

Workflow Clarity

Clear sequencing via Entry steps, the PREPARE→ACQUIRE→ACT→VERIFY→FINALIZE scenes, explicit failure/recovery, and a VERIFY checkpoint with 'fix root cause before handoff' plus a referenced checklist — a feedback loop for migration/persistence work. Not 5 because the checklist/feedback loop is referenced rather than inline and lightly specified; not 3 because validation checkpoints are explicitly present, satisfying the destructive/batch cap.

4 / 5

Progressive Disclosure

The body is well-sectioned with a clear one-level-deep References list pointing to resources/*.md and ../_shared/core/*.md files. However the referenced bundle files do not exist in the bundle (references/, scripts/, assets/, resources/, ../_shared are all absent), so the signaled navigation leads nowhere. Not 4 because the referenced targets are missing and navigation is undermined; not 2 because structure and signaling are genuinely present and bulk is appropriately deferred to references.

3 / 5

Total

15

/

20

Passed

Description

53%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 clearly states the backend capability area and draws a useful boundary to oma-db, but it omits any explicit 'Use when...' trigger guidance and lacks the most natural user trigger terms ('backend', 'endpoint', 'REST'). It is a competent but incomplete description that would benefit from explicit triggering language and broader keyword coverage.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks for backend work — APIs/endpoints, REST/GraphQL, auth, server-side logic, migrations, repositories, or background jobs.'

Broaden natural keyword coverage to include user-facing terms like 'backend', 'endpoint', 'REST', 'GraphQL', 'server-side', and 'migrations'.

Expand the action list beyond the three named (APIs, auth, data access) to cover migrations, server-side business logic, and background jobs for more comprehensive specificity.

DimensionReasoningScore

Specificity

Names the backend domain and several concrete actions ('server APIs, authentication, and application data access') but coverage is not comprehensive — migrations, business logic, and background jobs are absent. It is above anchor 2 (which has only minimal/generic actions) but below anchor 4 (which expects several specific actions with only minor gaps).

3 / 5

Completeness

A clear 'what' is present (implement server APIs, auth, data access) but there is no 'Use when...' or equivalent explicit 'when' clause, which caps completeness at 3 per the rubric guideline. Not 2 because the 'what' is concrete rather than vague; not 4 because 'when' is entirely absent.

3 / 5

Trigger Term Quality

Relevant keywords like 'server APIs', 'authentication', and 'application data access' appear, but common natural trigger phrases users would say ('backend', 'endpoint', 'REST', 'GraphQL', 'server-side') are missing. Matches anchor 3 (some relevant keywords, missing common variations/synonyms); not 4 because keyword coverage is not yet 'good with only a few missing'.

3 / 5

Distinctiveness Conflict Risk

It carves a backend niche and explicitly redirects 'Schema modeling and query tuning' to oma-db, reducing overlap with sibling skills. Mostly distinct with only minor overlap risk against a general db or data-access skill; not 5 because the triggers are not crisply distinctive and lack explicit trigger phrases.

4 / 5

Total

13

/

20

Passed

Validation

100%

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
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.