agent-multi-repo-swarm

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

4.34x

Quality

—

Does it follow best practices?

Impact

87%

4.34x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

50%

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 catalogue of swarm subcommands, but it is over-long for a SKILL.md overview, its code blocks are non-executable due to '$'-for-'/' corruption, and its only external references are dead links to non-existent files. It provides concrete guidance but falls short on executable actionability and progressive disclosure.

Suggestions

Fix the corrupted path separators ($ -> /) throughout so the bash examples are actually executable and copy-paste ready.

Slim the SKILL.md to a lean overview and move the exhaustive subcommand catalogue (Use Cases, Advanced Features, Performance, Troubleshooting) into reference files under references/, then link to them one level deep.

Add explicit validation/verification checkpoints to the batch PR-creation workflows (e.g., verify the PR was created, confirm linked-PRs succeeded, fail-fast on clone/push errors) rather than implicit sequencing.

Dimension	Reasoning	Score
Conciseness	Individual blocks are terse and avoid explaining concepts Claude knows, but the body is a ~518-line catalogue of near-duplicate 'npx ruv-swarm github <subcmd> --flag' listings across 15+ sections that could be trimmed substantially.	2 / 3
Actionability	Commands and flags look concrete, but path separators are corrupted to '$' (e.g., 'repos$org/$repo', '.swarm$multi-repo.yml', 'redis:/$shared-memory', '$tmp/$repo'), so the code is not executable or copy-paste ready as written.	2 / 3
Workflow Clarity	Sequenced steps exist (clone, task-execute, status check, branch, commit, push, PR) and the dependency section gates on 'npm test', but most batch/PR-creation workflows lack explicit validation checkpoints, capping clarity at 2.	2 / 3
Progressive Disclosure	Clear section headers give some structure, but the body is a monolithic wall that should be split, and the two 'See also' references (swarm-pr.md, project-board-sync.md) point to files that do not exist in any bundle directory.	2 / 3
	Total	8 / 12 Passed

Description

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 is meta-boilerplate that tells Claude how to invoke the skill rather than what it does or when to use it. It lacks concrete capabilities, natural trigger terms, and any 'use when' guidance, capping completeness at the floor.

Suggestions

Replace the meta invocation hint with concrete actions the skill performs (e.g., 'Coordinate AI swarms across multiple repositories: discover repos, run synchronized tasks, and open linked PRs').

Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., cross-repo updates, org-wide dependency bumps, multi-repo refactors).

Drop the '$agent-multi-repo-swarm' command token from the description; trigger guidance belongs in natural language, not invocation syntax.

Dimension	Reasoning	Score
Specificity	The description ('Agent skill for multi-repo-swarm - invoke with $agent-multi-repo-swarm') names no concrete actions, only a meta invocation hint, matching the vague/abstract anchor.	1 / 3
Completeness	It answers neither what the skill does nor when to use it — there is no action description and no 'Use when...' clause, so both what and when are missing.	1 / 3
Trigger Term Quality	The only terms are 'multi-repo-swarm' and the command token '$agent-multi-repo-swarm'; a user would not naturally say these, so it is technical jargon with no natural keywords.	1 / 3
Distinctiveness Conflict Risk	'multi-repo-swarm' denotes a specific niche, but the description is otherwise generic meta-boilerplate, so it is somewhat specific yet could still overlap with related orchestration skills.	2 / 3
	Total	5 / 12 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/claude-flow
Commit: 03d4f84

Reviewed: 2 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.