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.
74
63%
Does it follow best practices?
Impact
89%
1.34xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-coordination/SKILL.mdQuality
Discovery
75%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 description has strong structural completeness with explicit 'Use when' and 'Skip when' clauses, and occupies a distinct niche around multi-agent coordination. However, it could be more specific about the concrete actions it performs beyond high-level categories, and the trigger terms lean technical rather than matching natural user language.
Suggestions
Add more specific concrete actions, e.g., 'spawn specialized agents, distribute subtasks across agent pools, monitor agent health, handle agent failures and retries'
Include more natural trigger term variations users might say, such as 'run multiple agents,' 'parallel execution,' 'delegate tasks,' 'orchestrate agents,' or 'agent workflow'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (agent spawning, lifecycle management, coordination) and mentions '60+ agent types with specialized capabilities,' but doesn't list specific concrete actions beyond high-level categories. The actions remain somewhat abstract—what does 'coordination patterns' actually entail? | 2 / 3 |
Completeness | Clearly answers both 'what' (agent spawning, lifecycle management, coordination patterns, 60+ agent types) and 'when' with explicit 'Use when' and 'Skip when' clauses that provide clear trigger and exclusion guidance. | 3 / 3 |
Trigger Term Quality | Includes relevant terms like 'spawning agents,' 'multi-agent tasks,' 'agent pools,' and 'coordination,' but these are somewhat technical. Missing natural variations users might say like 'run multiple agents,' 'parallel agents,' 'delegate to agents,' 'orchestrate,' or 'agent workflow.' | 2 / 3 |
Distinctiveness Conflict Risk | The focus on multi-agent spawning, lifecycle management, and coordination is a clear niche. The 'Skip when' clause for single-agent work further sharpens distinctiveness and reduces conflict risk with simpler agent-related skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
52%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is concise and provides useful reference material for agent types and CLI commands. However, it critically lacks workflow guidance for its core purpose—coordinating multi-agent tasks. For a skill managing 60+ agent types with complex coordination patterns, the absence of step-by-step orchestration workflows with validation checkpoints is a significant gap.
Suggestions
Add a complete multi-agent coordination workflow example (e.g., 'Bug Fix Workflow: 1. Spawn coordinator → 2. Spawn researcher → 3. Wait for research output → 4. Spawn coder → 5. Validate fix → 6. Spawn tester → 7. Confirm tests pass → 8. Stop all agents') with explicit validation and error recovery steps.
Include guidance on what to do when agents fail or become unresponsive (e.g., check status, retry, stop and respawn), as multi-agent coordination involves destructive/batch operations that need feedback loops.
Add references to detailed documentation files for agent type capabilities (e.g., 'See [AGENT_TYPES.md](AGENT_TYPES.md) for full list of 60+ agents and their capabilities') and coordination pattern details.
Show a concrete end-to-end example using the routing codes, demonstrating the actual commands needed to execute a routing code workflow from start to finish.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-organized. It lists agent types, commands, and routing codes without unnecessary explanation. No concepts are over-explained, and every section earns its place. | 3 / 3 |
Actionability | Commands are concrete and copy-paste ready, which is good. However, there's no example of a complete multi-agent coordination workflow showing how to actually orchestrate agents together (e.g., spawning multiple agents and coordinating them for a task). The routing codes table hints at workflows but doesn't show how to execute them. | 2 / 3 |
Workflow Clarity | For a skill about coordinating multi-agent tasks, there is no sequenced workflow showing how to spawn, coordinate, and manage agents through a complete task lifecycle. No validation checkpoints, no error recovery, no feedback loops for what to do when agents fail or tasks stall. The 'Best Practices' section is vague guidance rather than a clear process. | 1 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections and a routing codes table. However, with 60+ agent types mentioned in the description, the inline listing of agent types could benefit from referencing a separate detailed file. No external references are provided for deeper documentation on specific agent types or coordination patterns. | 2 / 3 |
Total | 8 / 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
- ruvnet/claude-flow
- Commit
01070ed
- 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.