Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Frontend Engineering

ASecurity

Use when building, styling, fixing, or reshaping an interface, component, page, or frontend interaction. Use ui-ux-review for a read-only assessment of existing UI.

2 stars
0 votes
0 copies
2 views
Added 9/19/2026
ai-agentsdebuggingapifrontendbackend

Works with

api

Security Analysis

A100/100

Scanned 9/19/2026

$npx -y skills add adtn0810/truestack --skill frontend-engineering --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Frontend Engineering?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Frontend Engineering
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/adtn0810-frontend-engineering/badge)](https://www.skillsdirectory.com/skills/adtn0810-frontend-engineering)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: frontend-engineering
description: Use when building, styling, fixing, or reshaping an interface, component, page, or frontend interaction. Use ui-ux-review for a read-only assessment of existing UI.
---

# Frontend engineering

Build the requested experience within the product's design language and actual frontend stack. Inspect the changed route, shared components, tokens, state/data conventions, assets, and build configuration first. Reuse working patterns; do not upgrade frameworks or introduce a component library as a side effect.

For a new interface or requested redesign, choose a visual direction tied to the product, audience, and content. Set a coherent type scale, spacing rhythm, hierarchy, and restrained color system. Put emphasis where the user's primary task needs it. Avoid decorative cards, gradients, motion, or oversized headings that obscure the information. Preserve existing visual identity on a narrow fix.

Model the user journey and its states: initial, loading, empty, success, validation error, service failure, disabled, and permission-limited where relevant. Keep input during recoverable errors. Prevent duplicate submissions when they create duplicate effects. Make optimistic updates reversible and stale responses harmless. Match local, shared, and server state ownership to the application's existing architecture; do not impose a framework-specific state ladder.

Use semantic elements and appropriate labels. Support keyboard navigation, visible focus, sensible tab order, and focus management for dialogs and route changes. Check contrast, zoom/reflow, reduced motion, and accessible error feedback in the affected UI. ARIA should supplement native semantics when needed.

Check that users can find the requested actions, identify the entity they are editing, and distinguish an unsaved preview from persisted settings. Compare initial defaults with validation rules and existing saved state; explain real state differences instead of dismissing a contradictory UI as user error. Exercise save and reload when persistence matters. Preserve existing capabilities during simplification. If the user requests a preview for approval, prepare it before implementing that design; do not impose this gate on other UI work.

Keep component responsibilities clear and avoid unnecessary derived state, render side effects, data waterfalls, and unbounded DOM lists. Confirm compiler and framework capabilities before using version-specific APIs or adding manual memoization. Profile a reported slowdown with systematic-debugging before optimizing it.

Use existing repository checks and test-verify for the changed behavior. When browser access is available, exercise the actual flow, inspect loading/error behavior, check console/runtime errors, and view relevant mobile and desktop widths. Review screenshots against the intended hierarchy and layout; a passing build does not prove visual quality. Use available accessibility tooling plus a keyboard walkthrough where the interaction warrants it.

Report what the user can now see or do, the checks actually performed, and concrete limitations such as an unavailable backend or browser. Do not claim screenshots, live integration, or accessibility conformance that was not established.

Attribution

adtn0810adtn0810
View sourceSee grades on GitHubMore from adtn0810 →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →