agent-swarm
Agent skill for swarm - invoke with $agent-swarm
47
17%
Does it follow best practices?
Impact
100%
2.27xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-swarm/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 provides no information about what the skill does, when it should be used, or what distinguishes it from other skills. It reads more like a label than a functional description, making it nearly impossible for Claude to correctly select this skill from a pool of available options.
Suggestions
Add concrete actions describing what the skill actually does (e.g., 'Orchestrates multiple sub-agents to collaboratively solve complex tasks by dividing work, coordinating outputs, and merging results').
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 needs to parallelize work across multiple agents, coordinate multi-step workflows, or distribute tasks').
Remove the invocation command ('invoke with $agent-swarm') from the description and replace it with domain-specific keywords and capability details that help Claude distinguish this skill from others.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions whatsoever. 'Agent skill for swarm' is entirely vague and abstract, giving no indication of what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states it's an 'agent skill for swarm' with an invocation command, providing no functional or contextual information. | 1 / 3 |
Trigger Term Quality | The only keyword is 'swarm', which is not a natural term users would use to describe a task. '$agent-swarm' is a command invocation, not a trigger term. There are no natural language keywords that would help Claude match user requests. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's impossible to distinguish it from any other agent-related skill. 'Agent skill for swarm' could mean virtually anything, creating high conflict risk with any other agent or orchestration skill. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is overly verbose, spending significant tokens on persona description, concept explanations, and enumerated lists that Claude doesn't need. While the MCP tool call examples provide some actionable guidance, the skill lacks concrete decision-making criteria, validation steps, error handling workflows, and practical examples showing complete input-to-output scenarios. The content reads more like marketing documentation than an actionable skill.
Suggestions
Remove the persona framing and concept explanations (topology definitions, agent type descriptions, quality standards) — Claude already understands these concepts. Focus on when to use each topology/agent type with concrete decision criteria.
Add a complete end-to-end example showing a real task being decomposed, agents spawned, tasks orchestrated, and results aggregated — with actual expected outputs.
Add explicit validation checkpoints: how to verify swarm initialization succeeded, how to check agent health before orchestrating tasks, and error recovery steps when agents fail.
Trim the quality standards and generic advice sections entirely — they describe good practices Claude already knows without providing any skill-specific actionable guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive explanations of concepts Claude already knows (what topologies are, what agent types do, generic quality standards). The bullet-point lists of agent types, topologies, and quality standards are largely redundant with the code examples and add little actionable value. The persona framing ('You are a Flow Nexus Swarm Agent, a master orchestrator...') is unnecessary padding. | 1 / 3 |
Actionability | The code examples show concrete MCP tool calls with parameters, which is useful. However, the code is illustrative rather than executable in context—there's no guidance on when to use which topology, no example of a complete workflow from input to output, and the orchestration approach is described abstractly rather than with concrete decision criteria. | 2 / 3 |
Workflow Clarity | The 6-step orchestration approach provides a sequence but lacks validation checkpoints, error recovery steps, or feedback loops. For a system involving multi-agent deployment and scaling (which are potentially destructive/complex operations), there's no guidance on verifying swarm health before proceeding, handling failed agent spawns, or validating task completion. | 2 / 3 |
Progressive Disclosure | The content is a monolithic document with no references to external files and no clear separation between quick-start and advanced content. Everything is inline in one long file. For a skill of this complexity (multiple topologies, agent types, management operations), the content would benefit from being split into overview + detailed references, but there are no bundle files to support this. | 2 / 3 |
Total | 7 / 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/ruflo
- Commit
844f68d
- 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.