multi-agent-patterns

This skill should be used when designing multi-agent systems that need context isolation, supervisor or swarm coordination, explicit handoffs, parallel execution, or a decision on whether multiple agents are justified.

Quality

75%

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/multi-agent-patterns/SKILL.md

Quality

Content

67%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 well-organized and actionable with concrete code and quantified guidance, but it is somewhat verbose and re-explains familiar concepts. The orphaned coordination.py bundle file and a few over-explanatory sections are the main areas to tighten.

Suggestions

Reference scripts/coordination.py from the body (or remove it from the bundle) so every bundled file is discoverable and the progressive disclosure is complete.

Trim sections that re-explain concepts Claude already knows (e.g., the lost-in-middle/telephone-game definitions) to keep the skill lean and respect the token budget.

Make the pattern code examples fully self-contained (complete imports and runnable Agent definitions) rather than partial snippets to push actionability higher.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete code and numbers, but several sections re-explain concepts Claude already knows (lost-in-middle effect, telephone game, general pattern definitions) and could be tightened.	3 / 5
Actionability	Provides executable code snippets (forward_message, transfer_to_agent_b, handoff routing) and concrete numbers (15x baseline, 3-5 workers), but some examples are partial rather than fully copy-paste-ready end-to-end.	4 / 5
Workflow Clarity	Decision flow is well sequenced (when to activate, choose pattern, isolation mechanism, failure-mode mitigations) with feedback-loop guidance like validate-then-retry, though it is design-oriented rather than a rigid checkpointed procedure.	4 / 5
Progressive Disclosure	Good section structure with a clearly signaled one-level reference (frameworks.md 'Read when'), but the bundled scripts/coordination.py is never referenced in the body and some detailed content stays inline.	4 / 5
	Total	15 / 20 Passed

Description

83%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 strong: it clearly states both what the skill does and when to use it, with concrete capability terms and an explicit trigger clause. Minor improvements are possible around adding synonyms and sharpening the niche to reduce overlap with adjacent agent skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities (context isolation, supervisor/swarm coordination, explicit handoffs, parallel execution, justified-multi decision) with only minor coverage gaps, matching the 'lists several specific actions' anchor.	4 / 5
Completeness	Explicitly answers both what (designing multi-agent systems with these coordination needs) and when ('This skill should be used when...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural terms users would say (multi-agent systems, context isolation, supervisor or swarm coordination, parallel execution) but lacks synonyms or file extensions, leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	The multi-agent topology niche is mostly distinct with minor overlap risk against adjacent agent-design skills rather than the clear-niche minimal-conflict profile.	4 / 5
	Total	17 / 20 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: muratcankoylan/Agent-Skills-for-Context-Engineering
Path: skills/multi-agent-patterns/SKILL.md
Commit: 6dbe1a1

Reviewed: 19 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.