Name: agent-swarm
Rating: 72 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-swarm

Agent skill for swarm - invoke with $agent-swarm

2.27x

Quality

56%

Does it follow best practices?

Impact

100%

2.27x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-swarm/SKILL.md

The canonical home for this skill is agent-swarm in ruvnet/claude-flow

Quality

Content

57%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body delivers concrete, executable MCP examples and a clear orchestration sequence, but is padded with persona prose and lacks validation/feedback loops for destructive swarm operations, and inlines reference material that would benefit from separation. Tightening prose and adding explicit validation checkpoints would most improve the weakest dimensions.

Suggestions

Add explicit validation/verification checkpoints for destructive and batch operations (e.g., check swarm_status before swarm_destroy; verify task_orchestrate results before scaling).

Trim persona prose ("You are…", "Your core responsibilities", the closing "always consider…" sentence) and consolidate restated quality standards to improve token efficiency.

Split the topology and agent-type catalogs into a separate references file (e.g., REFERENCES.md) with clearly signaled one-level-deep links from SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but padded with persona prose ("You are a Flow Nexus Swarm Agent, a master orchestrator…"), restated responsibility/quality lists, and a closing summary that repeats earlier points, fitting anchor 3.	3 / 5
Actionability	Concrete MCP toolkit code with real function names and parameters plus enum-style agent-type/topology references give mostly executable guidance, though placeholders like swarm_id: "id" and the illustrative-snippet form keep it below anchor 5.	4 / 5
Workflow Clarity	A clear 6-step orchestration sequence is present but has no validation checkpoints or error-recovery feedback loops; since scaling and destroying swarms are batch/destructive operations, the rubric caps workflow clarity at 3.	3 / 5
Progressive Disclosure	No bundle files exist and all content is inlined; section headers give some structure, but reference-style catalogs (topologies, agent types, quality standards) are inlined in a ~70-line body rather than split out, matching anchor 3.	3 / 5
	Total	13 / 20 Passed

Description

56%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description clearly states what the skill does with concrete verbs and a distinct niche, but lacks an explicit trigger clause and leans on technical jargon rather than natural user phrases. Adding a 'Use when…' sentence with common synonyms would raise both completeness and trigger quality.

Suggestions

Add an explicit 'Use when…' clause naming natural user triggers (e.g., 'Use when the user asks to deploy or coordinate a multi-agent swarm, orchestrate agents, or scale agent teams').

Include common synonyms and concrete trigger phrases users would actually say (e.g., 'agent swarm', 'multi-agent', 'orchestrate agents', 'Flow Nexus').

Broaden the action list toward comprehensive coverage (e.g., monitor, debug, terminate) to lift specificity toward anchor 5.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ("Deploys, coordinates, and scales multi-agent swarms") plus the target platform, but coverage is not exhaustive, matching anchor 4 rather than 5.	4 / 5
Completeness	The 'what' is clear (deploys/coordinates/scales swarms) but there is no explicit 'Use when…' trigger clause, only weak implication via 'for complex task execution', which caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant terms like "swarm" and "multi-agent swarms" appear but lean technical; common natural variations a user would say are missing, fitting anchor 3.	3 / 5
Distinctiveness Conflict Risk	The Flow Nexus / multi-agent swarm niche is mostly distinct with only minor overlap risk against closely related agent-orchestration skills, matching anchor 4.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Path: .agents/skills/agent-swarm/SKILL.md
Commit: fa13ee4

Reviewed: about 9 hours ago

Table of Contents

Discovery Implementation Validation

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.