Skills Directory

diegosouzapw/OmniRoute

cli-eval

Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI.

307 installs 60K starsUpdated Sep 3, 2026License: MIT

Install

npx skills add diegosouzapw/OmniRoute@cli-eval

Runs in your terminal. Adds the skill globally for Claude Code, Cursor, Codex and others; add -g -y to skip prompts.

What it does

Overview Create and run evaluation suites, watch live benchmark progress, view scorecards, compare model performance, and integrate eval runs with CI workflows from the CLI. Quick install Subcommands eval Example: eval suites Example: eval list Example: eval get Example: eval create Flags: - --file Example: eval run Flags: - -m, --model - --combo - --concurrency - --tag - --watch Example: eval list Flags: - --suite - --status - --since - --limit Example: eval get Example: eval results Flags: - --failed Example: eval cancel Flags: - --yes Example: eval scorecard Example: simulate [prompt]…

Excerpt from the skill's own SKILL.md. Read the full file on GitHub before installing: skills run with your agent's permissions.

View source on GitHub

Before you install

Skills are plain text instructions the agent follows, sometimes with scripts. Check the source, prefer repositories with many installs and stars, and read any script it ships.

Categories

Related skills

  • omni-combos-routing

    diegosouzapw/OmniRoute

    Create and manage routing combos with 19 strategies (priority, weighted, round-robin, Auto-combo, and more). Configure fallback chains, test routing outcomes, and retrieve combo metrics.

    395 installs 60KTestingSecurity
  • cli-setup

    diegosouzapw/OmniRoute

    Run initial setup, configure global CLI settings, manage environment variables, check for updates, and configure autostart via the CLI setup and config commands.

    385 installs 60K
  • omni-mcp

    diegosouzapw/OmniRoute

    Connect to the OmniRoute MCP server (110 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 33 permission scopes.

    370 installs 60KSecurityAI & agentsCode review
  • cli-providers

    diegosouzapw/OmniRoute

    Manage provider connections from the CLI: list available/configured providers, add, test, test-all, validate, rotate API keys, and view per-provider metrics.

    365 installs 60KTesting
  • omni-auth

    diegosouzapw/OmniRoute

    Manage API key authentication and session tokens. Start here to authenticate requests via Bearer token, obtain session cookies, and configure login requirements for the OmniRoute API.

    359 installs 60KSecurity
  • cli-routing

    diegosouzapw/OmniRoute

    Create, list, update, and delete routing combos from the CLI. Test routing strategies, inspect combo metrics, and configure fallback chains interactively.

    352 installs 60KTesting

← Search skills

/skills/diegosouzapw/OmniRoute/cli-eval/