team-composition-patterns

Design optimal agent team compositions with sizing heuristics, preset configurations, and agent type selection. Use this skill when deciding how many agents to spawn for a task, when choosing between a review team versus a feature team versus a debug team, when selecting the correct subagent_type for each role to ensure agents have the tools they need, when configuring display modes (tmux, iTerm2, in-process) for a CI or local environment, or when building a custom team composition for a non-standard workflow such as a migration or security audit.

Quality

85%

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

Quality

Content

71%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 well-structured, concise, and actionable with good tables and troubleshooting, but it fails to point to the available reference files, leaving content inline that could be split out for progressive disclosure.

Suggestions

Add a short reference section linking to references/agent-type-selection.md and references/preset-teams.md, and slim the inlined tables to summaries that point readers to those files for full detail.

Expand the display-mode config example to show a complete ~/.claude/settings.json snippet or a concrete spawn command so guidance is fully copy-paste ready.

Tighten the 'Rule of thumb' line and the longest troubleshooting answers to reduce remaining padding.

Dimension	Reasoning	Score
Conciseness	Mostly lean — tables and bullets carry the content with little padding — but sections like the 'Rule of thumb' and some troubleshooting elaboration could be trimmed slightly.	4 / 5
Actionability	Concrete tables for team sizing, agent types, and display modes plus an executable JSON config snippet; minor gaps such as the minimal config example and absence of a spawn command template.	4 / 5
Workflow Clarity	Clear structure with a numbered custom-team checklist and a troubleshooting section that provides feedback loops for common failure modes; not a destructive/batch workflow so the validation cap does not apply.	4 / 5
Progressive Disclosure	Body inlines the agent-type table and preset teams even though references/agent-type-selection.md and references/preset-teams.md exist as bundle files but are never signaled or linked from the body.	3 / 5
	Total	15 / 20 Passed

Description

100%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 comprehensive, concrete, and uses third-person voice throughout. It clearly states both capabilities and multiple explicit use-when triggers with natural language.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'sizing heuristics, preset configurations, and agent type selection', choosing team counts, selecting subagent_type, configuring display modes, and building custom compositions — with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' ('Design optimal agent team compositions...') and 'when' ('Use this skill when deciding how many agents to spawn...') with concrete trigger clauses.	5 / 5
Trigger Term Quality	Includes natural phrases users would say — 'how many agents to spawn', 'review team versus a feature team versus a debug team', 'migration or security audit' — plus concrete terms like subagent_type and tmux/iTerm2/in-process.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (agent team composition for Claude Code) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 suspicious	Warning

	Total	14 / 16 Passed

Repository: wshobson/agents
Path: plugins/agent-teams/skills/team-composition-patterns/SKILL.md
Commit: 4236bb9

Reviewed: 12 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.