agent-swarm

Agent skill for swarm - invoke with $agent-swarm

2.27x

Quality

—

Does it follow best practices?

Impact

100%

2.27x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

50%

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

The body is a reasonably structured, system-prompt-style skill with a concrete MCP toolkit, but it is padded with buzzword prose, lacks validation checkpoints in its orchestration workflow, and keeps all reference material inline with no progressive disclosure. It also contains a misplaced duplicate frontmatter block at the top of the body.

Suggestions

Add validation/verification checkpoints to the orchestration workflow (e.g., call swarm_status to verify deployment before scaling).

Trim buzzword prose in the intro, closing, and "Quality standards" sections so every token earns its place.

Move the API toolkit/topology/agent-type reference into a separate reference file and link to it from a concise overview, and remove the stray duplicate frontmatter block from the body.

Dimension	Reasoning	Score
Conciseness	The toolkit code and topology/agent-type lists are useful, but the opening ("a master orchestrator...", "tackle complex problems through intelligent collaboration") and closing ("maximize collective intelligence while maintaining system stability") plus the vague "Quality standards" section are padded with buzzwords that could be trimmed; it is mostly efficient but could be tightened, so below level 3.	2 / 3
Actionability	The toolkit block provides concrete, parameterized MCP calls (swarm_init, agent_spawn, task_orchestrate), but much of the surrounding guidance is abstract direction ("Break down complex objectives into manageable agent tasks") with no complete end-to-end executable example, matching the level-2 anchor of some concrete guidance but incomplete.	2 / 3
Workflow Clarity	The 6-step orchestration approach gives a clear sequence, but there are no validation/verification checkpoints for batch/resource operations (deploy, scale, destroy); per the rubric this caps workflow clarity at 2 even though a sequence is present.	2 / 3
Progressive Disclosure	The body is organized into labeled sections but is monolithic — the API toolkit and reference material are inline with no external references (and no bundle files exist), matching the level-2 anchor of structure present but content that could be separate kept inline.	2 / 3
	Total	8 / 12 Passed

Description

22%

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 frontmatter description is weak: it states only a vague domain ("swarm") plus invocation syntax, with no concrete capabilities and no explicit use-when trigger. It reads as a placeholder rather than a discoverable, well-scoped skill description.

Suggestions

Rewrite the description to list concrete actions, e.g. "Deploys, coordinates, and scales multi-agent swarms..." rather than "Agent skill for swarm".

Add an explicit "Use when..." trigger clause naming natural user phrases (e.g. "Use when orchestrating multi-agent swarms or scaling agent teams").

Remove the invocation-syntax fragment "$agent-swarm" from the description; it is jargon, not a natural trigger term.

Dimension	Reasoning	Score
Specificity	The description "Agent skill for swarm - invoke with $agent-swarm" names no concrete actions, only the abstract domain "swarm"; this matches the vague/abstract anchor and is below level 2, which requires naming some actions.	1 / 3
Completeness	It offers only a very weak "what" ("Agent skill for swarm") and no "Use when..." trigger clause for the "when", satisfying the level-1 anchor where both what and when are weak/missing; it cannot reach 2 because there is no explicit when guidance.	1 / 3
Trigger Term Quality	"swarm" is a relevant keyword a user might say, but it is the only natural term and the rest ("invoke with $agent-swarm") is invocation syntax/jargon, so it has some relevant keywords while missing common variations.	2 / 3
Distinctiveness Conflict Risk	"swarm" gives it a somewhat distinct niche, but the generic "Agent skill for ..." framing and lack of specific triggers mean it could still overlap with other agent-orchestration skills, matching the level-2 anchor.	2 / 3
	Total	6 / 12 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/claude-flow
Commit: 8ae8752

Reviewed: 2 days 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.