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.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/oma-frontend/SKILL.md

Quality

Content

67%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 dense, rule-driven overview with concrete tools, commands, and a clear workflow including validation and recovery, scoring well on actionability and workflow clarity. Its weak spots are conciseness (redundant restatements and emphatic padding) and progressive disclosure (heavily referenced resource files are absent from the bundle).

Suggestions

De-duplicate the 'components/ui/* is read-only' rule — state it once authoritatively in Guardrails and reference it elsewhere rather than repeating it three times.

Trim the dramatic emphasis in the proxy.ts and prefetch guardrails to a single crisp directive plus the rationale; drop stacked NEVER/restatement padding.

Either ship the referenced resources/*.md, ../_shared/core/*, and ../../rules/frontend.md files in the bundle, or mark which references are resolved by the parent project at runtime so progressive disclosure is verifiable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude already knows React/Next.js/Tailwind, but it carries real redundancy — 'treat components/ui/* as read-only' is stated in Guardrails #2, the UI Implementation section, and the closing blockquote — and dramatic padding in the proxy.ts guardrail ('touch it and you die', multiple stacked NEVER clauses) that could be tightened.	3 / 5
Actionability	It gives concrete executable guidance: real `rg` commands, named shadcn registry tools (`shadcn_search_items_in_registries`, `shadcn_get_add_command_for_items`), specific file paths (`packages/design-tokens`, `components/ui/*`), pinned library versions, and explicit directives like `prefetch={false}`; the gap is that actual component/TSX code is deferred to resources rather than shown inline.	4 / 5
Workflow Clarity	A clear Entry → Scenes (PREPARE/ACQUIRE/ACT/VERIFY/FINALIZE) → Exit sequence is present with an explicit VERIFY checkpoint and feedback loops in 'Failure and recovery' plus a referenced checklist, so the destructive-codebase edits do not hit the missing-validation cap; it stops short of anchor 5 because concrete validation commands are referenced rather than stated inline.	4 / 5
Progressive Disclosure	Content is well structured with a Stack Reference table and a dedicated References section giving one-level-deep, clearly signaled pointers to tech-stack/tailwind-rules/snippets/angular-rules/execution-protocol/checklist; it does not reach anchor 5 because none of the referenced resource files actually ship in this skill bundle, so the navigation cannot be verified against real bundle content.	4 / 5
	Total	15 / 20 Passed

Description

65%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 identifies a frontend specialty with an explicit 'Use for' trigger clause and strong natural-keyword coverage, so completeness and trigger quality are solid. Its main weakness is specificity: it describes a role and domains rather than concrete actions.

Suggestions

Replace generic phrasing like 'specialist for' and 'work' with concrete action verbs (e.g., 'Build, modify, and verify React/Next.js or Angular TypeScript UIs').

Add a few missing natural trigger terms such as 'forms', 'hooks', 'state', and 'responsive design' to push trigger-term coverage toward comprehensive.

Tighten distinctiveness by noting the boundary against a general web/design skill (e.g., 'frontend implementation, not design-system authoring').

Dimension	Reasoning	Score
Specificity	The description names the domain broadly ('React, Next.js, Angular, TypeScript ... FSD-lite architecture, shadcn/ui, and design system alignment') but uses only generic action language ('specialist for', 'Use for ... work') with no concrete action verbs like build, modify, or verify, matching the 'names the domain but actions are minimal or generic' anchor.	2 / 5
Completeness	Both 'what' ('Frontend specialist for ... with FSD-lite architecture, shadcn/ui, and design system alignment') and an explicit 'when' ('Use for UI, component, page, layout, CSS, Tailwind, shadcn, Angular, and RxJS work') are present with concrete trigger phrases, but the 'what' is a role description rather than an enumeration of concrete actions, placing it just below the anchor-5 ideal.	4 / 5
Trigger Term Quality	It lists many natural terms a user would actually say — 'UI, component, page, layout, CSS, Tailwind, shadcn, Angular, and RxJS' plus React/Next.js/TypeScript — with synonym coverage across both React and Angular ecosystems; a few common terms (forms, hooks, state) are absent, so it does not reach the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	The frontend niche is sharply framed by framework-specific triggers (shadcn, FSD-lite, Angular, RxJS, Next.js) making it mostly distinct from sibling agents, with only minor overlap risk against a general web/design skill — not the minimal-conflict anchor 5 because terms like 'UI, component, page, CSS' are somewhat broad.	4 / 5
	Total	14 / 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-frontend/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.