agent-swarm

Agent skill for swarm - invoke with $agent-swarm

2.27x

Quality

50%

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

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 delivers a concrete MCP toolkit and a clear orchestration sequence with good section structure, but it is padded with non-actionable prose, lacks validation checkpoints, and keeps all reference material inline. It is a competent but unpolished middle-of-the-road skill.

Suggestions

Add validation checkpoints to the workflow (e.g., check swarm_status after init before spawning agents; confirm scale targets before swarm_destroy).

Trim non-actionable padding — the introductory paragraph, the 'Quality standards' platitudes, and the closing paragraph earn few tokens.

Move detailed reference material (full tool API, topology and agent-type catalogs) into reference files and link them from SKILL.md for progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The toolkit, topology, and agent-type catalogs are lean, but the intro paragraph, the 'Quality standards' platitudes, and the closing paragraph add unnecessary padding, matching the score-2 anchor.	2 / 3
Actionability	The MCP toolkit gives concrete parameterized calls, but the 'orchestration approach' steps stay abstract and result/error-handling details are missing, leaving the guidance incomplete.	2 / 3
Workflow Clarity	A clear six-step sequence is present, but there are no validation checkpoints or error-recovery feedback loops for destructive/batch operations like swarm_destroy, capping it at 2.	2 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a monolithic inline body with no reference files or links despite reference-worthy content (full tool API, topology and agent-type catalogs), matching the score-2 anchor.	2 / 3
	Total	8 / 12 Passed

Description

50%

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 canonical frontmatter description ('Agent skill for swarm - invoke with $agent-swarm') identifies a domain but states no concrete capabilities and provides no use-when trigger, landing at middling scores across all dimensions. A richer description exists in a second frontmatter block inside the body, but the top-level description that a loader would use is weak.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when deploying, coordinating, or scaling multi-agent swarms in the Flow Nexus platform'.

Replace the vague 'Agent skill for swarm' with concrete capability verbs (e.g., 'Deploys, coordinates, and scales multi-agent swarms...').

Consolidate the duplicate frontmatter blocks so the canonical top-level description carries the real capabilities and triggers instead of the bare invocation line.

Dimension	Reasoning	Score
Specificity	It names the swarm domain and the invocation mechanism ('invoke with $agent-swarm') but lists no concrete capability actions, placing it above the vague score-1 anchor yet short of the action-listing score-2 anchor.	2 / 3
Completeness	It offers only a weak 'what' ('Agent skill for swarm') and no explicit 'when to use' trigger, so it is capped at 2 per the missing-'Use when' guideline.	2 / 3
Trigger Term Quality	It includes the natural keyword 'swarm' (and 'agent-swarm') a user might say, but misses common variations like 'multi-agent' or 'orchestration', matching the score-2 anchor.	2 / 3
Distinctiveness Conflict Risk	The swarm niche is fairly distinct, but the vague framing ('Agent skill for swarm') leaves it able to overlap with related skills, matching the score-2 anchor.	2 / 3
	Total	8 / 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/ruflo
Path: .agents/skills/agent-swarm/SKILL.md
Commit: 26c35b5

Reviewed: about 4 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.