Arthur CHENAIS
Community@fullya99 · Paris
Ingénieur Cloud & IA
Agent Skills by Arthur CHENAIS
Showing 13 vetted skills indexed across 1 GitHub repositories.
fullya99gstack
Automates QA testing and site verification through a persistent headless Chromium browser CLI.
fullya99ui
Generate UI components from text, images, or Figma using Stitch and Magic MCP.
fullya99design-to-code
Convert Figma designs into accessible, responsive components with mapped CSS and design tokens.
fullya99qa
Systematically test web applications and produce structured QA reports with screenshots and health scores.
fullya99setup-browser-cookies
Import cookies from installed Chromium browsers into a headless Playwright browse session.
fullya99components
Discovers and catalogs design system components from Storybook or static code analysis.
fullya99review
Reviews pull request diffs against main for SQL safety, race conditions, and LLM trust boundary issues.
fullya99plan-ceo-review
Reviews implementation plans with scope-mode selection, error mapping, and adversarial edge-case analysis.
fullya99retro
Analyzes git commit history to generate weekly engineering retrospectives with per-contributor metrics and trends.
fullya99a11y
Audits source code or live URLs against WCAG 2.1 AA and generates scored accessibility reports.
fullya99browse
Controls a persistent headless Chromium browser for QA testing and site verification.
fullya99ship
Automates merging, testing, versioning, committing, and pull request creation for feature branches.
fullya99plan-eng-review
Reviews implementation plans interactively across architecture, code quality, tests, and performance.
Frequently Asked Questions About Arthur CHENAIS
FAQPage SchemaWhat tasks can I accomplish with Arthur CHENAIS's skills?▼
You can QA test web apps with a fast headless browser, generate UI components via Google Stitch and 21st.dev Magic MCP, convert Figma designs to code, audit WCAG 2.1 AA accessibility, catalog design system components, review PR diffs, run engineering retrospectives, and execute a full ship sequence with version bumps and PRs.
Who are these skills designed for?▼
Front-end engineers, QA testers, design system maintainers, and engineering leads. The plan-ceo-review and plan-eng-review skills target founders and engineering managers who need scope challenges or rigorous execution-plan validation, while retro serves team leads tracking per-person contributions.
How do the QA and browser testing skills work in practice?▼
The gstack/browse skills navigate any URL at roughly 100ms per command, interact with elements, diff before/after states, and capture annotated screenshots. The qa skill adds three modes—full, quick smoke, and regression—while setup-browser-cookies imports sessions from Chrome, Arc, Brave, or Edge for authenticated pages.
What are the prerequisites and dependencies?▼
UI generation requires Google Stitch, 21st.dev Magic MCP, and Figma MCP access; design-to-code needs Figma MCP and a Figma URL or node-id. Component discovery uses Storybook MCP or static analysis. All skills run through Bash, Read, Write, Edit, Grep, and Glob permissions.
Are these skills free and open source?▼
The skills are published publicly on the fullya99 GitHub profile with versioned frontmatter (e.g., ui 2.0.0, retro 2.0.0). No licensing fee or paid tier is specified in the manifest; external services like Figma MCP or Google Stitch follow their own terms.