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?".
EnglishAdaptively 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.
EnglishDeclare 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.
English
AGENT SKILLS ATLASIncludes Tap Capture Replay, Tap Triggers, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
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.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Tap Capture Replay skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.