agent-swarm
Agent skill for swarm - invoke with $agent-swarm
43
11%
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
Add concrete actions describing what the swarm skill actually does (e.g., 'Coordinates multiple sub-agents to parallelize tasks such as X, Y, Z').
Add an explicit 'Use when...' clause with natural trigger terms that describe the situations where this skill should be selected (e.g., 'Use when the user needs to distribute work across multiple agents, parallelize tasks, or coordinate multi-agent workflows').
Replace the invocation instruction ('invoke with $agent-swarm') with a meaningful description of capabilities — invocation syntax belongs in the skill body, not the description field.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for swarm' is entirely vague and abstract, providing no information about what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. There is no explanation of capabilities and no 'Use when...' clause or equivalent trigger guidance. | 1 / 3 |
Trigger Term Quality | The only keyword is 'swarm', which is technical jargon without context. There are no natural user-facing trigger terms that someone would use when needing this skill. The invocation command '$agent-swarm' is not a natural language trigger. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it provides no clear niche. 'Agent skill for swarm' could mean anything and provides no distinguishing characteristics to differentiate it from other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
22%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 persona description and product overview than an actionable operational guide. While it provides useful MCP tool call signatures, the surrounding content is heavily padded with explanatory material that Claude doesn't need (topology definitions, agent type descriptions, generic quality standards). The workflow lacks concrete sequencing, validation steps, and error handling critical for orchestrating multi-agent systems.
Suggestions
Remove the descriptive lists of topologies, agent types, and quality standards—replace with a concise decision table or inline comments in the code examples showing when to use each option.
Add a concrete end-to-end workflow example showing the actual sequence of MCP calls with response handling, e.g.: init swarm → check status → spawn agents → orchestrate task → monitor → scale/destroy, with explicit validation between steps.
Add error handling guidance: what to check after each MCP call, how to recover from failed agent spawns or task orchestration failures, and when to use swarm_destroy.
Remove the persona-style opening paragraph and quality standards section—these don't add actionable information and consume token budget.
| 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. Much of the content reads like a product brochure rather than operational instructions. | 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 context—there's no guidance on how to handle responses, chain calls together, or deal with specific scenarios. The orchestration approach section is abstract rather than instructive. | 2 / 3 |
Workflow Clarity | The 6-step 'orchestration approach' is a high-level description of phases rather than a concrete workflow with validation checkpoints. There are no feedback loops, no error recovery steps, no validation between steps (e.g., checking swarm_status after init before deploying agents), and no guidance on what to do when operations fail. For a system involving multi-agent orchestration and scaling, this lack of validation is a significant gap. | 1 / 3 |
Progressive Disclosure | The content is organized into logical sections (toolkit, approach, topologies, agent types, quality standards), which provides some structure. However, it's a monolithic file with no references to external documentation, and several sections (topology descriptions, agent type descriptions, quality standards) could be separated or omitted entirely. No bundle files are provided to offload detail. | 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
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.