From upwork-scraper
Fetch and display your Upwork Best Matches. Use when the user wants to see their personalized job recommendations from Upwork, or mentions "best matches", "my jobs", "job recommendations".
How this skill is triggered — by the user, by Claude, or both
Slash command
/upwork-scraper:best-matchesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Fetch the user's personalized Upwork Best Matches using the MCP tools.
Fetch the user's personalized Upwork Best Matches using the MCP tools.
This plugin provides MCP tools (prefixed mcp__upwork-scraper__* or called as tool_* below) that control a Camoufox browser for scraping Upwork. The plugin works from any directory.
If MCP tools are NOT available (you don't see mcp__upwork-scraper__* in your tools): the MCP server failed to start, likely because dependencies aren't installed. Tell the user:
The plugin's MCP server is not connected. Run
/upwork-scraper:setupto install dependencies, then restart Claude Code.
Do NOT try workarounds (Chrome extension, curl, direct DB access). Only the MCP tools work.
Check session: Call tool_session_status to check if the browser session is authenticated.
tool_start_session(headless=false). A browser window will open. Tell the user to log in to Upwork and solve any CAPTCHAs. When the user confirms, call tool_check_auth to verify.Fetch jobs: Call tool_fetch_best_matches(max_jobs=$ARGUMENTS or 20, force_refresh=true).
Present results as a clean numbered list with:
Offer next steps: Ask if they want to:
npx claudepluginhub southlab-ai/claude-plugin-marketplace --plugin upwork-scraperLists career-ops skills directory, checks job search state from data files, suggests next action like profile setup or job evaluation based on progress.
Automates job search with 34 tools: search, auto-apply, tailored resume generation, application tracking, salary intelligence, and recruiter outreach via the JobGPT MCP server.
Searches and ranks job listings using a connector-first strategy (Indeed MCP, browser, or manual fallback). Normalizes results into a standard schema for ranking.