agent-coordination
Agent spawning, lifecycle management, and coordination patterns. Manages 60+ agent types with specialized capabilities. Use when: spawning agents, coordinating multi-agent tasks, managing agent pools. Skip when: single-agent work, no coordination needed.
Install with Tessl CLI
npx tessl i github:ruvnet/claude-flow --skill agent-coordination87
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 89%
↑ 1.34xAgent success when using this skill
Validation for skill structure
Discovery
89%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 solid skill description with excellent completeness and trigger term coverage. The explicit 'Use when' and 'Skip when' clauses provide clear guidance for skill selection. The main weakness is the specificity of capabilities - '60+ agent types with specialized capabilities' is vague and could benefit from concrete examples of what actions can be performed.
Suggestions
Replace '60+ agent types with specialized capabilities' with 2-3 concrete examples of agent types or specific actions (e.g., 'spawn worker agents, terminate idle agents, route tasks between specialized agents')
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (agent management) and some actions (spawning, lifecycle management, coordination patterns), but 'manages 60+ agent types with specialized capabilities' is vague about what those capabilities actually are. Lacks concrete specific actions like 'create worker agents, terminate idle agents, route tasks between agents'. | 2 / 3 |
Completeness | Clearly answers both what (agent spawning, lifecycle management, coordination patterns, manages 60+ agent types) AND when (explicit 'Use when:' clause with spawning agents, coordinating multi-agent tasks, managing agent pools). Also includes helpful 'Skip when' guidance. | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms: 'spawning agents', 'coordinating multi-agent tasks', 'managing agent pools', 'agent types'. These are terms users would naturally use when needing this functionality. The 'Skip when' clause also helps clarify boundaries. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on multi-agent coordination and spawning. The 'Skip when: single-agent work' clause explicitly distinguishes it from general agent skills. Unlikely to conflict with other skills due to specific multi-agent focus. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill excels at conciseness and actionability - it provides executable commands and clear agent categorization without unnecessary explanation. However, it lacks workflow guidance for actually coordinating multi-agent tasks (the core purpose) and could better leverage progressive disclosure for the extensive agent type catalog.
Suggestions
Add a complete workflow example showing how to spawn, coordinate, and manage a multi-agent task from start to finish with validation checkpoints
Include error handling guidance: what to do when agent spawn fails, how to verify agent health before assigning tasks
Add references to detailed documentation for each agent category (e.g., 'See [SWARM-AGENTS.md](SWARM-AGENTS.md) for swarm coordinator details')
Include a feedback loop for agent coordination: monitor -> detect issues -> recover/restart pattern
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is lean and efficient - lists agent types tersely, provides executable commands without explanation of what agents are or how they work. Every section earns its place. | 3 / 3 |
Actionability | Provides fully executable bash commands that are copy-paste ready. The routing codes table gives concrete agent combinations for specific task types. Commands include all necessary flags. | 3 / 3 |
Workflow Clarity | Commands are listed but there's no sequenced workflow showing how to coordinate a multi-agent task from start to finish. Missing validation checkpoints for agent health, no error recovery guidance, and no feedback loops for failed agent spawns. | 2 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but for 60+ agent types mentioned in the description, this could benefit from references to detailed documentation for each agent category. All content is inline with no external references. | 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.
- 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.