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.
The description is structurally well-formed with explicit 'Use when' and 'Skip when' clauses, which is a strong pattern. However, it remains somewhat abstract in describing capabilities—'lifecycle management' and 'coordination patterns' are high-level terms that don't convey specific concrete actions. The trigger terms could be expanded to include more natural user language variations.
Suggestions
Add specific concrete actions beyond category names, e.g., 'Spawns, monitors, restarts, and terminates agents; routes tasks across agent pools; handles inter-agent messaging and result aggregation.'
Expand trigger terms with natural user language variations 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. What does 'lifecycle management' actually entail? What coordination patterns? | 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 guidance and negative boundaries. | 3 / 3 |
Trigger Term Quality | Includes some 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, coordination, and pool management is a clear niche that is unlikely to conflict with other skills. The 'Skip when' clause for single-agent work further sharpens the boundary. | 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 provides a clean, concise reference for agent types and CLI commands, but falls short on its core purpose of teaching coordination patterns. It reads more like a command reference card than a coordination guide. The most critical gap is the absence of any end-to-end workflow showing how to actually coordinate multiple agents for a task, including validation and error recovery.
Suggestions
Add a complete end-to-end workflow example showing how to coordinate a multi-agent task (e.g., 'Bug Fix with Routing Code 1': spawn coordinator → spawn researcher → assign task → validate results → stop agents), including validation checkpoints and error recovery steps.
Add a 'Common Patterns' section with concrete examples of hierarchical coordination, including how agents communicate via memory and how to verify coordination is working.
Include error handling guidance: what to do when an agent fails, how to check agent health, and how to recover from coordination failures.
Consider splitting the agent type catalog into a separate AGENTS.md reference file and keeping SKILL.md focused on coordination workflows and patterns.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-organized. It lists agent types concisely without explaining what agents are or how coordination works conceptually. Every section serves a clear purpose with no padding. | 3 / 3 |
Actionability | Commands are concrete and copy-paste ready, which is good. However, there are no examples of complete workflows showing how to actually coordinate multiple agents together (e.g., spawning a team, assigning tasks, collecting results). The routing codes table hints at multi-agent patterns but doesn't show how to execute them. | 2 / 3 |
Workflow Clarity | For a skill about agent coordination, there is no sequenced workflow showing how to spawn, coordinate, and manage a multi-agent task end-to-end. Individual commands are listed but there's no validation, no error handling, no feedback loops for managing agent failures or checking coordination status. The routing codes suggest multi-step processes but don't describe the actual steps. | 1 / 3 |
Progressive Disclosure | The content is reasonably structured with clear sections and headers. However, with 60+ agent types mentioned in the description, the inline listing of agent types could benefit from a separate reference file. No external references are provided, and there are no bundle files to support deeper exploration of individual agent capabilities 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
9d4a9ea
- 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.