My Agent (aka Claude) Skills
npx skills add https://github.com/schalkneethling/webdev-agent-skills --skill frontend-securityInstallieren Sie diesen Skill über die CLI und beginnen Sie mit der Verwendung des SKILL.md-Workflows in Ihrem Arbeitsbereich.
A curated collection of Agent Skills for web development projects, focusing on web standards, semantic HTML, accessibility, security, and modern CSS practices.
Agent Skills are specialized knowledge packages that extend AI coding agents' capabilities with domain-specific expertise, best practices, and project patterns. Each skill contains:
Generates component skeletons for Drupal/Twig projects with web components and Miyagi validation. Includes JSON schema and mock data patterns.
Analyzes component dependencies and usage patterns. Provides search patterns for finding usage, checking removal safety, and auditing dependencies.
Provides a foundational set of CSS custom property tokens for design systems. Includes spacing, typography, color, and layout tokens that serve as a starting point for new projects and can be customized per project.
CSS authoring guidance emphasizing web standards, accessibility, and performance. Includes patterns for modern CSS syntax, logical properties, and responsive design.
Comprehensive security audit capability for frontend codebases. Identifies XSS, CSRF, DOM vulnerabilities, CSP misconfigurations, and dependency issues. Supports React, Astro, Twig, Node.js, and vanilla web platform. Based on OWASP security guidelines with detailed reference documentation for common vulnerability patterns.
Write tests that start with acceptance criteria, then add implementation tests for robustness. Use when writing unit tests (Vitest), end-to-end tests (Playwright), visual regression tests, or accessibility tests. Emphasizes user-centric testing, semantic locators, accessibility validation, and the balance between acceptance and implementation testing.
Guidance for well-considered semantic HTML. Emphasizes native HTML elements over ARIA, proper document structure, and accessibility foundations.
Copy this prompt to add the installation script:
Please copy the install script from https://github.com/schalkneethling/webdev-agent-skills/blob/main/scripts/install-skills.sh
Save it to: scripts/install-skills.sh in the current project root
Then make it executable: chmod +x scripts/install-skills.sh
Copy this prompt to install specific skills:
Please install these Agent Skills using the install script:
Skills to install: css-coder, semantic-html, frontend-security, frontend-testing
Run: bash scripts/install-skills.sh "css-coder,semantic-html,frontend-security,frontend-testing"
Install to: .claude/skills/ (default) or specify a different directory as the second argument
Notes:
.claude by convention, but you can use a different name (e.g., .ai, .agent, etc.)[target-dir]/[skill-name]/To commit customized skills with your project:
.claude/skills/ in version controlTo keep skills out of version control:
.claude/skills/ to your .gitignoreIf you use Cursor IDE, this repository includes a sync script that converts skills to Cursor's rule format (.mdc files).
Copy this prompt to add the sync script to your project:
Please copy the sync script from https://github.com/schalkneethling/webdev-agent-skills/blob/main/scripts/sync-skills-for-cursor.sh
Save it to: scripts/sync-skills-for-cursor.sh in the current project root
Make the script executable: chmod +x scripts/sync-skills-for-cursor.sh
The script reads skills from .claude/skills/ and converts them to .cursor/rules/:
./scripts/sync-skills-for-cursor.sh
This will:
SKILL.md files and reference docs from .claude/skills/*/.mdc format.cursor/rules/*.mdcRun this script whenever you update your skills to keep Cursor in sync.
When installed, each skill follows this structure:
.claude/skills/
├── skill-name/
│ ├── SKILL.md # Core instructions and guidance
│ ├── README.md # (optional) Additional context
│ └── references/ # (optional) Supporting documentation
│ ├── patterns.md
│ ├── examples.md
│ └── ...
Available skills and their focus:
| Skill | Purpose | Files |
|---|---|---|
css-coder |
CSS authoring with web standards, accessibility, and performance | SKILL.md, references/ |
css-tokens |
Design system token foundation (spacing, typography, color) | SKILL.md, references/tokens.css |
semantic-html |
Well-considered semantic HTML and accessibility foundations | SKILL.md, references/ |
frontend-security |
Security audit for XSS, CSRF, DOM vulnerabilities, and more | SKILL.md, references/ (9 docs) |
frontend-testing |
Acceptance and implementation testing strategies | SKILL.md, references/ |
component-scaffolding |
Drupal/Twig component skeletons with web components | SKILL.md, references/ |
component-usage-analysis |
Component dependency and usage pattern analysis | SKILL.md, references/ |
Once installed, skills are automatically available to AI agents when working in your project. The agent will reference the skills when relevant to the task at hand.
You can customize installed skills for your specific project needs - they serve as starting points, not rigid templates.
Contributions are welcome! To add a new skill:
Fork this repository
Create a skill directory with this structure:
your-skill-name/
├── SKILL.md # Main skill instructions
└── reference/ # Supporting materials (optional)
├── examples/
└── patterns/
Write clear SKILL.md content that includes:
Submit a pull request with:
MIT - see LICENSE file.