agent-multi-repo-swarm
Agent skill for multi-repo-swarm - invoke with $agent-multi-repo-swarm
35
3%
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 description that provides virtually no useful information for skill selection. It only names the skill and provides an invocation command, but fails to describe any capabilities, actions, or usage triggers. Claude would have no basis for selecting this skill appropriately from a pool of available skills.
Suggestions
Add concrete actions describing what the skill does, e.g., 'Coordinates tasks across multiple Git repositories, synchronizes changes, runs parallel operations across codebases'.
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user needs to work across multiple repositories simultaneously, coordinate cross-repo changes, or perform bulk operations on several codebases'.
Remove the invocation command from the description (it belongs in the skill body) and replace with meaningful capability and context information.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. It only says 'Agent skill for multi-repo-swarm' which is entirely vague and abstract, providing no information about 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 provides neither capability information nor usage triggers — only an invocation command. | 1 / 3 |
Trigger Term Quality | The only potentially relevant 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 term 'multi-repo-swarm' is somewhat distinctive as a specific tool/concept name, which reduces conflict risk slightly, but the lack of any descriptive content means it's still unclear what domain it operates in. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
0%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 verbose, largely aspirational document that reads more like a product roadmap or marketing spec than actionable instructions. The majority of commands reference a hypothetical 'ruv-swarm' CLI tool without verifying its existence, and the bash scripts contain path syntax errors throughout. The skill attempts to cover an enormous scope (microservices coordination, Kafka streaming, GraphQL federation, monorepo migration, etc.) without providing executable, validated guidance for any single workflow.
Suggestions
Reduce scope dramatically to 2-3 core workflows (e.g., cross-repo dependency update, synchronized PR creation) with fully executable, tested bash scripts using only gh CLI and standard tools
Fix all path syntax errors (e.g., 'repos$org/$repo' should be 'repos/org/repo') and remove or clearly mark 'npx ruv-swarm' commands as requiring a specific tool installation with verification steps
Add explicit validation checkpoints and rollback strategies for destructive cross-repo operations (e.g., verify PR creation succeeded, check test results before proceeding, rollback on failure)
Move communication strategies, synchronization patterns, configuration schemas, and troubleshooting into separate referenced files, keeping SKILL.md as a concise overview with quick-start guidance
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~400+ lines with massive amounts of speculative, non-executable content. Includes conceptual sections (GraphQL federation, Kafka config, synchronization patterns, communication strategies) that are not actionable and pad the token budget enormously. Many sections repeat the same pattern of 'npx ruv-swarm github <command> --flags' without adding real value. | 1 / 3 |
Actionability | Most commands reference 'npx ruv-swarm' which appears to be a hypothetical/non-standard tool with no installation or verification instructions. The bash scripts in sections 1-3 contain syntax errors (using '$' instead of '/' in paths like 'repos$org/$repo$contents$package.json'). The vast majority of commands are aspirational CLI invocations that cannot be verified as real, making them essentially pseudocode. | 1 / 3 |
Workflow Clarity | Despite being a complex multi-step orchestration skill involving destructive operations across multiple repositories, there are no validation checkpoints, no error recovery feedback loops, and no verification steps. The synchronized operations section creates PRs across repos without any rollback strategy or validation gates. Steps are loosely described without clear sequencing or decision points. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with 20+ sections all inline. Content that should be in separate reference files (communication strategies, synchronization patterns, configuration schemas, troubleshooting) is all dumped into the main skill file. The two references at the bottom (swarm-pr.md, project-board-sync.md) are insufficient given the massive scope. No clear quick-start section to orient the reader. | 1 / 3 |
Total | 4 / 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/claude-flow
- Commit
0d9f9b1
- 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.