--- layout: tap site_name: scys tap_name: input-keyword description: "Input search keyword into SCYS search box (requires login)" intent: write columns: - status - selector args: - name: keyword type: string description: "Search keyword" args_json: | {"keyword":{"type":"string","required":true,"description":"Search keyword"}} health_json: | {"min_rows":1,"non_empty":[]} example_args: "" source_url: https://github.com/LeonTing1010/tap-skills/blob/main/community/scys/input-keyword.plan.json license: MIT ---

What it does

Input search keyword into SCYS search box (requires login)

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 scys/input-keyword

Terminal, once installed:

tap run scys/input-keyword

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

tap.run({ site: "scys", name: "input-keyword" })

Why compile it once

This plan was forged once — the AI read scys, 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 scys 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.

Related scys taps

tapdescription
scys/extract-resultsExtract search results from SCYS Pinia store (requires login)
scys/articleRead SCYS article with title, author, stats, full text
scys/trigger-searchTrigger search on SCYS (Vue component method or form submit, requires login)
scys/navNavigate to SCYS homepage (requires login)
scys/searchSearch SCYS by keyword (requires login)