Stats
Actions
Tags
From upwork-scraper
Search Upwork jobs with keywords and filters. Use when the user wants to find specific types of freelance jobs, mentions "search jobs", "find work", "look for jobs on Upwork".
How this skill is triggered — by the user, by Claude, or both
Slash command
/upwork-scraper:searchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Search for Upwork jobs using the MCP tools with the user's query.
Search for Upwork jobs using the MCP tools with the user's query.
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. If not active, call tool_start_session and guide the user through login.
Parse the query: The user's input is in $ARGUMENTS. Extract:
Search: Call tool_search_jobs with the parsed parameters.
Present results as a clean numbered list showing:
Offer to refine: Ask if they want to:
npx claudepluginhub southlab-ai/claude-plugin-marketplace --plugin upwork-scraperAutomates job search via MCP server: search jobs with filters like title/location/salary/remote, auto-apply, generate tailored resumes, track applications, get salary intel, outreach recruiters.
Searches LinkedIn, Indeed, GitHub via Nimble Web Search Agents to find qualified candidates. Accepts job descriptions or role titles, returns ranked list.
Searches and ranks job listings using a connector-first strategy (Indeed MCP, browser, or manual fallback). Normalizes results into a standard schema for ranking.