Content
65%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is highly actionable with concrete commands and full workflow templates, but it is verbose and monolithic, packing what should be separate reference materials into one oversized file. Batch and destructive operations lack validation feedback loops.
Suggestions
Move the workflow templates and command reference into separate reference files and link to them one level deep, leaving SKILL.md as a lean overview.
Add explicit validation/verification steps before destructive or batch operations such as --auto-execute deploys and parallel PR creation.
Strip marketing buzzwords ('intelligent', 'Swarm-Powered', 'self-organizing') and redundant attribute tables to reduce token overhead.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The ~640-line body is mostly a dense catalog of concrete commands, but it is wrapped in heavy marketing padding ('self-organizing, adaptive', 'intelligent', 'Swarm-Powered') and emoji-laden attribute tables that could be tightened considerably. | 2 / 3 |
Actionability | Provides numerous copy-paste-ready commands (e.g. 'npx ruv-swarm actions generate-workflow --analyze-codebase --detect-languages --create-optimal-pipeline') and complete YAML workflow files with specific flags and structure. | 3 / 3 |
Workflow Clarity | Sequences appear in examples and an integration checklist exists, but batch and destructive operations (auto-execute deploys, --create-pr-complex auto-fix, parallel issue/PR creation) lack explicit validation checkpoints or feedback loops, capping workflow clarity at 2. | 2 / 3 |
Progressive Disclosure | Content is organized into collapsible <details> sections within a single monolithic file, but no bundle files exist and everything is inline; material that should be split into reference files (templates, command reference) is kept in one large document. | 2 / 3 |
Total | 9 / 12 Passed |