opencli-usage
OpenCLI provides a unified interface for interacting with websites, desktop applications, and external command-line tools. It acts as an orientation layer for agents to discover available adapters, manage browser sessions, and execute commands without manual screen-scraping.
Is opencli-usage safe to install?
Review the source first: our audit of opencli-usage's source files found 21 shell commands, 1 external URL, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The tool executes shell commands, manages local browser sessions, and interacts with external CLI tools. It reads and writes to local configuration files and cache directories.
How we audit skills: our security review methodology.
Who is this skill for?
AI agents and developers who need to automate interactions with web services, Electron apps, or external CLI tools through a standardized command surface.
What can you do with it?
- Discovering available site adapters and commands via JSON output
- Executing commands against web services using specific strategies like PUBLIC, COOKIE, or UI
- Managing browser sessions for automation and scraping
- Integrating external CLI tools like gh or docker into a unified workflow
- Developing and validating custom site adapters
- Repairing broken adapters using trace logs
How good is this skill?
Quality score: 5/10. The documentation is comprehensive, providing clear instructions for installation, usage, and troubleshooting. It explicitly defines the tool surface and provides necessary context for agent integration.
What does the skill file contain?
# opencli-usage OpenCLI turns any website, Electron desktop app, or external CLI into a uniform `opencli <site> <command>` surface that agents can drive without screen-scraping. This skill is the orientation layer — once you know what you want to do, load one of the specialized skills below. ## The three pillars - **Adapter commands** — `opencli <site> <command> [...]`. Built-in adapters live in `clis/`, user adapters in `~/.opencli/clis/`. Each is backed by a strategy (`PUBLIC | COOKIE | INTERCEPT | UI | LOCAL`) that tells you whether a Chrome session is needed. - **Browser driving** — `op...
Frequently asked questions
How do I find out which commands are available for a specific site?
Run 'opencli list -f json' to get a machine-readable list of all commands, or 'opencli <site> --help' for site-specific details.
Do all OpenCLI commands require a browser?
No. Commands with the 'PUBLIC' or 'LOCAL' strategy do not require a browser. Only 'COOKIE', 'INTERCEPT', and 'UI' strategies require a browser session.
How can I debug a failing adapter command?
Re-run the command with the '--trace retain-on-failure' flag to generate a trace block and identify the source path for repair.
Where are user-defined adapters stored?
Private user adapters are stored in '~/.opencli/clis/<site>/<command>.js'.
Related skills
find-skills
2.3MUsers seeking to extend agent capabilities with specialized tools, workflows, or knowledge packages
The find-skills skill enables agents to search for, discover, and install modular packages from the open agent skills ecosystem using the Skills CLI.
agent-browser
506.7KAI agents and developers requiring programmatic web interaction, exploratory testing, or automation of Electron desktop applications
The agent-browser CLI provides browser automation for AI agents using Chrome or Chromium via CDP. It supports page navigation, form interaction, data extraction, and testing. The tool utilizes accessibility-tree snapshots and element references for interaction.
video-edit
338.7KUsers of the RunComfy CLI who need to automate video editing tasks like restyling, background swapping, or motion transfer
The video-edit skill acts as a router for the RunComfy CLI, selecting between Wan 2.7 Edit-Video, Kling 2.6 Pro Motion Control, and Lucy Edit Restyle models based on user intent to perform video transformations.
agentspace
324.0KDevelopers and AI agent users who need to share, monitor, or collaborate on agent-generated files and workspaces in real-time
Agentspace provides a mechanism to share local agent files, logs, and artifacts via a live browser-accessible URL. It enables remote viewing, commenting, and editing of specified local paths through the ascli command-line tool.