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 that Claude could use for skill selection.
Suggestions
Describe the concrete actions this skill performs (e.g., 'Coordinates multiple agents to perform parallel tasks, distributes workloads, and aggregates 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 run multiple tasks in parallel, coordinate agent workflows, or distribute work across agents').
Remove the invocation command ('invoke with $agent-swarm') from the description and replace it with capability-focused language that helps Claude distinguish this skill from others.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for swarm' is entirely vague and abstract, providing no information about what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description fails to explain the skill's purpose or provide any trigger guidance. | 1 / 3 |
Trigger Term Quality | The only keyword is 'swarm', which is technical jargon without context. There are no natural user-facing trigger terms that someone would use when needing this skill. '$agent-swarm' is an invocation command, not a trigger term. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it provides no distinguishing characteristics. 'Agent skill for swarm' could mean almost anything and offers no clear niche or distinct triggers. | 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 a persona/role description masquerading as actionable guidance. While it provides useful MCP tool call signatures, the majority of the content is descriptive padding (topology explanations, agent type descriptions, quality standards) that Claude doesn't need spelled out. The workflow lacks validation steps and error handling critical for orchestrating multi-agent systems.
Suggestions
Remove the descriptive sections about topologies, agent types, and quality standards—Claude can infer these from the tool parameters. Focus on decision-making heuristics (e.g., 'Use hierarchical when tasks have dependencies; use mesh for independent parallel work').
Add explicit validation and error recovery steps to the workflow: check swarm_status after init, verify agent health after spawn, handle task failures with retry logic.
Replace the illustrative code block with a concrete end-to-end example showing a complete orchestration flow including response handling and chaining calls.
Add guidance on when NOT to use swarms (simple tasks) and how to determine appropriate swarm size based on task complexity.
| 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 and topologies with descriptions are padding that doesn't add actionable value. The 'Your core responsibilities' and 'Quality standards' sections describe rather than instruct. | 1 / 3 |
Actionability | The JavaScript code examples showing MCP tool calls are concrete and provide specific function signatures with parameters, which is useful. However, the examples are illustrative rather than executable in a real workflow—there's no guidance on how to handle responses, chain calls together, or deal with errors. Much of the content is descriptive rather than instructional. | 2 / 3 |
Workflow Clarity | The 6-step orchestration approach provides a sequence but lacks validation checkpoints, error recovery steps, or feedback loops. For a multi-agent orchestration system where things can fail (agents not responding, tasks failing), there's no guidance on what to verify at each step or how to handle failures. This caps the score at 2. | 2 / 3 |
Progressive Disclosure | All content is inline in a single monolithic file with no references to external documentation. The topology descriptions, agent type descriptions, and quality standards could be separated or omitted. However, the content does have some structural organization with headers and sections, preventing a score of 1. | 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
398f7c2
- 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.