team-builder
Intelligently compose and deploy Claude Code Agent Teams based on user requirements. Auto-selects optimal team composition from all available skills and agents (project, user, global, plugin scopes), generates task dependency graphs, and orchestrates team lifecycle. Use when creating multi-agent teams for complex tasks requiring parallel specialized work.
77
71%
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/team-builder/skills/team-builder/SKILL.mdQuality
Discovery
85%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 a strong description that clearly articulates specific capabilities and includes an explicit 'Use when' trigger clause. Its main weakness is that the trigger terms lean toward technical jargon rather than natural user language — users might phrase requests differently (e.g., 'run tasks in parallel', 'coordinate multiple agents', 'break this into subtasks'). The description is distinctive and unlikely to conflict with other skills.
Suggestions
Add more natural user-facing trigger terms such as 'run tasks in parallel', 'coordinate agents', 'break work into subtasks', or 'fan out work' to improve keyword coverage for how users actually phrase requests.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'compose and deploy Claude Code Agent Teams', 'auto-selects optimal team composition', 'generates task dependency graphs', 'orchestrates team lifecycle'. These are distinct, concrete capabilities. | 3 / 3 |
Completeness | Clearly answers both what ('compose and deploy agent teams, auto-select composition, generate dependency graphs, orchestrate lifecycle') and when ('Use when creating multi-agent teams for complex tasks requiring parallel specialized work'). The 'Use when' clause is explicit. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'multi-agent teams', 'parallel', 'agent teams', 'task dependency graphs', but uses more technical/internal jargon ('orchestrates team lifecycle', 'deploy', 'scopes') than natural user language. A user might say 'run multiple agents' or 'split work across agents' but those terms are missing. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — focuses specifically on multi-agent team composition and orchestration with dependency graphs, which is a clear niche unlikely to conflict with single-purpose skills. The combination of team composition, dependency graphs, and lifecycle management is unique. | 3 / 3 |
Total | 11 / 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-structured skill for a complex orchestration task, with good progressive disclosure and clear mode-based workflows. Its main weaknesses are the lack of validation/error-recovery steps in the deployment workflow and the somewhat abstract deployment sequence that lacks fully executable examples. The content is moderately concise but could benefit from moving some reference tables to external files.
Suggestions
Add explicit validation checkpoints and error recovery steps to the deployment sequence (e.g., what to do if TeamCreate fails, how to verify teammates spawned correctly, how to handle task failures).
Make the deployment sequence more actionable by showing concrete, executable API calls or tool invocations rather than abstract pseudo-commands like 'TeamCreate(team_name, description)'.
Consider moving the Domain Detection table and Available Templates table to reference files to reduce the main skill's token footprint, keeping only a brief summary with links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly well-organized but includes some content that could be tightened—the domain detection table, model selection table, and templates table are useful reference material but make the SKILL.md quite long. Some of this could be offloaded to reference files. The args table is thorough but borderline verbose for a skill file. | 2 / 3 |
Actionability | The deployment sequence provides a concrete pseudo-workflow and the usage examples are helpful, but the actual commands (TeamCreate, TaskCreate, TaskUpdate, Task) are described abstractly without showing exact API calls or executable code. The discover_resources.py script is referenced but no concrete output format or integration code is shown. | 2 / 3 |
Workflow Clarity | Three modes (AUTO, TEMPLATE, MANUAL) are clearly sequenced with numbered steps, which is good. However, there are no explicit validation checkpoints or error recovery steps—what happens if discover_resources.py fails, if team creation fails, or if a teammate's task errors out? For an orchestration skill involving multi-agent deployment, missing feedback loops and error handling caps this at 2. | 2 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled references to external files (team-templates.md, composition-guide.md, discover_resources.py). Content is appropriately split between the main skill file and reference materials, with one-level-deep navigation that's easy to follow. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- sc30gsw/claude-code-customes
- Commit
7aff694
- 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.