Discover and invoke OpenCLI capabilities for websites and Chrome. Find commands, inspect schemas, interpret results and choose browser or adapter tools.
Intro in this page language first. The official description stays in its original wording; we do not rewrite SKILL.md.
What it does
Discover and invoke OpenCLI capabilities for websites and Chrome. Find commands, inspect schemas, interpret results and choose browser or adapter tools.
When to use it
The official description does not include a separate “Use when”. Per the spec, agents activate this skill when the task matches keywords in that description.
How agents load it
Per Agent Skills progressive disclosure: name and description load at startup (~100 tokens); the full SKILL.md body loads when the skill activates; scripts/, references/, and assets/ load only as needed. This file's sections: OpenCLI; Results; Browser; Adapters and installation.
File analysis
File analysis: instruction-only skill (SKILL.md). The agent loads the full body when activated.
Discover and invoke OpenCLI capabilities for websites and Chrome. Find commands, inspect schemas, interpret results and choose browser or adapter tools.
allowed-tools
Bash(opencli:*), ReadExperimental field; support depends on the client and does not grant permissions by itself.
DiscoverThe client exposes names and descriptions to the agent.
ActivateYour request or the task context selects the skill and loads its instructions.
Load resourcesReferenced scripts, documentation and assets are used when needed.
Choose the target agent and installation scope, keep referenced package files, then verify the skill appears in the client's catalog.
Ask your Agent to install
Copy these instructions to a compatible agent and confirm the target directory matches your client.
Install the agent skill "opencli-usage" into my project. The full SKILL.md and official description are at https://zicq.com/en/skills/skl-0841370d072416c7-Opencli-Usage.html
Save it as .cursor/skills/opencli-usage/SKILL.md or .claude/skills/opencli-usage/SKILL.md and keep the frontmatter name and description exactly as-is.
The CLI lets you choose the agent interactively. The default scope is the project; use -g for user scope. Confirm package availability with the discovery command, then use npx skills list to inspect installed skills.
Readable layout
---
name: opencli-usage
description: Discover and invoke OpenCLI capabilities for websites and Chrome. Find commands, inspect schemas, interpret results and choose browser or adapter tools.
allowed-tools: Bash(opencli:*), Read
---
# OpenCLI
OpenCLI exposes reusable website adapters and direct Chrome tools to agents.
```sh
opencli list search
opencli list --site github --limit 20
opencli github search --help -f json
```
`list [query]` searches command names and descriptions across built-ins and adapters.
Results are compact and paginated: `{ok:true,data:{commands,total,nextOffset?}}`.
Pass `--offset ` to continue. Inspect exact inputs using command help.
Do not hard-code the adapter catalog or dump all commands into context.
## Results
Commands default to JSON: `{ok:true,data:...}`. Failures produce a nonzero exit
code and `{ok:false,error:{code,message,hint?,...}}` on stdout. Logs use stderr.
Explicit `-f table|yaml|csv|md|plain` exports are available where command help lists
them. Help, version, completion and explicit plain exports retain their own formats.
Browser follow modes stream one JSON envelope per line.
Use error codes and supplied candidates/keys to recover. Unknown write outcomes
require inspecting state before repeating an action. An empty successful result
is distinct from an execution failure.
## Browser
```sh
opencli browser open https://example.com --session research
opencli browser state --session research
opencli browser close --session research
opencli browser chrome describe
```
Page commands use `--session`; native Chrome methods need no session. `--profile`
selects a connected Chrome profile. `profile list` discovers profiles and
`profile use ` selects the default. Use `doctor` for connection diagnosis.
See `opencli-browser` for interaction, API evidence and tab/group management.
## Adapters and installation
```sh
opencli adapter init example/search
opencli adapter check example/search
opencli adapter test example/search --args '{"query":"hello"}'
opencli adapter status
```
See `opencli-adapter-author` for implementation. `adapter eject` makes an official
site editable locally; `adapter reset` removes that local override. Adapter tests
execute real commands and can perform writes.
`plugin list|install|update|uninstall|create` manages plugin packages. `auth status`
reports website login facts; `auth refresh` touches sessions. `daemon status|restart|stop`
manages the bridge process. Read help for the selected capability.
Bundled skill content is available through `skills list` and
`skills read opencli-browser -f plain` (omit `-f plain` for JSON).