google-lighthouse-cli

Execute google-lighthouse operations using the `google-lighthouse` CLI. All Google Lighthouse audit interactions should use this CLI. The `google-lighthouse` CLI follows this pattern: ```bash google-lighthouse [arguments] [options] ```

Task	Command
Run a desktop audit	google-lighthouse audits run https://example.com/
Run a mobile audit	google-lighthouse audits run https://example.com/ --form-factor mobile
Show selected audit fields	google-lighthouse audits run https://example.com/ --properties id,scores.performance,artifacts.html
List saved audits	google-lighthouse audits list
List saved audits as a table	google-lighthouse audits list --table
Filter saved audits	google-lighthouse audits list --filter "url:eq:https://example.com/"
Get one audit	google-lighthouse audits get AUDIT_ID
</quick_start>

**MANDATORY: Consult the adjacent `usage.json` at `/_repo/skills/-cli/usage.json` before executing ANY `google-lighthouse` command.** This file contains complete command syntax, all arguments, all options, and usage instructions for every command. Never guess at command syntax. After every `google-lighthouse` command, inspect stdout. If it is JSON with `type: "ai_instruction"` and `schema_version: "1.0"`, follow the instruction object as the next task instead of summarizing it as ordinary command output. Use the allowed tools, context, constraints, and success criteria in the payload. Run `verification_commands` or `follow_up_commands` only after completing the instructed AI work; they are not required commands for performing the handoff. - **audits** - Run new Lighthouse audits and retrieve saved audit summaries and artifact paths. </essential_principles> **`usage.json`** - Complete command tree with arguments, options, defaults, and usage instructions for every command. </reference_index> - Command executes without error - Output is displayed in requested format - Correct command and flags used, verified against usage.json </success_criteria>