Use when the task requires a transcript of speech with timestamps and speaker labels — from an audio file, a voice memo, or the audio track of a local video (it gets extracted automatically). Frames are never sent, so an hour costs about 2 cents and up to ~9 hours fit in one call. Not for describing what is visible on screen (go-watch) and not for remote URLs.
EnglishUse when the task requires seeing how a UI animation or micro-interaction actually moves — order, duration, easing of 200-400 ms transitions — from a local screen recording. Normal video analysis samples 1 frame per second and reports these as "appears instantly"; this skill slows the video so a cheap model sees every source frame, and returns timings in real milliseconds. For following what happens in a video use go-watch; for a still image use go-glance.
EnglishUse when the task requires knowing what happens in a video — a screen recording, a tutorial, a demo, a recorded call, or a public YouTube link — including what is said on the audio track. Claude has no video input; this delegates the watching to a cheap model and returns a text account. Not for frame-precise UI animation timing (go-scrub) and not for transcribing long audio (go-listen).
English
AGENT SKILLS ATLASExplore the listed skills and choose the workflows that fit your task.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Go Listen
Use when the task requires a transcript of speech with timestamps and speaker labels — from an audio file, a voice memo, or the audio track of a local video (it gets extracted automatically). Frames are never sent, so an hour costs about 2 cents and up to ~9 hours fit in one call. Not for describing what is visible on screen (go-watch) and not for remote URLs.
Go Scrub
Use when the task requires seeing how a UI animation or micro-interaction actually moves — order, duration, easing of 200-400 ms transitions — from a local screen recording. Normal video analysis samples 1 frame per second and reports these as "appears instantly"; this skill slows the video so a cheap model sees every source frame, and returns timings in real milliseconds. For following what happens in a video use go-watch; for a still image use go-glance.
Go Watch
Use when the task requires knowing what happens in a video — a screen recording, a tutorial, a demo, a recorded call, or a public YouTube link — including what is said on the audio track. Claude has no video input; this delegates the watching to a cheap model and returns a text account. Not for frame-precise UI animation timing (go-scrub) and not for transcribing long audio (go-listen).
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 Go Listen 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.
- License details are not provided in these listings. Check the author’s terms before using the skills.