bedrock-agentcore-multi-agent

Amazon Bedrock AgentCore multi-agent orchestration with Agent-to-Agent (A2A) protocol. Supervisor-worker patterns, agent collaboration, and hierarchical delegation. Use when building multi-agent systems, orchestrating specialized agents, or implementing complex workflows.

Quality

73%

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/bedrock-agentcore-multi-agent/SKILL.md

Quality

Content

60%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 highly actionable with substantial executable code and a clear sequenced workflow, but it is token-heavy (decorative diagrams, dated claims) and fails progressive disclosure: all content is monolithically inlined and the three referenced files do not exist.

Suggestions

Create references/routing-strategies.md, references/context-management.md, and references/failure-handling.md (or remove the broken References entries) so cited materials actually resolve.

Move the per-operation full code listings into one-level-deep reference files, keeping SKILL.md a concise overview with short key snippets and clear links.

Trim the ASCII architecture diagrams and the 'Quality Targets'/'validated by AWS December 2025' metrics block to reduce token cost and remove time-sensitive claims.

Dimension	Reasoning	Score
Conciseness	The ~700-line body is mostly code (justified) but carries padding that does not earn its tokens — large decorative ASCII diagrams, a 'Quality Targets' metrics block, and a time-sensitive 'validated by AWS December 2025' date — so it sits at 'mostly efficient but could be tightened' rather than lean.	3 / 5
Actionability	Mostly executable, copy-paste-ready Python (supervisor/specialist agents, A2A config, IAM policy, CloudWatch dashboard) with minor gaps — e.g. the 'Multi-Turn Handoff Example' is comment-only prose with no runnable code — placing it just below fully executable 5.	4 / 5
Workflow Clarity	Five operations are clearly sequenced with time/automation/purpose metadata and embedded fallback try/except error handling; it falls short of 5 because the create/configure operations lack explicit validate-before-proceeding checkpoints, though they are not destructive batch ops that would trigger the 3 cap.	4 / 5
Progressive Disclosure	No references/, scripts/, or assets/ directories exist, yet the body lists references/routing-strategies.md, context-management.md, and failure-handling.md — broken pointers — and all five operations' bulk code is inlined in SKILL.md rather than split into one-level-deep files.	2 / 5
	Total	13 / 20 Passed

Description

87%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 well-crafted: it states the domain and concrete patterns, gives explicit 'Use when' trigger guidance, and occupies a distinct niche. Its only weakness is mild abstraction in the action verbs versus fully concrete, comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (AgentCore A2A protocol) and several concrete patterns — 'Supervisor-worker patterns, agent collaboration, and hierarchical delegation' — but 'orchestration' is somewhat abstract and lacks discrete per-action verbs, leaving minor coverage gaps versus the comprehensive 5 anchor.	4 / 5
Completeness	Explicitly answers both 'what' (A2A orchestration, supervisor-worker, hierarchical delegation) and 'when' ('Use when building multi-agent systems, orchestrating specialized agents, or implementing complex workflows') with concrete trigger phrases, matching the 5 anchor.	5 / 5
Trigger Term Quality	Good natural keyword coverage — 'multi-agent systems, orchestrating specialized agents, implementing complex workflows' — phrases a user would actually say, though a few synonyms/variations are missing relative to the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Clear niche — Bedrock AgentCore multi-agent A2A orchestration — with distinct triggers and minimal overlap risk with other skills, matching the 5 anchor; voice is third person.	5 / 5
	Total	18 / 20 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
skill_md_line_count	SKILL.md is long (706 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	13 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/bedrock-agentcore-multi-agent/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.