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

90%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

80%

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

A well-organized, token-efficient reference with concrete config and agent-type guidance, but it duplicates detail that lives in the reference files without linking to them, and its custom-team workflow lacks explicit validation checkpoints.

Suggestions

Replace the inline Preset Team Compositions and Agent Type Selection detail with concise overviews that link to references/preset-teams.md and references/agent-type-selection.md so the body stays a true overview.

Add explicit validation/verification checkpoints to the Custom Team Guidelines (e.g., confirm every role maps to a writable agent type, verify file ownership has no gaps before spawning) to lift workflow clarity.

Drop the 'When to Use This Skill' bullet list or trim it, since the frontmatter description already states the same triggers, removing redundancy.

Dimension	Reasoning	Score
Conciseness	Lean and table-driven with no padding of concepts Claude already knows; sizing, presets, agent types, and display modes are each compressed into dense tables. Minor redundancy (the 'When to Use' list echoes the description) keeps it just at efficient rather than verbose.	3 / 3
Actionability	Concrete and copy-paste ready: exact `subagent_type` values per role, a real JSON config snippet (`{"teammateMode": "tmux"}`), specific team sizes, and explicit tool lists per agent type.	3 / 3
Workflow Clarity	The Custom Team Guidelines are a numbered 1–5 sequence, but there are no explicit validation checkpoints or validate→fix→retry feedback loops in the composition workflow, leaving checkpoints implicit.	2 / 3
Progressive Disclosure	Bundle files `references/preset-teams.md` and `references/agent-type-selection.md` exist but are never linked or signaled from the body, and their content is largely duplicated inline rather than split out, so navigation to the detail files is missing.	2 / 3
	Total	10 / 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, third-person description that states concrete capabilities and gives explicit 'Use when' triggers covering sizing, preset selection, agent typing, display modes, and custom compositions. It is distinguishable and free of vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'sizing heuristics, preset configurations, and agent type selection', 'deciding how many agents to spawn', 'configuring display modes (tmux, iTerm2, in-process)' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what ('Design optimal agent team compositions with sizing heuristics, preset configurations, and agent type selection') and when ('Use this skill when deciding how many agents to spawn...').	3 / 3
Trigger Term Quality	Covers natural terms a user would say — 'how many agents to spawn', 'review team versus a feature team versus a debug team', 'migration or security audit' — with good breadth of phrasings.	3 / 3
Distinctiveness Conflict Risk	Clear niche (Agent Teams composition) with distinct triggers — subagent_type selection, preset team choice, display-mode configuration — unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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
Commit: d7cf7dc

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.