omni-combos-routing

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.

Quality

66%

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/omni-combos-routing/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 a highly actionable API reference with concrete examples for the common cases, but it duplicates content between generated and curated sections, lacks an explicit create→activate→test workflow with validation, and inlines reference material that could live in separate files.

Suggestions

Add a sequenced quick-start workflow (create combo → activate via toggle → call /v1/chat/completions → check metrics) with an explicit validation/simulate checkpoint before destructive DELETE calls.

De-duplicate the generated endpoint stubs against the curated section and replace empty `-d '{}'` placeholders with real example payloads or a pointer to the OpenAPI spec.

Move the full endpoint reference into a separate REFERENCE.md bundle and keep SKILL.md as a concise overview pointing to it, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	Mostly lean curl/table reference with little over-explanation, but the auto-generated endpoint stubs duplicate the curated section (list combos and metrics appear twice) and several `-d '{}'` placeholders add noise that could be tightened.	3 / 5
Actionability	Concrete, executable curl commands with real JSON payloads for the key operations (create combo, auto-combo, simulate), though the generated stub endpoints ship empty `-d '{}'` bodies that are not copy-paste ready.	4 / 5
Workflow Clarity	Operations are listed as discrete endpoints rather than a sequenced workflow, and destructive operations (DELETE combo, DELETE fallback chain) carry no validation/verification checkpoints, capping this at 3 per the rubric.	3 / 5
Progressive Disclosure	Well-sectioned with headers and it does offload detailed schemas to the OpenAPI spec, but the bulk API reference is inlined in SKILL.md with no bundle files to split it out, so structure is only adequate.	3 / 5
	Total	13 / 20 Passed

Description

75%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 distinct, naming concrete actions and domain trigger terms, but it omits any explicit "Use when..." guidance for when Claude should invoke the skill.

Suggestions

Add an explicit trigger clause, e.g. "Use when configuring OmniRoute routing, setting up model failover/fallback chains, or testing routing outcomes."

Include common synonyms users might say ("load balancing", "failover", "model routing") alongside "routing combos" to broaden natural trigger coverage.

Keep the action list but ensure the "when" is as concrete as the "what" so Claude knows the invocation context.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Create and manage routing combos", "Configure fallback chains", "test routing outcomes", "retrieve combo metrics" — giving comprehensive coverage of capabilities.	5 / 5
Completeness	The "what" is clearly and comprehensively stated, but there is no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Strong domain-natural terms ("routing combos", "fallback chains", "combo metrics", named strategies) but missing common synonyms a user might say like "load balancing", "failover", or "model routing".	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (OmniRoute routing combos, 19 strategies, fallback chains) with distinct triggers unlikely to fire for unrelated skills.	5 / 5
	Total	17 / 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/omni-combos-routing/SKILL.md
Commit: ea0cdc5

Reviewed: about 6 hours 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.