Name: multi-agent-patterns
Rating: 57.599999999999994 (1 reviews)
Author: administrakt0r

multi-agent-patterns

This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.

Quality

66%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/multi-agent-patterns/SKILL.md

The canonical home for this skill is multi-agent-patterns in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

57%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 content is a well-organized, actionable catalog of multi-agent patterns with real code examples, but it is conceptually verbose for a skill body, lacks explicit sequenced workflows with validation, and does not progressively disclose detail into bundle files.

Suggestions

Trim conceptual rationale (context-bottleneck and token-economics prose) to the minimum needed to justify each pattern, since Claude already knows these concepts.

Move the framework comparison and consensus-protocol detail into a references/ bundle file and link to it from SKILL.md so the main body stays a lean overview.

Resolve the dangling 'Internal reference - Frameworks Reference' by either creating the referenced file or removing the pointer, and add a short prescriptive workflow (assess decomposition need -> choose pattern -> define handoffs -> set TTL/validation) with explicit checkpoints.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded with conceptual exposition Claude already knows (context bottlenecks, attention scarcity, token economics rationales) and rhetorical framing ('When designed well... When designed poorly...') that could be trimmed.	3 / 5
Actionability	Provides concrete, mostly executable Python examples (forward_message, transfer_to_agent_b, handle_customer_request routing) plus decision guidance, with only minor gaps where handoff snippets are illustrative rather than fully runnable.	4 / 5
Workflow Clarity	As a design-patterns catalog it gives coherent selection guidance and failure mitigations, but there is no explicit sequenced workflow with validation checkpoints or validate-fix-retry feedback loops.	3 / 5
Progressive Disclosure	The body is well-sectioned but monolithic (~250 lines in a single file), with detailed topics (framework considerations, consensus) inlined that could be split out, and an 'Internal reference' to a Frameworks Reference that has no corresponding bundle file.	3 / 5
	Total	13 / 20 Passed

Description

75%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 has strong, natural trigger phrasing and explicit usage guidance covering a distinct multi-agent architecture niche, but it front-loads the 'when' and leaves the 'what' only implicitly conveyed through the triggers.

Suggestions

Lead with a concise declarative 'what' statement (e.g., 'Designs and documents multi-agent architectures using supervisor, swarm, and hierarchical patterns.') before the 'Use when...' trigger clause.

Add a few more common user-facing synonyms or variants (e.g., 'orchestrator', 'agent orchestration', 'multi-agent workflow') to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete architectural actions ('design multi-agent system', 'implement supervisor pattern', 'create swarm architecture', 'coordinate multiple agents') rather than a single vague action, though it stops short of a comprehensive atomic action list.	4 / 5
Completeness	An explicit 'when' clause is present ('should be used when the user asks to... or mentions...'), and the 'what' is implied through the enumerated trigger actions, but there is no standalone declarative statement of what the skill does.	4 / 5
Trigger Term Quality	Good coverage of natural phrases a user would say ('design multi-agent system', 'coordinate multiple agents') plus synonyms (swarm, supervisor, sub-agents, handoffs), but lacks some common variations and is slightly jargon-leaning.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (multi-agent architecture) with distinctive triggers ('supervisor pattern', 'swarm architecture', 'agent handoffs'), with only minor overlap risk against generic agent skills.	4 / 5
	Total	16 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/multi-agent-patterns/SKILL.md
Commit: 57c135b

Reviewed: 3 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.