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.
82
78%
Does it follow best practices?
Impact
Pending
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 around agent team composition and provides comprehensive trigger guidance. It covers multiple concrete scenarios in the 'Use when' clause, uses natural terminology that users would employ, and occupies a 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 for specific workflows. | 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 and detailed 'Use this skill when...' clause covering multiple 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 both general and specific terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on agent team composition, subagent types, and multi-agent orchestration. The specific mentions of subagent_type, display modes (tmux, iTerm2), and team types (review, feature, debug) make 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 document with good use of tables and clear preset team definitions. Its main weaknesses are the lack of executable examples showing actual Task tool invocations for spawning teams, and the absence of a clear step-by-step workflow with validation checkpoints for team composition. The progressive disclosure and organization are strong points.
Suggestions
Add a concrete, executable example of spawning a team using the Task tool — show the actual tool invocation with subagent_type, prompt content, and expected behavior for at least one preset team.
Include a step-by-step workflow for composing a custom team: 1) assess complexity → 2) select preset or custom composition → 3) verify no role overlap → 4) spawn teammates with Task tool → 5) confirm all agents are active and have correct types.
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 some verbose troubleshooting entries. The 'Custom Team Guidelines' section contains advice Claude could infer. Overall mostly efficient but could be tightened. | 2 / 3 |
Actionability | The skill provides concrete team compositions, agent type mappings, and a specific JSON config example, which is good. However, it lacks executable examples of actually spawning a team — no Task tool invocation examples, no concrete prompt templates for teammates, no copy-paste-ready team setup commands. It describes what to do rather than showing how to do it with the Task tool. | 2 / 3 |
Workflow Clarity | The skill presents team compositions clearly but lacks a step-by-step workflow for actually composing and launching a team. There are no validation checkpoints — e.g., verifying teammates spawned correctly, checking that file ownership boundaries don't overlap, or confirming all dimensions are covered before proceeding. The custom team guidelines are a checklist but not a sequenced workflow. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, tables for quick reference, and appropriate cross-references to related skills (parallel-feature-development, team-communication-protocols) that are one level deep and clearly signaled. The structure supports scanning and discovery effectively. | 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
91fe43e
- 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.