team-orchestration
Creates and coordinates teams of persistent AI teammates with shared task lists, messaging, and lifecycle management. Use when spawning teammates, creating a team, setting up reviewers or implementers, coordinating multi-agent work, or any skill references "kit:team-orchestration". Provides the scaffolding for TeamCreate, teammate spawning, task dependencies, SendMessage communication, and graceful shutdown.
90
88%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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 a strong skill description that clearly articulates specific capabilities (team creation, task dependencies, messaging, lifecycle management), provides explicit trigger guidance via a 'Use when' clause with natural terms, and occupies a distinct niche around multi-agent team orchestration. The description is concise yet comprehensive, using third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: creating teams, spawning teammates, shared task lists, messaging, lifecycle management, task dependencies, SendMessage communication, and graceful shutdown. | 3 / 3 |
Completeness | Clearly answers both 'what' (creates and coordinates teams with shared task lists, messaging, lifecycle management) and 'when' (explicit 'Use when' clause listing spawning teammates, creating a team, setting up reviewers/implementers, coordinating multi-agent work, or skill references). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'spawning teammates', 'creating a team', 'setting up reviewers or implementers', 'coordinating multi-agent work', 'kit:team-orchestration'. Covers both natural language and technical identifiers. | 3 / 3 |
Distinctiveness Conflict Risk | Occupies a clear niche around multi-agent team orchestration with distinct concepts like 'TeamCreate', 'SendMessage', 'teammate spawning', and 'kit:team-orchestration' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%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 orchestration skill that clearly defines the lifecycle and coordination patterns for multi-agent teams. Its strengths are in workflow clarity and conciseness—it avoids over-explaining and provides clear sequential processes with validation steps. The main weakness is actionability: while tool names and parameters are mentioned, there are no concrete invocation examples showing exact syntax, which would make the skill more immediately executable.
Suggestions
Add concrete invocation examples for key tools (e.g., show exact TaskCreate call with all parameters like subject, description, activeForm, and team_name)
Show a complete mini-example of a TaskUpdate call with addBlockedBy to make dependency setup copy-paste ready
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured. It avoids explaining what teams, tasks, or messaging are conceptually and jumps straight into how to use them. Every section earns its place with specific guidance rather than filler. | 3 / 3 |
Actionability | The skill provides specific tool names (TeamCreate, TaskCreate, TaskUpdate, SendMessage, TaskList, TeamDelete) and naming conventions, but lacks executable code examples or copy-paste ready command sequences. The guidance is concrete in structure but relies on tool names without showing exact invocation syntax or parameters beyond brief mentions. | 2 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced: team setup (create → spawn → verify), task coordination (create → dependencies → assign → monitor), and shutdown (verify → request → wait → delete). Validation checkpoints are explicit (verify team config after spawning, check TaskList before shutdown), and the lifecycle diagram clearly shows the persistent teammate flow. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and a logical flow from setup to shutdown. However, for a skill of this length (~120 lines), some sections like the parallelism rules table and red flags could be split into referenced files. The integration section mentions domain skills but doesn't provide clear navigation links to related materials. | 2 / 3 |
Total | 10 / 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
- shousper/claude-kit
- Commit
a01bac9
- 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.