agent-skills

v0.5.0

A growing set of Claude Code skills. /uiux builds UI under strict UX rules and reviews it or audits a live site. /security runs an authorized security review of an app you own.

Claude Code2 Skills

By MarvelCollinLicense: MIT0 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes: Claude Code
Parsed components: 2 skill or MCP entries
Source updated: Oct 2, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install agent-skills for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install agent-skills-14@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/MarvelCollin/agent-skills

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

agent-skills/

├── .claude-plugin/plugin.json
├── skills/security/SKILL.md
└── skills/uiux/SKILL.md

Included Skills2

securityskills/security/SKILL.md

Run an authorized security review of a web app you own or are cleared to test, especially local and dev builds. Dev mode finds the running dev server, writes the scope itself and screens the build end to end with no setup questions. Works in phases that confirm authorization and scope, map the attack surface, then test for common vulnerability classes (injection, broken auth and access control, SSRF and server-side, XSS and client-side, session handling, business logic, misconfiguration, exposed secrets, API and LLM issues) against the OWASP WSTG and ASVS, verify each finding with evidence to kill false positives, then write a report with severity and remediation. Can also do a static secure-code review without running anything.

uiuxskills/uiux/SKILL.md

Build and audit web UI with real UX discipline. When building or changing UI, apply hard rules (pastel palette unless the user picks colors, no stat cards with icon tiles, no icons in rounded squares, no pill badges, search and filters on every table column, overlays that size to their content, custom scrollbars, date pickers, selects and other controls instead of browser built-ins, specific and consistent layouts, no semicolons or em dashes in copy, fast backend-paginated data loading with skeletons, real avatars instead of initials) plus navigation and color guidelines and Shneiderman's Eight Golden Rules, then review the result for ease of use, feel and navigation. Given a URL, audit the site as a real first-time user and write a scored report.

Plugin manifests1

.claude-plugin/plugin.json

{
  "name": "agent-skills",
  "displayName": "Agent Skills",
  "version": "0.5.0",
  "description": "A growing set of Claude Code skills. /uiux builds UI under strict UX rules and reviews it or audits a live site. /security runs an authorized security review of an app you own.",
  "author": {
    "name": "MarvelCollin",
    "url": "https://github.com/MarvelCollin"
  },
  "homepage": "https://github.com/MarvelCollin/agent-skills",
  "repository": "https://github.com/MarvelCollin/agent-skills",
  "license": "MIT",
  "keywords": [
    "claude-code",
    "skills",
    "ux",
    "usability",
    "accessibility",
    "wcag",
    "user-testing",
    "audit",
    "security",
    "pentest",
    "appsec",
    "owasp"
  ],
  "skills": "./skills/"
}