diegosouzapw--omniroute/skills/cli-eval/SKILL.md

name, description

name	description
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.

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

npm install -g omniroute   # or: npx omniroute
omniroute --version

Subcommands

eval

Example:

omniroute eval

eval suites

Example:

omniroute eval suites

eval list

Example:

omniroute eval list

eval get <suiteId>

Example:

omniroute eval get <suiteId>

eval create

Flags:

• --file <path>

Example:

omniroute eval create

eval run <suiteId>

Flags:

• -m, --model <id>
• --combo <name>
• --concurrency <n>
• --tag <tag>
• --watch

Example:

omniroute eval run <suiteId>

eval list

Flags:

• --suite <id>
• --status <s>
• --since <ts>
• --limit <n>

Example:

omniroute eval list

eval get <runId>

Example:

omniroute eval get <runId>

eval results <runId>

Flags:

• --failed

Example:

omniroute eval results <runId>

eval cancel <runId>

Flags:

• --yes

Example:

omniroute eval cancel <runId>

eval scorecard <runId>

Example:

omniroute eval scorecard <runId>

simulate [prompt]

Flags:

• --file <path>
• -m, --model <id>
• --combo <name>
• --reasoning-effort <level>
• --thinking-budget <n>
• --explain

Example:

omniroute simulate [prompt]

OmniRoute — CLI Evals

Requires the omniroute CLI. See CLI entry-point skill for install + global flags.

What are evals?

Evals are automated test suites that score LLM outputs against expected answers or rubrics. OmniRoute stores suites and run results in its local database.

Eval suites

omniroute eval suites list                       # List all eval suites
omniroute eval suites list --json                # JSON output

omniroute eval suites get <suiteId>              # Full suite definition

Create a suite

omniroute eval suites create \
  --name "code-quality" \
  --rubric "exact-match" \
  --samples-file ./samples.jsonl                 # JSONL: {input, expected_output}

Rubric options: exact-match, contains, llm-judge, regex.

--samples-file format (one JSON object per line):

{"input": "What is 2+2?", "expected_output": "4"}
{"input": "Translate 'hello' to Spanish", "expected_output": "hola"}

Run an eval

omniroute eval suites run <suiteId> \
  --model claude-sonnet-4-6                      # Run suite against a specific model

omniroute eval suites run <suiteId> \
  --model gpt-4o \
  --watch                                        # Live TUI progress (EvalWatch)

The run is asynchronous. Use --watch for a live terminal dashboard or poll manually:

RUN_ID=$(omniroute eval suites run <suiteId> --model claude-sonnet-4-6 --output json | jq -r '.id')
omniroute eval get $RUN_ID

Manage runs

omniroute eval list                              # List all eval runs
omniroute eval list --json

omniroute eval get <runId>                       # Run details (status, model, score)
omniroute eval results <runId>                   # Per-sample results
omniroute eval scorecard <runId>                 # Full scorecard with pass/fail per sample
omniroute eval cancel <runId>                    # Cancel a running eval

Scorecard output

omniroute eval scorecard <runId> --output json

Response fields per sample:

{
  "id": "sample-1",
  "score": 0.95,
  "passed": true,
  "input": "What is 2+2?",
  "output": "4",
  "expected": "4"
}

Comparing models

Run the same suite against multiple models and compare:

for MODEL in claude-sonnet-4-6 gpt-4o gemini-2.0-flash; do
  omniroute eval suites run $SUITE_ID --model $MODEL --output json | jq '{model: .model, score: .score}'
done

CI integration

# Run and fail CI if score drops below threshold
SCORE=$(omniroute eval suites run $SUITE_ID --model claude-sonnet-4-6 --output json | jq -r '.score')
python3 -c "import sys; score=float('$SCORE'); sys.exit(0 if score >= 0.90 else 1)"

Errors

• suites create fails with invalid rubric → use one of: exact-match, contains, llm-judge, regex
• suites run returns model not found → verify model ID with omniroute models --search <name>
• eval get shows status: failed → check omniroute logs --search eval for error details
• scorecard returns empty results → the run may still be running; poll omniroute eval get <runId> until status is completed