agent-coordinator-swarm-init
Agent skill for coordinator-swarm-init - invoke with $agent-coordinator-swarm-init
39
10%
Does it follow best practices?
Impact
87%
2.80xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-coordinator-swarm-init/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an extremely weak description that fails on every dimension. It reads as a placeholder or auto-generated stub rather than a functional skill description. It provides no information about what the skill does, when to use it, or what user requests should trigger it.
Suggestions
Add a clear statement of what the skill does with concrete actions (e.g., 'Initializes a coordinated swarm of sub-agents to parallelize tasks across multiple workstreams').
Add an explicit 'Use when...' clause with natural trigger terms that describe scenarios where this skill should be selected (e.g., 'Use when the user wants to split work across multiple agents, coordinate parallel tasks, or initialize a multi-agent workflow').
Remove the invocation syntax from the description and replace it with functional content — the description should help Claude decide *whether* to use the skill, not *how* to invoke it.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for coordinator-swarm-init' is entirely abstract and does not describe what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states the invocation command, providing no functional information or trigger guidance. | 1 / 3 |
Trigger Term Quality | The only terms present are technical jargon ('coordinator-swarm-init', '$agent-coordinator-swarm-init') that no user would naturally say. There are no natural language keywords that would help Claude match user requests to this skill. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's impossible to distinguish this skill from any other agent or coordinator skill. The term 'swarm-init' hints at a niche but without any explanation, it provides no meaningful differentiation. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
20%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a high-level design document or README than an actionable skill for Claude. It describes what a swarm initializer should do conceptually but provides almost no concrete, executable guidance on how to actually initialize swarms, configure topologies, or allocate resources. The hooks in the frontmatter contain the only real commands, while the body is largely descriptive padding.
Suggestions
Replace the vague 'Usage Examples' section with concrete, executable command sequences showing how to actually initialize a swarm with specific topology configurations and agent counts.
Add concrete memory coordination command examples with actual `npx claude-flow@alpha memory store/search` syntax for each of the 5 mandatory protocol steps.
Add validation checkpoints to the workflow: e.g., after spawning agents, verify each agent has written its initial status to memory before proceeding to task orchestration.
Remove or drastically condense the 'Best Practices' and 'Integration Points' sections — these are generic advice that Claude can infer, and they consume tokens without adding actionable value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is verbose and explains many concepts Claude already understands (what topologies are, what resource allocation means, generic best practices like 'choose topology based on task characteristics'). Much of the content is descriptive padding rather than actionable instruction. The 'Integration Points' and 'Best Practices' sections are largely obvious advice. | 1 / 3 |
Actionability | Despite describing a complex coordination task, the skill provides no executable code, no concrete commands for initializing a swarm, no specific configuration examples, and no copy-paste ready snippets. The 'Usage Examples' section contains only vague natural language prompts rather than actual implementation guidance. The memory coordination protocol lists key patterns but without concrete command syntax beyond what's in the hooks. | 1 / 3 |
Workflow Clarity | The MANDATORY Memory Coordination Protocol provides a 5-step sequence which is helpful, and the Handoff Patterns show multi-step flows. However, there are no validation checkpoints, no error recovery feedback loops, and no concrete verification steps to confirm agents are actually writing to memory as required. For a destructive/batch coordination operation, this lack of validation caps the score. | 2 / 3 |
Progressive Disclosure | The content has reasonable section organization with headers, but it's a monolithic document with no references to external files for detailed content. The topology descriptions, integration points, and best practices could be split out. However, with no bundle files provided, the inline approach is somewhat justified, though the content that is inline is more descriptive than useful. | 2 / 3 |
Total | 6 / 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
e6dc21f
- 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.