Summary
If you're testing or automating Amazon Fire TV apps, this is your bridge to Vega's D-pad navigation model. The approach is disciplined: describe the UI tree to find the focused element, calculate your D-pad path in one shot, then describe again to verify. No touch gestures, no guessing from screenshots. The two-call loop keeps things deterministic. It's part of Software Mansion's Argent toolkit and has cleared three security audits, which matters when you're shipping automation into CI. The constraint is real though: you're working entirely through remote control simulation, so if your UI has complex focus traps or non-standard navigation, expect to iterate on those paths.
Install to Claude Code
npx -y skills add software-mansion/argent --skill argent-vega --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
