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.

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/cli-eval/SKILL.md

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is actionable with strong executable examples in the curated section, but it carries redundant auto-generated command stubs that duplicate curated content and lack an explicit sequenced workflow with validation checkpoints. Organization is decent but undermined by the parallel duplicated command listings.

Suggestions

Remove or collapse the auto-generated subcommand stubs that duplicate the curated section (notably the two 'eval list' entries and bare 'Example' blocks that just echo the command).

Add an explicit numbered end-to-end workflow (create suite → run with --watch/poll → check status → read scorecard) with validation checkpoints such as polling until status is 'completed'.

Show flags inline in the auto-generated examples (e.g. 'omniroute eval run <suiteId> --model <id> --watch') so the examples are immediately executable.

Dimension	Reasoning	Score
Conciseness	The curated section is lean and efficient, but the auto-generated command reference pads each subcommand with an 'Example' block that merely restates the command, and 'eval list' appears twice with different flag sets, adding noticeable redundancy.	3 / 5
Actionability	The curated section provides copy-paste-ready commands with real flags, JSONL sample format, jq pipelines, and a CI threshold script; the auto-generated examples use bare placeholders like <suiteId> without demonstrating flags in context, leaving minor gaps.	4 / 5
Workflow Clarity	Commands are grouped by topic (suites, runs, scorecard, compare, CI) implying a create→run→results flow, and there is polling/CI-threshold feedback, but the workflow is not laid out as an explicit sequenced process with validation checkpoints for these batch operations.	3 / 5
Progressive Disclosure	Section headers give the file reasonable structure and the external CLI link is clearly signaled, but the auto-generated and curated sections duplicate the same command set (eval list/get/results/cancel/scorecard), an organization issue that keeps it from scoring higher.	3 / 5
	Total	13 / 20 Passed

Description

71%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and lists several concrete capabilities with good trigger-term coverage, but it omits an explicit 'Use when...' trigger clause, which caps completeness. It is clearly distinct from most other skills.

Suggestions

Add an explicit 'Use when...' clause naming trigger phrases (e.g. 'Use when the user asks to run evals, benchmark models, or check scorecards from the CLI').

Include shorthand synonyms like 'evals' alongside 'evaluation suites' to match natural user phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'create and run evaluation suites', 'watch live benchmark progress', 'view scorecards', 'compare model performance', 'integrate eval runs with CI workflows' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The 'what' is clear and comprehensive, but there is no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 3.	3 / 5
Trigger Term Quality	Includes natural terms a user would say ('evaluation suites', 'benchmark progress', 'scorecards', 'compare model performance', 'CI workflows') but is missing common synonyms or shorthand like 'evals' or file/format variations.	4 / 5
Distinctiveness Conflict Risk	The eval/benchmark/scorecard niche is fairly distinct and specific to CLI evaluation workflows, with only minor overlap risk against general CLI or testing skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: diegosouzapw/OmniRoute
Path: skills/cli-eval/SKILL.md
Commit: ea0cdc5

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.