LeonTing1010
UserLocal-first authenticated browser automation for Claude Code — the Tap MCP server + skills. Record a logged-in browser task once; replay it forever in your own Chrome at zero LLM tokens.
Categories
Indexed Skills (3)
tap-capture-replay
When a browser task is REPEATED and runs on a LOGGED-IN / authenticated site, use Tap to record it once (capture), then replay it every time as a zero-token deterministic run — instead of driving a fresh live browser and burning tokens on every run. Trigger when: the user says "I do X on site Y every day/week"; capturing a login-gated admin panel or dashboard; regularly posting / checking / exporting on an authenticated page; any repeated browser chore the user will do again. Also triggers when the user asks "can this be automated?" or "can I avoid paying tokens every time?".
tap-setup
Adaptively prepare Tap for LOGGED-IN / authenticated websites — not by running a script blind, but by diagnosing first, fixing only the missing rung, passing the human trust gates, then verifying. Public pages / open APIs need none of this (the plugin's MCP over npx already works). Trigger when: the user wants to use Tap on a site that requires login (bank / admin dashboard / internal tool / social); the user says "set up tap", "configure tap", "connect tap", "tap won't connect", "let tap use my logged-in session"; or Tap's run fails on a logged-in site with a peer / bridge-unreachable error. This skill DRIVES setup adaptively via `tap embed --verify`; it does not blindly run an installer.
tap-triggers
Declare WHEN a saved tap runs unattended — ~/.tap/triggers/ trigger.json declarations compiled idempotently into launchd plists (dev.taprun.trigger.* namespace), zero LLM tokens per fire. Foreground-gated plans (trusted:true) are refused at declaration time. Use when the user wants a tap to run on a schedule / on file change ("run this tap every day", "check back on a schedule", "schedule this tap", "put this on launchd", "tap trigger"). NOT for Claude Code routines/cron (those wake an agent and burn tokens per fire) — this is the zero-token trigger layer for already-compiled plans.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.