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.
65
78%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/agent-teams/skills/team-composition-patterns/SKILL.mdQuality
Discovery
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.
This is an excellent skill description that clearly articulates specific capabilities (team composition design, sizing heuristics, preset configurations, agent type selection, display mode configuration) and provides comprehensive trigger guidance with five distinct use-case scenarios. The description uses proper third-person voice, includes natural keywords users would employ, and occupies a clearly distinct niche that minimizes conflict risk with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: designing agent team compositions, sizing heuristics, preset configurations, agent type selection, configuring display modes, and building custom team compositions. Very detailed and actionable. | 3 / 3 |
Completeness | Clearly answers both 'what' (design optimal agent team compositions with sizing heuristics, preset configurations, and agent type selection) and 'when' with an explicit 'Use this skill when...' clause listing five distinct trigger scenarios. | 3 / 3 |
Trigger Term Quality | Includes many natural trigger terms users would say: 'how many agents to spawn', 'review team', 'feature team', 'debug team', 'subagent_type', 'tmux', 'iTerm2', 'CI', 'migration', 'security audit', 'team composition'. Good coverage of variations and concrete scenarios. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on agent team composition, subagent types, and display mode configuration. The specificity of terms like 'subagent_type', 'tmux', 'iTerm2', 'review team versus feature team versus debug team' makes it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-organized reference skill that effectively catalogs team compositions and agent types using tables and structured sections. Its main weaknesses are the lack of executable examples showing actual Agent tool invocations for spawning teams, and the absence of a clear end-to-end workflow for team composition decisions. The content could be tightened by removing the redundant 'When to Use' section and trimming some troubleshooting explanations.
Suggestions
Add a concrete example of an Agent tool call showing how to actually spawn a team (e.g., a review team with 3 reviewers), including the prompt passed to each teammate.
Add a brief decision workflow at the top: assess task complexity → select preset or build custom → choose agent types → configure display mode → spawn teammates, with explicit validation (e.g., 'verify no two agents own the same files').
Remove the 'When to Use This Skill' section since it duplicates the frontmatter description and wastes tokens.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is generally well-structured with tables that convey information efficiently, but includes some unnecessary sections like 'When to Use This Skill' (which duplicates the description) and the troubleshooting section is somewhat verbose with explanations Claude could infer. The preset team compositions are well-formatted but could be more compact. | 2 / 3 |
Actionability | The skill provides concrete team compositions, agent type mappings, and a JSON config example, but lacks executable examples of actually spawning a team using the Agent tool. The guidance is specific about what to choose but not fully copy-paste ready for the actual invocation patterns — there are no example Agent tool calls or prompt templates. | 2 / 3 |
Workflow Clarity | The custom team guidelines provide a numbered list of considerations, but there's no clear step-by-step workflow for composing a team (e.g., assess complexity → select preset or custom → choose agent types → configure display → spawn). The troubleshooting section helps with error recovery but there are no explicit validation checkpoints for verifying team composition correctness before execution. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections, tables for quick reference, and appropriate cross-references to related skills (parallel-feature-development, team-communication-protocols). For a skill of this nature without bundle files, the structure is clean with logical progression from sizing → presets → agent types → configuration → custom guidelines → troubleshooting. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- wshobson/agents
- Commit
34632bc
- Reviewed
Table of Contents
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.