--- layout: tap site_name: quora tap_name: feed-jp description: "Quora Japan homepage feed — questions + answer snippets from the explore feed. Each question is a L3/L5 signal container by construction." intent: read columns: [] args: [] args_json: | {} health_json: | {"min_rows":3,"non_empty":["title"]} example_args: "" source_url: https://github.com/LeonTing1010/tap-skills/blob/main/community/quora/feed-jp.plan.json license: MIT ---

What it does

Quora Japan homepage feed — questions + answer snippets from the explore feed. Each question is a L3/L5 signal container by construction.

Install Taprun once

Taprun ships as a single MCP server exposing a catalog of compiled taps. One-time setup on macOS / Linux:

brew install LeonTing1010/tap/taprun
tap mcp connect

Or drop this into your claude_desktop_config.json (works identically in Claude Code, Cursor, Cline, Windsurf — any MCP host):

{
  "mcpServers": {
    "tap": {
      "command": "tap",
      "args": ["mcp", "start"]
    }
  }
}

Call quora/feed-jp

Terminal, once installed:

tap run quora/feed-jp

From the MCP host — exact same compiled plan, deterministic replay, zero LLM tokens:

tap.run({ site: "quora", name: "feed-jp" })

Why compile it once

This plan was forged once — the AI read quora, picked stable structural addresses (JSON-LD, ARIA, RSS, or declared API endpoints, in that priority order), and saved them to a .plan.json. Every replay since then has used zero LLM tokens. When quora ships a site change that breaks the extraction, tap verify surfaces it before your data goes stale — not after your pipeline silently writes garbage for a week.