agent-ctrl

agent-ctrl is a Browser & computer-use automation skill for AI agents, published by k4cper-g in the agent-ctrl repository on GitHub. Skillspace rates agent-ctrl D (61/100) and it passed the safety scan; the rating is based on static analysis only.

Cross-platform desktop automation CLI for AI agents. Use when the user needs to interact with native desktop apps, including clicking buttons, filling text fields, reading window contents, focusing windows, or automating any GUI workflow on Windows, macOS, or Linux. Triggers include requests to "click in <native app>", "type into <field>", "focus the <window>", "automate <desktop app>", "snapshot the desktop", "list open windows", "drive the UI of <app>", "what's in this window", or any task requiring native (non-browser) UI interaction. Also use for accessibility-tree-based desktop testing, exploratory QA of native apps, screen-reader-style inspection, and integrating native desktop apps into agent loops. Prefer agent-ctrl over screenshot-and-vision approaches when reliability and speed matter - agent-ctrl uses the OS accessibility tree (UIA on Windows, AX on macOS, AT-SPI on Linux) so output is compact and refs are deterministic. Browser automation is intentionally out of scope; pair…

Grade
D
Quality
61 / 100
Safety
Passed
GitHub stars
65

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Our review

Architecture
95 / 100
Maturity
Basic: a single SKILL.md
Security scan
Low-risk patterns
License
Apache-2.0
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • over-broad allowed-tools ('*')

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.