CtrlK
BlogDocsLog inGet started
Tessl Logo

oma-frontend

Frontend specialist for React, Next.js, Angular, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment. Use for UI, component, page, layout, CSS, Tailwind, shadcn, Angular, and RxJS work.

64

Quality

76%

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 ./.agents/skills/oma-frontend/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

The body has a clear, well-validated workflow and some genuinely actionable directives, but it is padded with redundant stack listings and abstract process frameworking, and its progressive disclosure is undermined by a duplicated, partly-broken reference layout with no backing bundle files.

Suggestions

De-duplicate the stack: keep one authoritative Libraries table and remove the repeated React/Next.js/TypeScript/Tailwind/shadcn entries from Dependencies and Tools and instruments.

Collapse the abstract SSL-primitive action table and PREPARE/ACQUIRE/ACT scenes into the concrete Entry→VERIFY→Exit flow, or move them to a referenced resource so the body stays lean.

Consolidate the References section into a single, clearly signaled list and ensure each referenced resources/*.md file actually exists in the bundle.

DimensionReasoningScore

Conciseness

The stack is restated three times (Dependencies, the Libraries table, and Tools and instruments) and the References section lists resources twice in different formats; the abstract SSL-primitive and PREPARE/ACQUIRE/ACT scenes framing adds overhead Claude does not need.

2 / 3

Actionability

Concrete bits exist (rg discovery commands, a versioned/banned Libraries table, named shadcn registry tools, explicit guardrails like 'treat components/ui/* as read-only'), but actual executable code examples are deferred to resources/examples.md and the Structural Flow is described abstractly rather than instructed.

2 / 3

Workflow Clarity

A clear Entry → Scenes (PREPARE/ACQUIRE/ACT/VERIFY/FINALIZE) → Transitions → Failure and recovery → Exit sequence is given, with an explicit VERIFY checkpoint, a referenced checklist, and a feedback loop ('If verification fails, fix before handoff or report the blocker').

3 / 3

Progressive Disclosure

References are one level deep and signaled, but no bundle files actually exist in references/scripts/assets, the reference list is duplicated and inconsistently formatted (numbered list then a separate bullet list), and the body itself is a ~195-line monolithic wall rather than a lean overview pointing outward.

2 / 3

Total

9

/

12

Passed

Description

90%

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 with an explicit 'Use for' trigger and a well-scoped frontend stack niche. Its only weakness is specificity: it lists work areas and domain nouns rather than concrete actions.

Suggestions

Lead with concrete verbs (e.g., 'Build, modify, and verify React/Next.js/TypeScript UIs…') so the description states actions, not just domains.

Tighten 'specialist for … with FSD-lite architecture, shadcn/ui, and design system alignment' into the action clause to avoid noun-stacking.

DimensionReasoningScore

Specificity

The main clause 'Frontend specialist for React, Next.js, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment' is noun-heavy and names the domain plus work areas ('UI, component, page, layout, CSS, Tailwind, and shadcn work') but lacks concrete verbs like build/modify/verify that appear only in the body.

2 / 3

Completeness

It answers both what ('Frontend specialist for…') and when via the explicit 'Use for UI, component, page, layout, CSS, Tailwind, and shadcn work' trigger clause, matching the rubric's good example pattern.

3 / 3

Trigger Term Quality

'UI, component, page, layout, CSS, Tailwind, and shadcn' alongside 'React, Next.js, TypeScript' are exactly the natural terms a user would say when requesting frontend work, with good coverage of variations.

3 / 3

Distinctiveness Conflict Risk

The specific stack niche (FSD-lite architecture, shadcn/ui, design system alignment) gives it a clear, distinct trigger surface unlikely to fire for backend or mobile work.

3 / 3

Total

11

/

12

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.

Validation16 / 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.