Scenario 01
QA documentation
Agent task involves capturing the current state of a UI flow for a QA report.
Capture the current state of our checkout flow for the QA report.
Let Antigravity Agents Capture Visual Evidence, Not Just Text
Antigravity's Browser Subagent can control Chrome — but capturing, annotating, and organizing screenshots into a structured report is a different job. Website Screenshot Agent reads a Markdown capture plan, visits each URL, takes screenshots, handles authenticated pages, and assembles a documented report the team can review and share.
How it works
Agent tasks that trigger doc-screenshot-agent automatically
These are the prompts where Antigravity's Agent Manager routes to doc-screenshot-agent — when the task needs visual evidence, not just text.
01 · User
Prompt sent
You type a task in Antigravity. No special syntax needed.
02 · Agent Manager
Task analysis
Gemini 3 plans the task and detects knowledge cutoff risk.
03 · SKILL.md router
Semantic match
SKILL.md description matches the task. The skill is loaded.
04 · Skill
Skill execution
The matched skill runs and fetches or processes the data.
05 · Output
Cited answer inline
Structured answer with source links returned to the agent.
Scenario 02
Before/after comparison
Agent needs to document a UI change with visual evidence.
Capture the login page before and after the redesign for the release notes.
Scenario 03
Competitor UI analysis
Agent task involves capturing and analyzing a competitor's UI for a design review.
Screenshot Linear's issue detail page and extract the UI patterns used.
How it works
What doc-screenshot-agent adds to Antigravity
Six capabilities that let agents capture and reason over visual evidence without leaving the IDE.
Visual evidence capture
Agent captures screenshots of any URL as part of a documentation or QA task.
Element-level capture
Targets specific UI elements or page sections — not just full-page screenshots.
Screenshot-to-text
Extracts readable text from captured screenshots for further agent reasoning.
Before/after comparison
Agent captures states before and after a change for visual diff documentation.
Artifact storage
Screenshots are stored and referenced by URL in the agent's output.
SKILL.md auto-routing
Activated when the agent task involves visual documentation, QA, or UI verification.
Use Cases
Real tasks, real workflows
How developers use this skill inside Antigravity — from quick lookups to complex multi-step workflows.
01
QA documentation
Agent task involves capturing the current state of a UI flow for a QA report.
❯Capture the current state of our checkout flow for the QA report.
02
Before/after comparison
Agent needs to document a UI change with visual evidence.
❯Capture the login page before and after the redesign for the release notes.
03
Competitor UI analysis
Agent task involves capturing and analyzing a competitor's UI for a design review.
❯Screenshot Linear's issue detail page and extract the UI patterns used.
Installation
Three steps to structured visual capture inside Antigravity
Once installed, the Agent Manager triggers doc-screenshot-agent when a task requires visual evidence — the agent reads a capture plan and produces a documented report automatically.
Method 1 · Terminal
Install via command line
Clone the Felo skills repo and copy the skill into your global Antigravity skills directory.
# Clone the Felo skills repository
git clone https://github.com/Felo-Inc/felo-skills.git
# Copy this skill to your global Antigravity skills folder
cp -r felo-skills/doc-screenshot-agent ~/.gemini/antigravity/skills/Installs to ~/.gemini/antigravity/skills/ — available across all your projects
Method 2 · Agent prompt
Let the agent install it for you
Paste this prompt directly into Antigravity. The agent clones the repo and copies the skill automatically.
Paste into Antigravity
Install https://github.com/Felo-Inc/felo-skills into my global Antigravity skills directory.
The agent handles cloning, copying, and directory setup — no terminal needed
1
Copy the skill into .agent/skills/
Clone the Felo skills repo and copy doc-screenshot-agent into .agent/skills/ for team-wide access via Git. The SKILL.md description activates it for tasks that require visual page capture or UI documentation.
2
Write a Markdown capture plan
Create a .md file listing the URLs, sections, and evidence you want captured. The skill reads the plan, visits each page in order, and organizes screenshots according to your instructions — including authenticated pages when credentials are set.
3
Agent delivers a structured visual report
The skill produces a Markdown report with embedded screenshots, organized by your capture plan. The Agent Manager can include this report in a larger deliverable — a competitive analysis, a QA summary, a design review — without any manual screenshot work.
No configuration needed. The SKILL.md file inside the skill folder tells Antigravity's Agent Manager when to activate it. Once the folder is in place, the agent routes to the skill automatically based on your prompt.
FAQ
Website Screenshot Agent in Google Antigravity — FAQ
The Browser Subagent is interactive — it clicks, scrolls, and responds to the agent's instructions in real time. doc-screenshot-agent is batch-oriented: give it a Markdown capture plan and it executes the full list, producing a structured report. It's better suited for systematic documentation tasks where you know exactly what you need to capture.
Give Antigravity agents a visual evidence layer for audits, reviews, and monitoring
Install doc-screenshot-agent in .agent/skills/ and let the Agent Manager capture, annotate, and report on web pages as part of any research or QA workflow.
One API key. Commit to .agent/skills/ and your agents can document the visual web — authenticated pages included.
More Antigravity Skills
