swarm-advanced
Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows
48
21%
Does it follow best practices?
Impact
100%
3.84xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/swarm-advanced/SKILL.mdQuality
Discovery
14%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 overly vague and reads more like a buzzword-laden tagline than a functional skill description. It fails to specify concrete actions, lacks a 'Use when...' clause, and uses terms so broad ('research', 'development', 'testing') that it would likely conflict with many other skills in a large skill library.
Suggestions
Add a 'Use when...' clause with specific trigger scenarios, e.g., 'Use when the user needs to coordinate multiple parallel agents, distribute tasks across sub-agents, or orchestrate multi-step research pipelines.'
Replace vague language with concrete actions, e.g., 'Spawns and coordinates multiple sub-agents for parallel task execution, aggregates results from distributed workers, and manages agent communication patterns.'
Narrow the scope to reduce conflict risk—specify what distinguishes this from general development, testing, or workflow skills, such as mentioning specific swarm patterns, agent counts, or the type of distributed coordination involved.
| 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 operations (e.g., 'spawn agents', 'coordinate tasks', 'aggregate results') are mentioned. | 1 / 3 |
Completeness | The description only vaguely addresses 'what' (orchestration patterns) and completely lacks a 'when' clause or any explicit trigger guidance. There is no 'Use when...' or equivalent statement. | 1 / 3 |
Trigger Term Quality | It includes some relevant keywords like 'swarm', 'orchestration', 'research', 'development', 'testing', and 'distributed workflows', but these are broad and somewhat jargon-heavy. A user might say 'swarm' or 'orchestration' but the terms lack natural variation and specificity. | 2 / 3 |
Distinctiveness Conflict Risk | The description is very generic and could overlap with many skills related to development, testing, research, or any workflow orchestration. Terms like 'research', 'development', and 'testing' are extremely broad and would conflict with numerous other skills. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is extremely verbose and repetitive, presenting four nearly identical swarm patterns with full boilerplate code inline rather than using progressive disclosure. While it demonstrates concrete API shapes and clear phased workflows, the code examples reference undefined variables and aren't truly executable. The content would benefit enormously from being split into separate files per pattern, with the main SKILL.md serving as a concise overview.
Suggestions
Reduce the main SKILL.md to a concise overview (~100 lines) covering topology selection, agent strategies, and the quick start, then move each pattern (Research, Development, Testing, Analysis) into separate referenced files like RESEARCH_SWARM.md, DEV_SWARM.md, etc.
Make code examples truly executable by defining all referenced variables (e.g., `findings`, `researchData`, `testSuites`) or replace with complete, self-contained snippets that can be copy-pasted.
Add explicit validation checkpoints between workflow phases (e.g., 'Check swarm_status before proceeding to Phase 2; if any agent failed, restart it before continuing').
Remove explanatory content Claude already knows (e.g., what mesh/hierarchical/star topologies are conceptually, generic best practices like 'implement proper error handling') and focus only on tool-specific guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 600+ lines with massive repetitive code blocks. The four swarm patterns (Research, Development, Testing, Analysis) follow nearly identical structures with redundant agent spawning boilerplate. Topology descriptions, best practices, and troubleshooting sections explain concepts Claude already knows. Much of this could be condensed to a fraction of its size. | 1 / 3 |
Actionability | Provides concrete MCP tool call syntax and CLI commands, which is good. However, the code is pseudocode-like JavaScript that isn't truly executable (e.g., `mcp__claude-flow__swarm_init({...})` as function calls with `await` mixed inconsistently, undefined variables like `findings`, `researchData`, `testSuites`). The examples show API shapes but aren't copy-paste ready. | 2 / 3 |
Workflow Clarity | Each pattern has clear phased workflows (Phase 1-4) with logical sequencing. However, validation checkpoints are largely absent — there's no explicit 'verify this succeeded before proceeding' step between phases. The error handling section exists but is generic and not integrated into the workflow phases. For complex distributed operations, missing feedback loops between phases is a significant gap. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no bundle files to offload detail into. All four patterns with full code examples are inline, making the skill extremely long. The 'Related Skills' and 'References' sections at the bottom reference external resources but the core content desperately needs splitting — each pattern could be its own file with the SKILL.md serving as an overview with links. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
81%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/ruvector
- Commit
c2089c4
- Reviewed
Table of Contents
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.