Name: github-multi-repo
Rating: 56.8 (1 reviews)
Author: ruvnet

Blog Docs Log inGet started

github-multi-repo

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

2.83x

Quality

38%

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

31%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 855-line monolithic feature catalog: executable CLI snippets are diluted by pseudocode wrappers, placeholder content, hardcoded paths, and marketing-style sections that teach Claude nothing new. Its strongest asset is the set of concrete 'npx claude-flow skill run' commands, but everything else needs radical trimming and splitting into reference files.

Suggestions

Split the body into reference files (e.g. references/sync-patterns.md, references/orchestration.md, references/troubleshooting.md) and keep SKILL.md as a lean overview that links to them one level deep.

Replace pseudocode blocks (Bash(...), Task(...), mcp__claude-flow__swarm_init(...), ':owner/:repo', '[GitHub modes documentation]' placeholders) with real executable commands, and remove hardcoded '/workspaces/ruv-FANN/...' paths.

Cut sections that restate common knowledge (Best Practices, Metrics and Reporting, Communication Strategies overview prose) and consolidate the repetitive 'npx claude-flow skill run' invocations into a single subcommand table, keeping the body under ~200 lines.

Dimension	Reasoning	Score
Conciseness	The ~855-line body is severely padded: marketing fluff in the Overview ('combines swarm intelligence, package synchronization, and repository architecture optimization'), dozens of near-identical 'npx claude-flow skill run github-multi-repo <subcommand>' blocks, placeholder strings like '[GitHub modes documentation]', and sections (Metrics and Reporting, Communication Strategies, Best Practices) that mostly restate what Claude already knows. This matches anchor 1.	1 / 5
Actionability	The bash 'npx claude-flow skill run ...' blocks are executable, but a large share of the body is pseudocode: Bash(...)/Task(...)/mcp__claude-flow__swarm_init(...) wrapper notation, unfilled ':owner/:repo' literals, hardcoded '/workspaces/ruv-FANN/...' paths, and placeholder content like '[GitHub modes template]'. Some concrete guidance but incomplete, with pseudocode instead of executable code — anchor 3; not 4 because the majority of examples cannot be run as written.	3 / 5
Workflow Clarity	The document is a feature catalog rather than a sequenced workflow. Some batch operations do include validation checkpoints (e.g. 'if npm test' gates PR creation and failures comment on the tracking issue), so it avoids the anchor-2 'validation absent' level, but the main flows (init, sync, optimize) have no defined step sequence, error-recovery loops, or checklists — anchor 3 (sequence present but checkpoints missing or implicit in the primary workflows).	3 / 5
Progressive Disclosure	A monolithic single file with no bundle: content that clearly belongs in separate reference files (config schemas, sync patterns, metrics, troubleshooting, examples) is inlined across 850+ lines, and the only cited resource '.claude/examples/github-multi-repo/' does not exist in the bundle. Matches anchor 2 (minimal structure; content that clearly belongs in separate files is inlined); not 3 because there are no actual reference files to point to at all.	2 / 5
	Total	9 / 20 Passed

Description

45%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 clear domain but relies on generic action nouns and buzzwords without a single concrete capability or any 'when to use' guidance. It would benefit most from an explicit trigger clause and specific operations like 'align package versions across repos' or 'create coordinated pull requests'.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. 'Use when managing changes across multiple GitHub repositories, aligning package versions, or coordinating cross-repo pull requests.'

Replace generic nouns with concrete actions: 'Align package versions across repos, synchronize documentation, and open coordinated pull requests' instead of 'coordination, synchronization, and architecture management'.

Include natural trigger variations users would say — 'multi-repo', 'cross-repo', 'monorepo', 'repo sync' — and drop the buzzword 'AI swarm orchestration'.

Dimension	Reasoning	Score
Specificity	The description names the domain ('multi-repository') but its actions are generic noun phrases — 'coordination, synchronization, and architecture management' — with no concrete operations, plus the buzzword 'AI swarm orchestration'. This matches anchor 2 (names the domain but actions minimal or generic) rather than 3, which requires 1-2 genuinely concrete actions.	2 / 5
Completeness	A 'what' is stated (multi-repo coordination, synchronization, architecture management) but there is no 'Use when...' clause or any trigger guidance, which per the judging guidelines caps completeness at 3. Not 2 because the 'what' is not vague; not 4 because 'when' is entirely absent.	3 / 5
Trigger Term Quality	It includes relevant keywords like 'multi-repository', 'synchronization', and 'architecture', but misses natural variations users would actually say such as 'monorepo', 'cross-repo', 'repo sync', or 'package version alignment'. Some relevant keywords but missing common variations — anchor 3.	3 / 5
Distinctiveness Conflict Risk	'Multi-repository' carves a niche, but the generic 'coordination' and 'architecture management' wording overlaps with sibling skills (the body itself lists github-workflow, github-pr, sparc-architect as related). Somewhat specific but could overlap with similar skills — anchor 3.	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: 4b59352

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.