Name: github-multi-repo
Rating: 58.4 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

github-multi-repo

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

2.83x

Quality

40%

Does it follow best practices?

Impact

88%

2.83x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/github-multi-repo/SKILL.md

The canonical home for this skill is github-multi-repo in ruvnet/agentic-flow

Quality

Content

38%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an oversized, padded monolith that mixes executable gh commands with non-executable pseudocode against invented APIs. Workflows show some validation but it is inconsistent across batch operations, and progressive disclosure is essentially absent with everything inlined into one file.

Suggestions

Move the patterns, API reference, and example workflows into separate reference files under references/ and link to them from a concise overview, cutting the body to a lean quick-start.

Make code examples executable as written or explicitly label pseudocode; replace invented `mcp__claude-flow__*` / `Task(...)` calls with real, verifiable commands or mark them as illustrative.

Add explicit validation/feedback checkpoints (validate -> fix -> retry) to every batch and destructive workflow, especially the security-patch and cross-repo update flows.

Dimension	Reasoning	Score
Conciseness	The body runs ~850 lines with heavily padded, repetitive sections (dozens of near-identical `npx claude-flow skill run ...` invocations and marketing-style overviews), noticeably exceeding token budget even though it avoids patronizing explanations of basic concepts.	2 / 5
Actionability	It mixes real executable gh-CLI shell commands with non-executable pseudocode using invented APIs (`mcp__claude-flow__swarm_init`, `Task(...)`, `Bash(\`...\`)`), so guidance is concrete in places but incomplete and not copy-paste ready.	3 / 5
Workflow Clarity	Sequences are present and some batch workflows include validation (`if npm test; then ... gh pr create`), but validation is inconsistent across the many destructive/batch operations, leaving checkpoints missing or implicit, which caps this at 3.	3 / 5
Progressive Disclosure	Despite section headers, the skill is a single monolithic ~850-line file with no bundle files in references/, scripts/, or assets/; content that clearly belongs in separate files (patterns, API reference, examples) is all inlined, and the one cited path (`.claude/examples/github-multi-repo/`) has no corresponding bundle.	2 / 5
	Total	10 / 20 Passed

Description

42%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description names a recognizable domain and several activities but relies on abstract, jargon-heavy language and omits any explicit 'when to use' trigger guidance. It is distinguishable enough to avoid total genericness but would benefit from concrete actions and a Use-when clause.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers such as 'synchronize versions across repos', 'coordinate changes across multiple repositories', or 'align dependencies between packages'.

Replace abstract verbs with concrete actions, e.g. 'discover related repositories, align package versions, open coordinated pull requests across repos'.

Drop the buzzword 'AI swarm orchestration' or relegate it to a secondary clause so the lead phrase uses terms a user would actually say.

Dimension	Reasoning	Score
Specificity	The phrase 'Multi-repository coordination, synchronization, and architecture management' names the domain plus several activities, but the actions are abstract rather than concrete executable operations like 'extract' or 'fill', so it sits at the named-but-not-comprehensive anchor.	3 / 5
Completeness	The 'what' is clear (multi-repo coordination, sync, architecture management) but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Terms like 'AI swarm orchestration', 'synchronization', and 'architecture management' are technical jargon; the natural phrases a user would actually say ('sync repos', 'coordinate multiple repositories') are largely missing, leaving only one or two generic keywords.	2 / 5
Distinctiveness Conflict Risk	'Multi-repository' is a fairly specific niche, but the broad activities (coordination, synchronization, architecture management) overlap with related GitHub skills such as github-workflow and github-pr, so it is somewhat specific but not yet clearly distinct.	3 / 5
	Total	11 / 20 Passed

Validation

87%

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 — 14 / 16 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	14 / 16 Passed

Repository: ruvnet/ruvector
Path: .claude/skills/github-multi-repo/SKILL.md
Commit: 74d2a60

Reviewed: 3 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.