agent-multi-repo-swarm
Agent skill for multi-repo-swarm - invoke with $agent-multi-repo-swarm
39
9%
Does it follow best practices?
Impact
87%
4.34xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-multi-repo-swarm/SKILL.mdQuality
Discovery
7%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an extremely weak skill description that essentially provides no useful information beyond a name and invocation command. It fails to describe any capabilities, actions, or usage triggers, making it nearly impossible for Claude to determine when to select this skill. It reads more like a label than a description.
Suggestions
Add concrete actions describing what the skill does, e.g., 'Coordinates changes across multiple repositories, synchronizes dependencies, and manages cross-repo pull requests.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs to make coordinated changes across multiple repositories, sync dependencies between repos, or manage multi-repo workflows.'
Replace the jargon 'multi-repo-swarm' with natural language descriptions of the domain, such as 'multiple repositories', 'cross-repo changes', 'monorepo alternatives', etc.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions whatsoever. It only says 'Agent skill for multi-repo-swarm' which is entirely vague and abstract, giving no indication of what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. It only provides an invocation command ($agent-multi-repo-swarm) but no explanation of capabilities or usage triggers. | 1 / 3 |
Trigger Term Quality | The only potentially useful term is 'multi-repo-swarm' which is technical jargon, not a natural keyword a user would say. There are no natural language trigger terms like 'multiple repositories', 'cross-repo', etc. | 1 / 3 |
Distinctiveness Conflict Risk | The specific invocation command '$agent-multi-repo-swarm' and the term 'multi-repo-swarm' are distinctive enough that it's unlikely to conflict with other skills, but the lack of any descriptive content makes it hard to properly distinguish its purpose from other multi-repo or agent skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
12%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an extremely bloated, largely non-actionable document that reads more like a product marketing page for a fictional 'ruv-swarm' tool than a practical skill guide. The vast majority of commands are invented CLI invocations that cannot be executed, bash examples contain systematic path syntax errors ($ instead of /), and the document includes unnecessary conceptual content (GraphQL schemas, Kafka configs, synchronization theory) that wastes tokens without providing executable guidance. The few sections with real gh CLI usage are buried in hundreds of lines of noise.
Suggestions
Strip the document down to 50-80 lines focusing only on the core workflow: discovering repos with gh CLI, executing changes across them, and creating/linking PRs — with correct, executable bash syntax.
Fix all path syntax errors where '$' is used instead of '/' (e.g., 'repos$org/$repo' should be 'repos/org/repo').
Remove all references to the unverifiable 'npx ruv-swarm' CLI tool, or clearly document how to install and verify it exists before use.
Split advanced topics (communication strategies, synchronization patterns, monitoring) into separate referenced files, keeping SKILL.md as a concise overview with links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 400+ lines with massive amounts of speculative, non-executable content. Includes conceptual sections (GraphQL federation, Kafka config, synchronization patterns, communication strategies) that are not actionable and pad the token budget enormously. Many sections repeat the same pattern of 'npx ruv-swarm github <command> --flags' without adding real value. | 1 / 3 |
Actionability | Most commands reference 'npx ruv-swarm github' which appears to be a fictional/unverifiable CLI tool with invented subcommands. The bash scripts in sections 1-3 contain syntax errors (using '$' instead of '/' in paths like 'repos$org/$repo$contents$package.json') making them non-executable. The webhook JavaScript and GraphQL examples are illustrative pseudocode, not actionable guidance. | 1 / 3 |
Workflow Clarity | The Synchronized Operations and Dependency Management sections do show multi-step workflows with some sequencing (clone, modify, test, create PR). However, there are no explicit validation checkpoints or error recovery loops beyond a single test check. The vast majority of sections are just single CLI commands with no workflow structure at all. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no meaningful content hierarchy. Everything is dumped into a single massive file covering initialization, discovery, configuration, orchestration, communication, monitoring, synchronization, use cases, best practices, performance, and troubleshooting. References to swarm-pr.md and project-board-sync.md at the bottom, but no bundle files exist. Content desperately needs splitting into focused sub-documents. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (558 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- ruvnet/ruflo
- Commit
48ca369
- 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.