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

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

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

Quality

Content

72%

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

The content is highly actionable with executable protocol examples and clear external references, but it carries redundant boilerplate (a verbatim Overview restatement and an empty Endpoints placeholder) and leaves the discovery-to-call workflow implicit rather than explicitly sequenced.

Suggestions

Remove the verbatim Overview restatement and the empty "Endpoints: No endpoints mapped" placeholder to reclaim tokens.

Reconcile the skill list: the body table lists 5 skills while the description promises 6 (list-capabilities is missing).

Make the protocol flow an explicit numbered workflow (discover Agent Card → select skillId → POST /a2a → validate result.status → handle error codes) so the sequence and validation checkpoint are unambiguous.

Dimension	Reasoning	Score
Conciseness	The A2A section is lean with executable curl and a compact skills table, but the body repeats the description verbatim in "Overview" and includes an empty "Endpoints" placeholder ("No endpoints mapped for this area yet."), wasting tokens. It is mostly efficient but could be tightened, matching the level-2 anchor.	2 / 3
Actionability	It provides copy-paste-ready executable curl commands for discovery and the JSON-RPC call, a concrete response shape, and specific error codes with remediation hints, matching the anchor for fully executable, specific examples.	3 / 3
Workflow Clarity	A logical sequence is implied (Discovery → Call → Response → Errors) with light error-recovery hints, but it is not framed as an explicit validated workflow and the skills table omits list-capabilities despite the description listing six skills. This fits level 2: sequence present but checkpoints implicit and a consistency gap.	2 / 3
Progressive Disclosure	The body is well-sectioned with clearly signaled one-level-deep references (OpenAPI spec, docs/openapi.yaml, the entry-point SKILL, and the full-docs link) and no nested reference chains, matching the anchor for clear overview with well-signaled references and easy navigation.	3 / 3
	Total	10 / 12 Passed

Description

67%

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 distinctive, clearly scoping a named A2A protocol and six concrete skills, but it omits explicit usage triggers and leans on technical jargon over natural user phrasing.

Suggestions

Add a "Use when..." clause naming natural triggers, e.g., "Use when routing a prompt to the best provider, checking quota balance, discovering providers by capability, estimating request cost, or pulling a health report."

Soften jargon with user-natural phrasings alongside the technical names (e.g., "best provider/model combo" alongside "smart-routing").

Ensure the skill list in the description matches the body exactly (description lists 6 skills including list-capabilities; the body table lists only 5).

Dimension	Reasoning	Score
Specificity	Names a concrete protocol ("JSON-RPC 2.0 agent-to-agent protocol") and lists multiple specific capabilities ("smart-routing, quota-management, provider-discovery, cost-analysis, health-report, list-capabilities"), matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	It clearly answers "what" (interact via A2A, six named skills) but lacks any "Use when..." or equivalent explicit trigger for when Claude should invoke it; per the guidelines a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Recognizable terms exist ("A2A", "smart-routing", "quota-management", "cost-analysis"), but the phrasing leans technical and omits natural variations a user would actually say (e.g., "route to the best provider", "check my quota", "compare model costs"). It is above level 1 (some relevant keywords) but below level 3 (no good coverage of natural user phrasings).	2 / 3
Distinctiveness Conflict Risk	It targets a named product and protocol ("OmniRoute", "JSON-RPC 2.0 agent-to-agent protocol") with six distinctive capability names, forming a clear niche unlikely to trigger for unrelated skills. It is above level 2 because the niche is specific rather than merely "somewhat specific".	3 / 3
	Total	10 / 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/omni-agents-a2a/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.