cli-routing

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

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

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

Quality

Content

57%

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

The body is a compact, well-sectioned CLI reference that earns high progressive-disclosure marks, but it suffers from placeholder examples, undocumented flags, repetitive verbatim command echoes, and missing validation guidance for the destructive delete operation.

Suggestions

Replace placeholder examples with concrete ones and demonstrate the 'suggest' flags (e.g. show 'omniroute suggest --max-latency-ms 500 --top 3 --explain').

Document what each 'suggest' flag does and add a confirmation/validation note for the destructive 'combo delete' operation.

Drop the verbatim Overview duplicate and avoid echoing each subcommand header as its own example.

Dimension	Reasoning	Score
Conciseness	Mostly lean with minimal concept fluff, but it repeats the Overview verbatim from the description and echoes each subcommand as its own example verbatim, adding little — fitting the score-2 'mostly efficient but could be tightened' anchor rather than the score-3 'every token earns its place'.	2 / 3
Actionability	Commands are executable but several examples are placeholders ('omniroute combo create <name>', 'combo switch <name>') and the six 'suggest' flags are listed yet never demonstrated in an example, matching the score-2 'some concrete guidance but incomplete' anchor.	2 / 3
Workflow Clarity	Subcommands are organized into sections, but the destructive 'combo delete' has no validation/confirmation checkpoint beyond an unexplained '--yes' flag, and 'suggest' and 'combo combo' lack descriptions, fitting the score-2 'sequence present but checkpoints missing or implicit' anchor.	2 / 3
Progressive Disclosure	This is a short, simple single-tool reference (under 50 lines of content) with no need for external files, cleanly sectioned by subcommand, which the scoring note allows to score 3 for simple skills with well-organized sections.	3 / 3
	Total	9 / 12 Passed

Description

60%

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 strong on concrete, specific capabilities but lacks an explicit 'Use when' trigger clause, which caps completeness. Trigger terms are relevant but somewhat product-specific rather than natural user phrasing.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g. 'Use when configuring routing combos, testing fallback chains, or comparing combo metrics').

Broaden trigger terms with common variations users might actually say (e.g. 'routing rules', 'model fallback', 'route testing').

Restate actions in third person only and verify no implied capabilities beyond the listed CLI operations.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions verbatim — 'Create, list, update, and delete routing combos', 'Test routing strategies', 'inspect combo metrics', and 'configure fallback chains' — matching the score-3 anchor for multiple specific concrete actions.	3 / 3
Completeness	Clearly answers 'what' the skill does but provides no 'Use when...' or equivalent trigger guidance, so per the judging guideline a missing when-clause caps completeness at 2.	2 / 3
Trigger Term Quality	Contains relevant domain terms ('routing combos', 'fallback chains', 'combo metrics') but they lean toward product-specific CLI jargon with no explicit natural-user phrasing or common variations, fitting the score-2 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The routing-combo niche is reasonably specific and unlikely to trigger unrelated skills, but the terminology is product-bound and could overlap with other routing-related skills, matching the score-2 'somewhat specific but could still overlap' anchor.	2 / 3
	Total	9 / 12 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-routing/SKILL.md
Commit: 3070925

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.