agent-multi-repo-swarm

Agent skill for multi-repo-swarm - invoke with $agent-multi-repo-swarm

4.34x

Quality

10%

Does it follow best practices?

Impact

87%

4.34x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-multi-repo-swarm/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 critically deficient across all dimensions. It functions as little more than a label and invocation command, providing no information about what the skill does, when to use it, or what user requests should trigger it. 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 code 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.'

Include natural keywords users would say, such as 'multiple repositories,' 'cross-repo changes,' 'monorepo,' 'dependency sync,' or 'multi-project coordination.'

Dimension	Reasoning	Score
Specificity	The description provides no concrete actions whatsoever. 'Agent skill for multi-repo-swarm' is entirely vague—it doesn't describe what the skill actually does, only that it's an 'agent skill' with a name.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. The description only provides an invocation command but no explanation of functionality or usage triggers.	1 / 3
Trigger Term Quality	The only potentially relevant term is 'multi-repo-swarm,' which is a technical/internal name rather than a natural keyword a user would say. There are no natural trigger terms like 'multiple repositories,' 'cross-repo,' 'coordinate changes,' etc.	1 / 3
Distinctiveness Conflict Risk	Without any description of what the skill does, Claude cannot distinguish it from other skills. The only distinguishing element is the invocation command name, which is not a meaningful differentiator for skill selection.	1 / 3
	Total	4 / 12 Passed

Implementation

20%

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 largely aspirational, presenting what appear to be fictional CLI commands (npx ruv-swarm github ...) as actionable instructions. The few real gh CLI examples contain syntax errors ($ instead of / in API paths). The content reads more like a product roadmap or feature wishlist than an executable skill, with extensive conceptual sections on distributed systems patterns that add no actionable value.

Suggestions

Remove all fictional 'npx ruv-swarm github' commands and replace with actual executable workflows using real tools (gh CLI, git, the MCP tools listed in the frontmatter)

Fix broken syntax in gh API calls (e.g., 'repos$org/$repo$contents$package.json' should use proper path separators)

Cut content by 70%+ — remove conceptual sections (GraphQL federation, Kafka config, Raft consensus, synchronization patterns) and focus on 2-3 concrete, tested workflows

Add explicit validation checkpoints to the batch operations (e.g., verify PR creation succeeded, validate test results before proceeding) to prevent silent failures across multiple repositories

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines with massive amounts of speculative/aspirational content. Most CLI commands (npx ruv-swarm github ...) appear to be fictional/non-existent tools presented as real. Huge sections on Kafka, GraphQL federation, Raft consensus, webhook coordinators, and synchronization patterns are conceptual padding that Claude doesn't need and likely can't execute. The skill explains many concepts Claude already knows (eventual consistency, circuit breakers, etc.).	1 / 3
Actionability	The vast majority of commands are calls to 'npx ruv-swarm github' with various subcommands that appear to be fictional/non-existent. The few real gh CLI commands in sections 1-3 and Dependency Management have broken syntax (using $ instead of / in paths like 'repos$org/$repo$contents$package.json'). The JavaScript, GraphQL, and YAML configuration examples are conceptual rather than executable. Almost nothing here is copy-paste ready or verifiably functional.	1 / 3
Workflow Clarity	The Dependency Management section shows a reasonable multi-step workflow (create tracking issue → find repos → update → test → create PR or report failure), which demonstrates some sequencing with a basic error path. However, most other sections are just single CLI invocations with no workflow steps. The Synchronized Operations section has a decent sequence but lacks explicit validation checkpoints. No feedback loops for the many destructive/batch operations throughout.	2 / 3
Progressive Disclosure	The content has clear section headers and some organization, and references two related files at the end (swarm-pr.md, project-board-sync.md). However, the massive amount of inline content (configuration examples, communication strategies, synchronization patterns, use cases, troubleshooting) should be split into separate reference files. The skill is a monolithic wall of content that would benefit greatly from being an overview pointing to detailed sub-documents.	2 / 3
	Total	6 / 12 Passed

Validation

90%

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 — 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: f547cec

Reviewed: 4 days 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.