Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →majiayu000/agent-eyes
Visual context analyzer for AI agents. Provides screenshots, accessibility scans, DOM snapshots, and element descriptions for web pages.
Passed 18 of 21 test cases with the skill, and 3 of 21 without it.
and 21 more in the full report
18 fixed3 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need to pull together a complete visual context bundle (screenshot, accessibility findings, DOM snapshot) for http://localhost:3000 in compact format. What is the single high-level command to execute?
| Checked | Without skill | With skill |
|---|---|---|
| Uses agent_eyes.py context subcommand. | Missed | Passed |
| Includes the --compact flag. | Passed | Passed |
The instructions your model reads when the skill loads.
Visual context analyzer for web pages. Provides AI agents with the ability to "see" web applications through screenshots, accessibility scans, DOM snapshots, and element descriptions.
uv package manager (recommended)playwright install chromiumAll commands support --compact / -c flag for token-efficient output:
| Mode | Screenshot | DOM | A11y | Total Tokens |
|---|---|---|---|---|
| Standard | Base64 inline | depth=5, 20 children | Full violations | ~500K+ |
| Compact | File path only | depth=3, 10 children | Summary only | ~3-5K |
Use compact mode when context window size is a concern (which is most of the time).
# Compact context - reduces ~500K tokens to ~3-5K tokens
uv run $SKILL_DIR/agent_eyes.py context http://localhost:3000 --compact
# Compact screenshot - always saves to file, never returns base64
uv run $SKILL_DIR/agent_eyes.py screenshot http://localhost:3000 --compact
# Compact a11y - returns summary + top N issues only
uv run $SKILL_DIR/agent_eyes.py a11y http://localhost:3000 --compact
# Compact DOM - stricter limits on depth and children
uv run $SKILL_DIR/agent_eyes.py dom http://localhost:3000 --compact
All commands use uv run for automatic dependency management:
test cases passed, vs 3 / 21 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.