cli-a2a

Interact with the OmniRoute A2A server from the CLI. Send tasks, inspect skill execution history, and test the JSON-RPC 2.0 agent-to-agent protocol interactively.

Quality

70%

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-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 body is an actionable, well-organized CLI command reference with executable examples, but the Overview duplicates the frontmatter description and the typical invoke-then-monitor workflow is not sequenced with checkpoints. Trimming the redundant overview and adding a brief workflow thread would improve conciseness and workflow clarity.

Suggestions

Remove or condense the Overview section, since it repeats the frontmatter description verbatim and adds no new information.

Add a short sequencing note linking the related multi-step flow (e.g. 'invoke' a skill, then 'watch'/'stream'/'logs' to observe results, or 'list'/'get' to inspect history).

Dimension	Reasoning	Score
Conciseness	The command reference is mostly lean with flags and copy-paste examples, but the Overview section reprints the frontmatter description verbatim and several subcommand sections carry only an example with no added value, so it 'could be tightened' rather than hitting the every-token-earns-its-place bar.	2 / 3
Actionability	Every subcommand ships an executable example (e.g. 'omniroute a2a status', 'omniroute a2a invoke <skill>') plus concrete flags (--input, --wait, --timeout), making the guidance copy-paste ready and matching the fully-executable anchor.	3 / 3
Workflow Clarity	Subcommands are listed individually but the natural multi-step flow (invoke a skill, then watch/stream/logs to monitor it) is not sequenced, and there are no validation or status-check checkpoints despite the implicit invoke-then-monitor loop, fitting the score-2 anchor.	2 / 3
Progressive Disclosure	The skill is a single self-contained file with no bundle references, organized into clear sections (Overview, Quick install, Subcommands) with one level of structure and no nested references, meeting the well-organized anchor for skills that need no external files.	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 clearly occupies a distinct niche, but it is missing an explicit 'Use when...' trigger clause and leans on technical jargon over natural user phrasing. Adding a use-when clause with conversational trigger terms would lift completeness and trigger_term_quality.

Suggestions

Append a 'Use when...' clause naming natural trigger situations (e.g. 'Use when you need to send tasks to an A2A agent, inspect task history, or test agent-to-agent protocol calls').

Soften or supplement the technical jargon ('JSON-RPC 2.0') with terms users actually say, like 'agent-to-agent calls' or 'A2A tasks'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Send tasks', 'inspect skill execution history', 'test the JSON-RPC 2.0 agent-to-agent protocol' — each tied to a named tool (OmniRoute A2A server, CLI), matching the multi-action anchor rather than the score-2 'domain and some actions'.	3 / 3
Completeness	Clearly answers 'what' (interact with the A2A server, send tasks, inspect history, test the protocol) but provides no 'Use when...' clause or equivalent trigger guidance, so 'when' is missing — capped at 2 per the judging guideline.	2 / 3
Trigger Term Quality	Includes some relevant keywords a user might say ('A2A', 'agent-to-agent', 'send tasks', 'skill execution history') but leans heavily on technical jargon ('JSON-RPC 2.0', 'OmniRoute A2A server') and omits common variations, so it sits at the score-2 anchor rather than full natural coverage.	2 / 3
Distinctiveness Conflict Risk	The niche is tightly scoped to OmniRoute's A2A server and the JSON-RPC 2.0 agent-to-agent protocol, making it unlikely to trigger for unrelated skills and matching the 'clear niche with distinct triggers' anchor.	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/cli-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.