frontend-expert

Especialista Senior en Frontend (Next.js, React, Tailwind, FSD) para la construcción de interfaces. Úsalo cuando el usuario pida "nueva funcionalidad", "modifica el front", "crea un componente", "actualiza el diseño" o "refactoriza la UI".

Quality

83%

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

Quality

Content

82%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.

A well-structured, highly actionable skill body: an exact-order SOP with a concrete scaffold command, worked examples, strict directives, and a genuinely useful progressive-disclosure section backed by real reference files. Remaining gaps are a missing validation step in the workflow and minor navigation issues around reference paths and orphaned bundle files.

Suggestions

Add an explicit validation checkpoint to the SOP (e.g., after scaffolding, confirm the generated slice and its index.ts exist and that imports resolve before writing component code).

Fix reference link paths to be relative to the skill bundle (e.g., references/component-rules.md instead of frontend-expert/references/component-rules.md) so the links resolve from the installed skill directory.

Either link ai-documentation.md and tech-stack.md from the body (or remove them), and delete the empty styling-rules.md so every bundle file is discoverable and purposeful.

Dimension	Reasoning	Score
Conciseness	Nearly all body content is project-specific (FSD layering rules, the cn utility, the scaffold script, docs/domains workflow) and assumes Claude's competence, with only minor trimmable redundancy — component-rules.md and api-standards.md are each linked twice, and the persona opener and hydration-mismatch explanation restate things Claude already knows.	4 / 5
Actionability	Fully executable guidance: a copy-paste-ready scaffold command with flags plus a concrete instantiation in the examples section, exact file paths (docs/domains/INDEX.md, shared/lib/utils.ts), concrete import examples, and a verified component template — the examples cover the common cases.	5 / 5
Workflow Clarity	The 4-step SOP is clearly sequenced with a wait-for-completion checkpoint and the troubleshooting table provides error recovery, but there is no explicit validation step (e.g., verify scaffold output, run build/lint) after generating files, which the anchor-5 pattern requires.	4 / 5
Progressive Disclosure	A dedicated 'Referencias (Progressive Disclosure)' section signals one-level-deep, per-topic references and all four referenced files exist, but the link paths carry a 'frontend-expert/' prefix that does not match the bundle layout (references/…), and three bundle files (ai-documentation.md, tech-stack.md, empty styling-rules.md) are orphans undiscoverable from the body.	4 / 5
	Total	17 / 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 description: it clearly states the domain and stack, and gives an explicit 'use when' clause with five natural quoted trigger phrases. Its main weakness is that the 'what' is a single generic action (building interfaces) rather than an enumerated list of concrete capabilities.

Suggestions

Enumerate 2-3 concrete capabilities after the role statement (e.g. scaffolds features, creates Server/Client Components, integrates Server Actions) to lift specificity beyond the single generic action 'construcción de interfaces'.

Add a couple of common synonym triggers (e.g. 'página', 'pantalla', 'landing') to cover requests phrased differently than the five quoted phrases.

Dimension	Reasoning	Score
Specificity	Names the domain precisely ('Next.js, React, Tailwind, FSD') but lists only one generic action — 'para la construcción de interfaces' — with no enumeration of concrete capabilities, matching the 'domain and 1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	Explicitly answers both what (frontend specialist for building interfaces, with the stack enumerated) and when ('Úsalo cuando el usuario pida…' with concrete trigger phrases), matching the anchor-5 example pattern exactly.	5 / 5
Trigger Term Quality	Five quoted natural phrases users would actually say ('nueva funcionalidad', 'modifica el front', 'crea un componente', 'actualiza el diseño', 'refactoriza la UI') give good coverage, but synonyms and other common asks (e.g. 'página', 'pantalla', 'arregla un bug') are missing, so it falls short of the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	The triggers ('crea un componente', 'actualiza el diseño', 'refactoriza la UI') carve a clear frontend niche with minimal conflict risk, but 'nueva funcionalidad' alone is generic enough to overlap with a backend or fullstack skill.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 7 missing, 7 deeper-than-1-level	Warning
referenced_paths_exist	Referenced path issues: 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: alpacapurpura/ap_sales_agent
Path: .agents/skills/frontend-expert/SKILL.md
Commit: d31f7bc

Reviewed: 1 hour 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.