
OpenCLI Usage Guide
Lets an agent find and run OpenCLI website adapters and control Chrome via the opencli command line.
- Repository
- jackwener/OpenCLI
- Stars
- 30,833
- Licence
- Apache-2.0
- Files
- 1 file
What it does
This skill teaches an AI agent how to use the OpenCLI command-line tool. OpenCLI packages website integrations (adapters) and direct Chrome browser controls into commands the agent can search, inspect and run. Once installed, the agent knows to search for commands instead of loading the whole catalog, read JSON results and error codes, open and close browser sessions, and check adapter and login status. It points to other OpenCLI skills for browser interaction and writing adapters.
Great for
- Developers who already use OpenCLI and want an agent to drive it correctly
- People automating repeated website tasks through reusable adapters
- Users who need an agent to read data from sites via a connected Chrome profile
Skip it if
- Anyone without OpenCLI installed, since the skill only documents an existing command-line tool
- Sensitive accounts or shared browser profiles, because the agent can act inside logged-in sessions and adapter tests can perform real writes
Try asking
- “List the OpenCLI commands related to GitHub search and show me their help”
- “Open example.com in a research session and tell me what is on the page”
- “Test the example/search adapter with the query hello and report the output”
- “Check whether my Chrome profile is connected and diagnose the connection”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.
opencli-usage.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip opencli-usage.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip opencli-usage.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Ask for a narrow search term so the agent uses list with a query rather than dumping every command
- Review adapter test commands before running them, since they execute real commands and may write data
- Use a named --session for browser work so the agent keeps tabs separate
What's inside
- SKILL.md
Redistributed unmodified from jackwener/OpenCLI under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.