agent-swarm
Agent skill for swarm - invoke with $agent-swarm
35
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically deficient across all dimensions. It provides only a name and invocation command without explaining what the skill does, what actions it performs, or when it should be used. Claude would have no basis for selecting this skill appropriately from a list of available skills.
Suggestions
Add concrete actions describing what the swarm agent actually does (e.g., 'Coordinates multiple sub-agents to parallelize complex tasks' or 'Orchestrates distributed processing across agent instances').
Include a 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user needs to parallelize work, coordinate multiple agents, or handle tasks requiring distributed processing').
Define the specific domain or niche this skill serves to distinguish it from other agent-related skills (e.g., specify if it's for code review, data processing, research, etc.).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for swarm' is completely abstract with no indication of what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. It only provides an invocation command ($agent-swarm) without explaining purpose or use cases. | 1 / 3 |
Trigger Term Quality | The only potential trigger term is 'swarm' which is technical jargon without context. No natural keywords a user would say when needing this skill are present. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'agent skill' is extremely generic and could apply to virtually any agent-based functionality. Without specifics, there's no way to distinguish this from other agent-related skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a decent overview of swarm orchestration concepts and API signatures, but lacks the concrete, executable guidance needed for Claude to actually orchestrate swarms effectively. The content is more descriptive than instructive, with abstract workflow steps instead of specific sequences with validation checkpoints. The API examples show function signatures but not complete, working code.
Suggestions
Add a complete, executable example showing a full swarm workflow from initialization through task completion, including error handling
Replace abstract orchestration steps with concrete sequences including validation checkpoints (e.g., 'After swarm_init, verify status shows READY before spawning agents')
Remove explanatory content about what topologies and agent types are - instead show when to use each with concrete decision criteria
Add error recovery guidance: what to do when agent_spawn fails, when tasks timeout, or when swarm becomes unhealthy
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content includes some unnecessary explanation (describing what each topology and agent type does when Claude could infer this), but the code examples are reasonably compact. The 'Your orchestration approach' and 'Quality standards' sections add padding without actionable value. | 2 / 3 |
Actionability | Provides concrete JavaScript function calls with parameters, which is good. However, these appear to be pseudocode/API signatures rather than executable examples - there's no context on how to actually invoke these (imports, setup, error handling), and no complete workflow example showing real usage. | 2 / 3 |
Workflow Clarity | The 'orchestration approach' lists abstract steps (Task Analysis, Topology Selection, etc.) but provides no concrete sequence for executing a swarm operation. No validation checkpoints, no error recovery guidance, and no feedback loops for what to do when agents fail or tasks don't complete. | 1 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections (toolkit, topologies, agent types), but everything is inline in one file. For a skill of this complexity, detailed API reference and examples could be split into separate files. No references to external documentation. | 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.
- 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.