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

49%

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%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 is rich with concrete, parameterized code and clear phase sequencing, but it suffers from heavy repetition across four patterns, missing validation checkpoints in batch workflows, and a monolithic structure with no bundle references. Trimming repetition and splitting patterns into referenced files would substantially improve it.

Suggestions

Extract the four full pattern implementations into separate reference files (e.g. RESEARCH.md, DEVELOPMENT.md) and keep SKILL.md as a concise overview with one-level-deep links.

Add explicit validation/verification checkpoints to each workflow (e.g. check swarm_status and verify results before proceeding to the next phase) to support the batch/parallel operations.

Collapse the repetitive agent-spawn and tool-call boilerplate into a shared snippet, and move version-specific install commands and the 'Last Updated' line into a clearly marked setup/deprecated section.

Dimension	Reasoning	Score
Conciseness	The ~970-line body is noticeably verbose: four near-identical pattern blocks each repeat full agent-spawn arrays and the same tool-call structure, and it embeds time-sensitive info ('claude-flow@alpha', 'Last Updated: 2025-10-19', 'version 2.0.0') outside any deprecated section.	2 / 5
Actionability	It provides mostly executable guidance — concrete MCP tool calls with real parameters and runnable CLI fallbacks (`npx claude-flow swarm ...`) — with minor gaps where referenced variables (e.g. `findings`, `researchData`, `testPlan`) are used but never defined.	4 / 5
Workflow Clarity	Each pattern is sequenced into clear phases (Phase 1–4), but validation checkpoints are absent from the main workflows; since these involve batch/parallel operations, the rubric caps workflow clarity at 3.	3 / 5
Progressive Disclosure	No bundle files exist and the skill is a monolithic document with section headers, but the four full pattern implementations (each with complete code) are inlined content that would be better split into separate reference files; external links are present but not structured as one-level-deep references.	3 / 5
	Total	12 / 20 Passed

Description

48%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 names a specific niche and several natural use-case terms, but it lacks concrete action verbs and any explicit 'Use when' trigger guidance. Adding concrete actions and a trigger clause would lift the weaker dimensions.

Suggestions

Add concrete action verbs, e.g. 'Coordinate multi-agent swarms for parallel research, development, and testing workflows'.

Append an explicit trigger clause such as 'Use when the user needs distributed multi-agent orchestration, parallel task execution, or swarm coordination'.

Include common synonyms users might say ('multi-agent', 'parallel agents', 'task coordination') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('swarm orchestration patterns') and lists application areas ('research, development, testing, and complex distributed workflows') but contains no concrete action verbs — it describes patterns 'for' use cases rather than what the skill does.	2 / 5
Completeness	A clear 'what' is present (advanced swarm orchestration patterns) but there is no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric completeness is capped at 3 with 'when' only weakly implied via the listed use cases.	3 / 5
Trigger Term Quality	It surfaces several natural terms a user might say ('research', 'development', 'testing', 'distributed workflows') but leans on jargon ('swarm orchestration') and omits common synonyms such as 'multi-agent', 'parallel agents', or 'coordination'.	3 / 5
Distinctiveness Conflict Risk	'Advanced swarm orchestration patterns' carves out a fairly specific niche that is mostly distinct from generic skills, with only minor overlap risk against closely related coordination/orchestration skills.	4 / 5
	Total	12 / 20 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/ruvector
Path: .claude/skills/swarm-advanced/SKILL.md
Commit: 74d2a60

Reviewed: 3 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.