omni-agents-a2a

Interact with OmniRoute via JSON-RPC 2.0 agent-to-agent protocol. 6 built-in A2A skills: smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities.

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/omni-agents-a2a/SKILL.md

Quality

Content

67%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 curated body is actionable and well-sequenced with concrete curl examples and clear error handling, but token efficiency is dragged down by duplicated description text and placeholder scaffold sections that should be pruned.

Suggestions

Remove the verbatim duplication of the description in the Overview section and delete the placeholder 'No endpoints mapped for this area yet.' stub to reclaim tokens.

Consolidate the two top-level headings (the '## Overview' and the curated '# OmniRoute — A2A Protocol') into a single coherent structure to remove redundancy.

Add a brief note on validating the response (e.g., checking the `status` field and handling non-`completed` states) to round out workflow clarity.

Dimension	Reasoning	Score
Conciseness	The curated section is lean (curl examples, a compact skill table, error list), but the description is duplicated verbatim in the Overview, the stub 'No endpoints mapped for this area yet' section is placeholder filler, and a redundant top-level heading repeats, adding avoidable tokens.	3 / 5
Actionability	Provides concrete, executable curl commands for discovery and the JSON-RPC call with real env vars, a documented response shape, and enumerated error codes — mostly copy-paste ready with only minor gaps.	4 / 5
Workflow Clarity	A clear discovery → call → response → errors sequence with named error codes, and since this is a read/query skill rather than a destructive or batch operation, the missing feedback loop does not trigger the cap; minor validation guidance could be added.	4 / 5
Progressive Disclosure	No bundle files exist, and the skill is self-contained with a single external reference link and a logically sectioned curated block; the auto-generated stub glued to the curated section is a minor organization gap rather than a structural problem.	4 / 5
	Total	15 / 20 Passed

Description

62%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 product-specific and enumerates concrete skills, giving it strong distinctiveness and decent specificity, but it lacks an explicit 'Use when' trigger clause and relies on somewhat jargon-heavy terms, capping completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., 'Use when the user asks to route requests across providers, check quota, or interact with OmniRoute's A2A API').

Soften jargon with natural trigger phrases and synonyms a user might say (e.g., 'agent routing', 'provider cost estimate', 'quota check') in addition to the product-specific terms.

Reframe the six enumerated items as concrete actions (e.g., 'route prompts, check quotas, discover providers, estimate costs') to strengthen the specificity of capabilities.

Dimension	Reasoning	Score
Specificity	Names the concrete protocol ('JSON-RPC 2.0 agent-to-agent protocol') and enumerates six specific built-in skills, giving several concrete actions, though they are listed as skill names rather than verbs.	4 / 5
Completeness	Provides a clear 'what' (interact via A2A protocol with six named skills) but has no explicit 'Use when...' trigger clause, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes relevant domain terms (OmniRoute, JSON-RPC 2.0, A2A, agent-to-agent) and the six skill names, but coverage leans product/jargon-heavy and omits common synonyms or file-extension-style triggers a user might naturally say.	3 / 5
Distinctiveness Conflict Risk	Tightly scoped to the OmniRoute product and its A2A protocol with distinct skill names, making conflict with other skills minimal.	5 / 5
	Total	15 / 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-agents-a2a/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.