Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Frontend

ASecurity

Frontend decision boundaries. Constrain decisions, not implementations. Use for web UI components, pages, forms, client-side state, and frontend code.

6 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsrefactoringapifrontendperformance

Works with

cliapi

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add vorlaxen-labs/Agent-Skills --skill frontend --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Frontend?

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

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

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: web-frontend
description: >-
  Frontend decision boundaries. Constrain decisions, not implementations.
  Use for web UI components, pages, forms, client-side state, and frontend code.
---
# Core Principle

**Constrain decisions, not implementations.**

These rules add frontend **decision boundaries** on top of global standards.

They do not prescribe components, hooks, state libraries, or styling approaches. Follow the project.

---

# Hard Rules — Read First

1. **Never hallucinate.** Do not invent components, hooks, routes, props, endpoints, or styling tokens. Read the codebase first.
2. **Match risk to action.** Stop and ask for API contracts, state shape, or auth — not for UI placement when the project already has a pattern. Read first, then proceed or ask.
3. **Do not change the project's frontend stack** unless the user explicitly asks.
4. **These rules constrain decisions only.** Implementation style comes from the existing codebase.

---

# Decision: Stack & Patterns

**Forbidden without explicit user request:**

- Introducing a new framework, UI library, or styling system
- Introducing a second state management system
- Introducing a second validation or data-fetching approach

**Required:** read existing frontend code and match its patterns before writing anything.

---

# Decision: Reuse vs Create

**Required before creating anything new:** search the repo for an existing component, hook, or utility.

**Forbidden:** duplicating something that already exists in the project.

---

# Decision: State Ownership

**Forbidden:** adding global state for data that belongs to a single component or page.

**Required:** follow the project's state management. If unknown, read existing components first.

---

# Decision: User-Facing Async Features

**Required outcome:** the user must never be left without feedback.

For async user-facing features, you must account for:

- In-progress state
- Failure state
- Empty state (when applicable)

**Not your decision:** how loading spinners, skeletons, or error UI look — follow the project.

**If unsure which states apply:** ask.

---

# Decision: Forms

**Required outcomes:**

- Input is validated before submission
- Errors are visible to the user
- Duplicate submission is prevented during in-flight requests
- User input is preserved on validation failure

**Not your decision:** which validation library or form pattern to use — follow the project.

**If validation approach is unknown:** find it in the codebase before writing.

---

# Decision: Accessibility

**Required outcome:** user-facing UI must be accessible.

**Forbidden:** shipping interactive UI that is keyboard-inaccessible or lacks proper labels/semantics.

**Not your decision:** specific ARIA patterns or component structure — follow the project and web standards.

---

# Decision: API Integration

**Required outcomes:**

- Network failures show user-visible feedback
- Raw API errors are not shown to users

**Forbidden:** inventing API endpoints or response shapes.

**Required:** read existing types, schemas, or API calls first.

---

# Decision: Performance Optimizations

**Forbidden without clear need:** adding memoization, virtualization, pagination, or debouncing.

**Required:** if performance work is needed beyond the task scope, describe it and ask before implementing.

---

# Decision: Scope

**Forbidden without approval:**

- Refactoring unrelated components
- Migrating the frontend to a new pattern or stack

**If unsure whether a change is in scope:** stop and ask.

Attribution

vorlaxen-labsvorlaxen-labs
View sourceMore from vorlaxen-labs →
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

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 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', ...

695601 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →