Name: swarm-advanced
Rating: 66.4 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

swarm-advanced

Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows

3.84x

Quality

50%

Does it follow best practices?

Impact

100%

3.84x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/swarm-advanced/SKILL.md

The canonical home for this skill is swarm-advanced in ruvnet/agentic-flow

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 content is rich with concrete, well-structured code and clearly sequenced workflows, but it is overly long and repetitive, not fully executable due to undefined placeholder variables, and monolithic rather than progressively disclosed. It lands at the mid-level on every dimension.

Suggestions

Split the four detailed patterns and 'Advanced Techniques' into separate reference files (e.g. PATTERNS.md, ADVANCED.md), keeping SKILL.md as a concise overview with one-level-deep links.

Add explicit validation/verification checkpoints between workflow phases, especially after batch and parallel operations.

Either define the placeholder variables (findings, researchData, testSuites) or explicitly mark them as illustrative so the examples read as executable rather than pseudocode.

Dimension	Reasoning	Score
Conciseness	The body is ~960 lines with four near-identical pattern sections (research/development/testing/analysis), each repeating the same swarm_init → agent_spawn → parallel_execute structure. It mostly avoids explaining concepts Claude knows, but the heavy repetition could be tightened considerably, so it sits at the mostly-efficient-but-could-tighten 2-anchor rather than the lean 3-anchor.	2 / 3
Actionability	Concrete MCP calls with specific parameters (topology, maxAgents, strategy) and CLI fallback commands are provided throughout. However the code references undefined variables (findings, researchData, testSuites, securityScanLogs, successfulWorkflows) so it is not fully copy-paste executable, matching the incomplete-guidance 2-anchor rather than the executable 3-anchor.	2 / 3
Workflow Clarity	Multi-step processes are clearly sequenced into Phase 1–4 across patterns, and an error-handling section shows a retry feedback loop. But the batch/parallel operations (parallel_execute, batch_process) lack explicit validate-then-proceed checkpoints between phases, which per guidelines caps workflow clarity at 2.	2 / 3
Progressive Disclosure	Sections are well-organized, but the entire skill is a single monolithic ~960-line file with the four detailed patterns and advanced techniques all inline. No bundle files exist and references are external URLs, so content that should be split into reference files is inline, matching the 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 description identifies a clear niche and use-case areas but stays abstract and omits an explicit trigger clause, leaving every dimension at the mid-level. Concrete actions and a "Use when..." statement would lift it substantially.

Suggestions

Add an explicit 'Use when...' clause with natural triggers, e.g. 'Use when coordinating multiple parallel agents for research, development, or testing workflows.'

Replace abstract 'patterns' with concrete actions such as 'initialize swarms, spawn specialized agents, orchestrate parallel tasks, and manage distributed state'.

Include common user phrasings ('coordinate agents', 'parallel research', 'distributed testing') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and action ("swarm orchestration patterns") plus areas ("research, development, testing, and complex distributed workflows"), but lists no concrete operations such as spawning agents or coordinating tasks. It is above the vague 1-anchor but below the multi-concrete-action 3-anchor.	2 / 3
Completeness	States what the skill covers (orchestration patterns) but provides no explicit "Use when..." trigger clause; "for research, development, testing" only implies when. Per guidelines, a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	"swarm orchestration" is technical jargon a user would rarely say verbatim, while "research, development, testing" are natural but lack common variations. Relevant keywords are present but coverage of terms users would actually say is incomplete.	2 / 3
Distinctiveness Conflict Risk	"swarm orchestration" is a recognizable niche, but the appended broad domains (research, development, testing) overlap with many other skills, so it could still trigger for the wrong skill. Not generic enough for 1, not distinct enough for 3.	2 / 3
	Total	8 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (974 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: ruvnet/RuView
Path: .claude/skills/swarm-advanced/SKILL.md
Commit: d9dfea2

Reviewed: about 14 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.