agent-multi-repo-swarm

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

4.34x

Quality

50%

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

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 content is code-rich and broadly organized, but it is overlong with repetitive CLI blocks, contains corrupted path syntax that makes examples non-executable, and lacks validation feedback loops for its batch/destructive workflows. Referenced files are missing and broken.

Suggestions

Fix the corrupted path separators throughout the code blocks (e.g. `repos$org/$repo` -> `repos/org/$repo`, `$tmp$created-prs.txt` -> `$tmp/created-prs.txt`) so examples are copy-paste executable.

Add explicit validation/retry checkpoints to the batch workflows, e.g. verify tests pass before pushing, check the push succeeded, and report or rollback on PR creation failure.

Trim the repetitive `npx ruv-swarm github ...` flag-list blocks (Monitoring, Performance, Troubleshooting, Use Cases) or move detailed command catalogs into reference files, keeping SKILL.md a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is largely code rather than concept-padding, but it runs ~510 lines with many near-duplicate `npx ruv-swarm github <cmd> --flag` blocks across Communication, Monitoring, Use Cases, Performance, and Troubleshooting sections that could be tightened or consolidated.	2 / 3
Actionability	Concrete gh CLI and ruv-swarm commands are provided throughout, but the code is not copy-paste executable as written because path separators are corrupted (e.g. `repos$org/$repo`, `gh api repos$my-organization/$repo$contents$package.json`, `$tmp$created-prs.txt`).	2 / 3
Workflow Clarity	Batch operations (clone, edit, commit, push, create PR across many repos) are clearly sequenced, but they lack explicit validation checkpoints and retry/rollback feedback loops, which caps workflow clarity at 2 for destructive batch operations.	2 / 3
Progressive Disclosure	The skill has section structure, but it is a monolithic inline wall of config, JS, GraphQL, and YAML content; the referenced files (swarm-pr.md, project-board-sync.md) do not exist and their links are broken (.$swarm-pr.md).	2 / 3
	Total	8 / 12 Passed

Description

50%

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 identifies a clear domain but relies on abstract buzzwords and omits any explicit use-when trigger guidance. It is serviceable but vague, lacking the concrete actions and natural trigger terms that would make it distinctive and reliably invoked.

Suggestions

Replace abstract phrasing ("intelligent collaboration", "automation") with concrete actions users would recognize, e.g. "Synchronize dependencies, run coordinated refactors, and open cross-repository PRs across an organization's repositories."

Add an explicit trigger clause such as "Use when coordinating changes, dependency updates, or refactors across multiple repositories in a GitHub organization."

Include natural keywords users actually say (multi-repo, cross-repo PRs, organization-wide updates) instead of jargon like "swarm orchestration".

Dimension	Reasoning	Score
Specificity	Names the domain ("Cross-repository swarm orchestration") and a couple of activities ("organization-wide automation"), but leans on abstract buzzwords ("intelligent collaboration") rather than listing multiple concrete actions like synchronizing dependencies or creating cross-repo PRs.	2 / 3
Completeness	It states what the skill does but provides no "Use when..." or equivalent trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	"Cross-repository" and "automation" have some natural relevance, but "swarm orchestration" is technical jargon a user would rarely say, and common phrasings (multi-repo updates, cross-repo PRs) are missing.	2 / 3
Distinctiveness Conflict Risk	The cross-repository scope is a real niche, but generic terms like "automation" and "collaboration" could overlap with broader coordination/orchestration skills and there are no distinct triggers to disambiguate.	2 / 3
	Total	8 / 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
Path: .agents/skills/agent-multi-repo-swarm/SKILL.md
Commit: 26c35b5

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.