github-multi-repo

Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration

2.83x

Quality

22%

Does it follow best practices?

Impact

88%

2.83x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/github-multi-repo/SKILL.md

Quality

Discovery

17%

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 suffers from abstract, buzzword-heavy language ('AI swarm orchestration') without concrete actions or explicit trigger guidance. While it identifies a domain (multi-repository work), it fails to explain what specific tasks it performs or when Claude should use it, making skill selection unreliable.

Suggestions

Add a 'Use when...' clause with explicit triggers like 'Use when coordinating changes across multiple repositories, syncing dependencies between repos, or managing cross-repo pull requests'

Replace abstract terms with concrete actions: instead of 'coordination and synchronization', specify 'propagate changes across repos, align version numbers, coordinate cross-repo merges'

Include natural user keywords: 'multiple repos', 'cross-repository', 'monorepo migration', 'repo sync', 'multi-project'

Dimension	Reasoning	Score
Specificity	Names the domain (multi-repository) and mentions some actions (coordination, synchronization, architecture management), but these are fairly abstract. 'AI swarm orchestration' is vague and doesn't describe concrete actions like 'merge branches' or 'sync dependencies'.	2 / 3
Completeness	Only addresses 'what' at a high level with no 'Use when...' clause or explicit trigger guidance. Users cannot determine when Claude should select this skill over others.	1 / 3
Trigger Term Quality	Uses technical jargon ('AI swarm orchestration', 'architecture management') that users are unlikely to naturally say. Missing common terms users would use like 'monorepo', 'multiple repos', 'cross-repo', 'sync repos', or 'coordinate repositories'.	1 / 3
Distinctiveness Conflict Risk	'Multi-repository' provides some specificity, but 'coordination', 'synchronization', and 'architecture management' are broad terms that could overlap with general git skills, CI/CD skills, or project management skills.	2 / 3
	Total	6 / 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 attempts to be comprehensive but suffers from severe verbosity and poor organization. While it provides many code examples, they are often not directly executable and lack validation steps for risky multi-repo operations. The content would benefit significantly from being split into focused sub-documents with a lean overview pointing to detailed references.

Suggestions

Reduce content by 70%+ by moving configuration examples, architecture patterns, troubleshooting, and advanced features to separate referenced files (e.g., CONFIG.md, ARCHITECTURE.md, TROUBLESHOOTING.md)

Make code examples executable by providing complete context - either use real gh CLI commands or clearly document the custom DSL (Task, Read, LS, mcp__* functions) in a referenced file

Add explicit validation checkpoints to multi-repo workflows: after cloning verify repo state, after changes run validation, include rollback procedures for batch operations

Remove redundant examples - the skill shows the same patterns (swarm init, task spawning, PR creation) repeatedly; consolidate into one canonical example per pattern

Dimension	Reasoning	Score
Conciseness	Extremely verbose at 700+ lines with extensive repetition. Contains unnecessary explanations, redundant examples showing the same patterns multiple times, and configuration options that could be referenced externally. Many sections explain concepts Claude already knows (what webhooks are, what Kafka does, basic sync strategies).	1 / 3
Actionability	Provides concrete code examples and CLI commands, but many examples use pseudocode-like JavaScript that isn't directly executable (e.g., `Task()`, `Read()`, `LS()` without context). The `mcp__` function calls assume tooling that isn't explained. Some bash commands are executable but others reference undefined variables or incomplete contexts.	2 / 3
Workflow Clarity	Multi-step processes are listed but lack explicit validation checkpoints. For example, the 'Synchronized Operations' section shows cloning, updating, and creating PRs but doesn't include verification steps for cross-repo consistency. The 'Security Patch Deployment' workflow lacks rollback procedures for failed patches across multiple repos.	2 / 3
Progressive Disclosure	Monolithic wall of text with everything inline. No references to external files for detailed content. Configuration examples, architecture patterns, troubleshooting, and advanced features could all be separate documents. The skill tries to cover too much in a single file without clear navigation structure.	1 / 3
	Total	6 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (875 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: 462536e

Reviewed: about 17 hours 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.