swarm-advanced

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

3.84x

Quality

28%

Does it follow best practices?

Impact

100%

3.84x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/swarm-advanced/SKILL.md

Quality

Discovery

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

This description is too abstract and buzzword-heavy to be useful for skill selection. It fails to specify concrete actions, lacks natural trigger terms users would say, and provides no guidance on when Claude should select this skill. The vague domain listing (research, development, testing) makes it nearly impossible to distinguish from other skills.

Suggestions

Add a 'Use when...' clause specifying explicit triggers like 'multi-agent tasks', 'parallel processing', 'coordinating multiple Claude instances', or 'distributed task execution'

Replace abstract language with concrete actions such as 'Spawns and coordinates multiple agent instances, distributes tasks across workers, aggregates results from parallel executions'

Include natural keywords users might say like 'run in parallel', 'multiple agents', 'batch processing', 'concurrent tasks', or 'fan-out/fan-in'

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language like 'advanced swarm orchestration patterns' and 'complex distributed workflows' without listing any concrete actions. No specific capabilities are described.	1 / 3
Completeness	Only vaguely addresses 'what' (orchestration patterns) and completely lacks any 'when' guidance. No 'Use when...' clause or explicit trigger conditions are provided.	1 / 3
Trigger Term Quality	Uses technical jargon ('swarm orchestration patterns', 'distributed workflows') that users are unlikely to naturally say. Missing common variations or natural language triggers.	1 / 3
Distinctiveness Conflict Risk	The term 'swarm orchestration' provides some specificity, but 'research, development, testing' is extremely broad and could overlap with many other skills.	2 / 3
	Total	5 / 12 Passed

Implementation

50%

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

This skill provides highly actionable, executable code examples for swarm orchestration with comprehensive coverage of patterns and use cases. However, it suffers from severe verbosity - the content could be reduced by 60-70% while preserving all essential information. The repetitive pattern structure (spawn agents, execute phases, monitor) is shown multiple times with minor variations when a single template with customization notes would suffice.

Suggestions

Consolidate the four nearly-identical swarm patterns (Research, Development, Testing, Analysis) into a single template with a configuration table showing topology/agent differences for each use case

Move Advanced Techniques, Best Practices, and Troubleshooting sections to separate reference files (ADVANCED.md, BEST-PRACTICES.md) and link from a concise overview

Add explicit validation checkpoints within workflows (e.g., 'Verify swarm_status shows all agents healthy before proceeding to Phase 2')

Remove explanatory text about what topologies are - instead provide a quick reference table mapping use-case to topology choice

Dimension	Reasoning	Score
Conciseness	Extremely verbose at 700+ lines with extensive repetition of similar patterns. Much content explains concepts Claude already knows (what mesh topology is, basic error handling patterns) and includes redundant examples that could be consolidated.	1 / 3
Actionability	Provides fully executable code examples with specific MCP tool calls, complete parameter structures, and CLI fallback commands. Code is copy-paste ready with concrete function signatures and configurations.	3 / 3
Workflow Clarity	Multi-step workflows are clearly sequenced with phases (Phase 1, 2, 3, 4), but lacks explicit validation checkpoints and error recovery feedback loops within the workflows themselves. The error handling section exists but is separate from the main workflow patterns.	2 / 3
Progressive Disclosure	References external documentation at the end but the main content is a monolithic wall of code examples. Advanced techniques, best practices, and troubleshooting could be split into separate files. The 'Related Skills' section is good but inline content is excessive.	2 / 3
	Total	8 / 12 Passed

Validation

81%

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 — 9 / 11 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	9 / 11 Passed

Repository: ruvnet/ruv-FANN
Commit: 46f6f8a

Reviewed: about 1 month 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.