Name: agent-multi-repo-swarm
Rating: 54.2 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-multi-repo-swarm

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

4.34x

Quality

35%

Does it follow best practices?

Impact

87%

4.34x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-multi-repo-swarm/SKILL.md

The canonical home for this skill is agent-multi-repo-swarm in ruvnet/claude-flow

Quality

Content

50%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 a broad, well-sectioned catalog of multi-repo swarm operations, but pervasive '$'-for-'/' corruption makes the code non-executable and the referenced companion files do not exist. Batch workflows also lack the validation checkpoints the rubric requires for destructive operations.

Suggestions

Fix the corrupted forward slashes throughout the code blocks (e.g. 'repos$org/$repo' -> 'repos/org/$repo', '$dev$null' -> '/dev/null', 'redis:/$shared-memory' -> 'redis://shared-memory') so examples are copy-paste executable.

Add explicit validation/feedback checkpoints to the batch workflows (e.g. verify the clone and test pass before committing; confirm the PR was created before linking; report a per-repo success/failure summary).

Either create the referenced swarm-pr.md and project-board-sync.md files under references/ with correct relative paths, or remove the dangling 'See also' links; consider moving the config and GraphQL/Kafka blocks into a separate reference file.

Dimension	Reasoning	Score
Conciseness	The body is mostly code rather than concept re-explanation, but it is a ~500-line catalog of near-duplicate 'npx ruv-swarm github <subcommand> --flag --flag' sections that could be tightened considerably.	3 / 5
Actionability	Concrete commands are present throughout, but forward slashes are corrupted to '$' (e.g. 'repos$org/$repo$contents$package.json', 'cd $tmp/$repo', '$dev$null'), so the examples are not executable as written.	3 / 5
Workflow Clarity	Batch/destructive operations (cloning many repos, pushing and opening PRs in a loop) lack explicit validation checkpoints, so per the batch-operation cap workflow clarity cannot exceed 3; the dependency section's 'if npm test' guard is the only partial checkpoint.	3 / 5
Progressive Disclosure	Section headers give the document structure, but it is a monolithic single file with config/API material inlined, and its only references ('.$swarm-pr.md', '.$project-board-sync.md') are broken paths to non-existent files.	3 / 5
	Total	12 / 20 Passed

Description

20%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 frontmatter description is a low-quality placeholder: it states only that this is an agent skill for a jargon-named domain and how to invoke it, without describing any concrete capability or when to use it. It would rarely trigger naturally and tells Claude almost nothing actionable.

Suggestions

Rewrite the description in third person to list concrete actions (e.g., 'Coordinate AI swarms across multiple GitHub repositories: discover related repos, run synchronized updates, and open linked PRs').

Add an explicit 'Use when...' trigger clause with natural phrases users would actually say (e.g., 'Use when coordinating changes across multiple repositories or orchestrating org-wide dependency/refactor updates').

Drop the 'invoke with $agent-multi-repo-swarm' invocation syntax from the description; that belongs in usage docs, not the trigger text.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for multi-repo-swarm - invoke with $agent-multi-repo-swarm' names the domain but lists zero concrete actions, and the imperative 'invoke with' is second-person voice, costing the specificity score a point per the voice penalty.	1 / 5
Completeness	It offers only a vague 'what' ('agent skill for multi-repo-swarm') and no 'when' / 'Use when...' trigger guidance, matching the anchor for a vague what with no when.	2 / 5
Trigger Term Quality	'multi-repo-swarm' and '$agent-multi-repo-swarm' are internal jargon/invocation syntax, not natural phrases a user would say when they need this skill.	1 / 5
Distinctiveness Conflict Risk	'multi-repo-swarm' is a fairly distinct niche term with minor overlap risk against closely related coordination skills, even though the surrounding phrasing is generic.	4 / 5
	Total	8 / 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 (558 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: ruvnet/ruflo
Path: .agents/skills/agent-multi-repo-swarm/SKILL.md
Commit: fa13ee4

Reviewed: about 8 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.