a2a-protocol

How agents call other agents via the A2A (agent-to-agent) JSON-RPC protocol. Use when enabling inter-agent communication, exposing agent skills to other agents, or calling external agents from scripts.

Quality

82%

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

Quality

Content

65%

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

Highly actionable with complete executable examples and clear endpoint/lifecycle structure, but it is verbose and monolithic — the full type reference and advanced integration details live inline in SKILL.md instead of being progressively disclosed into separate reference files.

Suggestions

Move the 'All Types' reference and the advanced A2AClient / idempotency / approved-actions deep-dives into a references/ file (e.g. A2A-REFERENCE.md) and link to it from a concise overview, so the body earns progressive_disclosure and conciseness.

Tighten the 'Why' section and the retry-safety/trace-linkage prose to bullet points that keep only what Claude would not already know, reducing verbosity without losing the security-critical constraints.

Add an explicit validation/checkpoint step to the main call flow (e.g. check task.status.state and handle 'input-required'/'failed' before proceeding) so the multi-pattern workflow has a clear feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly concrete API guidance, but the "Why" preamble and dense prose sections on retry safety, trace linkage, agent-activity parts, and approved-actions could be tightened; the ~250-line body carries explanatory context that competes with the token budget.	2 / 3
Actionability	Fully executable TypeScript examples (mountA2A, callAgent, invokeAgentAction, A2AClient) with imports, a complete config interface, agent-card JSON, and a cross-agent workflow example — copy-paste ready rather than pseudocode.	3 / 3
Workflow Clarity	Main flows (server enable → agent card → client call) and the task-lifecycle state diagram are sequenced, but the guide spreads across several usage patterns with no explicit validation/feedback checkpoints; checkpoints are absent or implicit.	2 / 3
Progressive Disclosure	Sections are well-organized, but the SKILL.md is a monolithic ~250-line file with no bundle references; content that could be split out (full type reference, advanced-client details, idempotency/security deep-dives) is inline rather than one level deep in separate files.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person voice, specific actions, explicit "Use when" triggers, and a distinct protocol niche that avoids skill conflicts. No fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "enabling inter-agent communication", "exposing agent skills to other agents", and "calling external agents from scripts" — tied to a named protocol (A2A JSON-RPC), rather than vague language.	3 / 3
Completeness	Explicitly states what ("How agents call other agents via the A2A (agent-to-agent) JSON-RPC protocol") and when ("Use when enabling inter-agent communication, exposing agent skills to other agents, or calling external agents from scripts"), so both what and when are answered with an explicit trigger clause.	3 / 3
Trigger Term Quality	Natural developer-facing terms like "agent-to-agent", "inter-agent communication", "exposing agent skills", and "calling external agents" cover the phrasings a user would actually say when needing this skill.	3 / 3
Distinctiveness Conflict Risk	A2A is a specific named protocol scoped to inter-agent calls, clearly distinguishable from sibling skills such as delegate-to-agent (which handles local-agent work), so it is unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: BuilderIO/agent-native
Path: .agents/skills/a2a-protocol/SKILL.md
Commit: c1ee18b

Reviewed: 4 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.