dejanvasic85

Document patterns for crawling dribl.com fixtures website using playwright-core with direct API calls (Cloudflare bypass via browser context) to extract clubs and fixtures data. Covers ID resolution, round-based extraction, and transformation phases.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

Creates and maintains implementation plans. This skill should be used when the user asks to create a plan, document a feature, or track implementation progress for a task. Plans are stored in docs/plans/ and follow the project's established conventions.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

End-to-end workflow for running and verifying the WSC fixture pipeline — crawling fixtures/results from Dribl and syncing to local JSON files. Use this skill when asked to crawl, sync, or verify fixtures for Williamstown SC teams, run the fixture pipeline, or validate fixture output data.

A headless CMS that provides a flexible content model and powerful APIs. Use for structured content management with type-safe queries for Williamstown SC.

Address review feedback on an existing GitHub pull request. Use when Codex needs to inspect PR comments, decide which suggestions to implement or push back on, make and verify scoped fixes, reply in the relevant threads, and resolve addressed review threads.

Generate a detailed execution plan directly from an idea file. Searches the codebase first, asks only what it cannot infer, then writes the plan. Use when the user says "create plan", "plan this idea", "plan the work", or invokes /plan-from-idea.

Scan git logs for a date range and produce a categorised invoice line-item list. Classifies commits as Maintenance (framework upgrades, bug fixes) or Feature work (new functionality, with size estimates). Use when the user says "generate invoice", "invoice from git", "what did I work on", or invokes /git-invoice.

Scan planning documents, parse YAML frontmatter, and regenerate docs/planning/*/_index.md dashboard files with current pipeline status summaries.

Capture a raw idea quickly into docs/planning/ideas/ with a date-prefixed filename and YAML frontmatter. Use when the user says "I have an idea", "capture idea", "new idea", or invokes /plan-idea.

Use when working with icons in any project. Provides CLI for searching 200+ icon libraries (Iconify) and retrieving SVGs. Commands: `better-icons search <query>` to find icons, `better-icons get <id>` to get SVG. Also available as MCP server for AI agents.

Fix failing Renovate dependency-upgrade pull requests with minimal, evidence-based changes. Use for CI failures in Renovate PRs, dependency compatibility breaks, lockfile drift, peer mismatch, or tooling version issues.

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

Token-first frontend design system with Tailwind v4 and CSS variables (light/dark only)

Reliable patterns for crawling dribl.com fixtures using playwright-core to establish Cloudflare clearance, then making direct mc-api.dribl.com API calls (via page.evaluate(fetch(...))) instead of driving the SPA. Covers hashed-ID resolution, round-based extraction, table extraction, and boundary validation.

Fix failing Renovate dependency-upgrade pull requests with minimal, evidence-based changes. Use for CI failures in Renovate PRs, dependency compatibility breaks, lockfile drift, peer mismatch, or tooling version issues.

Fix failing Renovate dependency-upgrade pull requests with minimal, evidence-based changes. Use for CI failures in Renovate PRs, dependency compatibility breaks, lockfile drift, peer mismatch, or tooling version issues.

Create a new blog post MDX file in the correct dated directory with proper frontmatter. Use when writing a new blog post, publishing a technical article, sharing an opinion piece, or documenting a solution.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.