CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-multi-repo-swarm

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

36

4.34x
Quality

6%

Does it follow best practices?

Impact

87%

4.34x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

12%Scale 1-3

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

This skill is an extremely verbose, largely non-actionable feature catalog for a hypothetical 'ruv-swarm' tool. Most code examples contain path syntax errors and reference non-existent CLI commands, making them non-executable. The document would benefit enormously from being reduced to a focused, tested workflow with actual working commands, splitting advanced topics into separate referenced files.

Suggestions

Replace hypothetical 'npx ruv-swarm github' commands with actual executable workflows using the MCP tools listed in the frontmatter (mcp__claude-flow__swarm_init, etc.) and gh CLI commands that actually work.

Fix all path syntax errors (e.g., 'repos$org/$repo' should be 'repos/org/repo', '$dev$null' should be '/dev/null') and verify scripts are executable.

Reduce the document to under 150 lines covering core workflows, and move communication strategies, synchronization patterns, advanced features, and troubleshooting into separate referenced files.

Add explicit validation checkpoints to the main workflows (e.g., verify PR creation succeeded, confirm test results before proceeding, validate repository access before batch operations).

DimensionReasoningScore

Conciseness

Extremely verbose at ~400+ lines with massive amounts of speculative, non-executable content. Includes conceptual sections (GraphQL federation, Kafka config, Raft consensus, synchronization patterns) that are architectural abstractions rather than actionable instructions. Many sections repeat the same pattern of 'npx ruv-swarm github <command> --flags' without adding real value. The skill explains concepts Claude already knows (what eventual consistency is, what circuit breakers are) and includes best practices that are generic software engineering advice.

1 / 3

Actionability

The vast majority of commands reference 'npx ruv-swarm' which appears to be a hypothetical/non-standard tool with no installation or verification instructions. Most code blocks are not executable - they're aspirational CLI invocations with invented flags. The bash scripts in sections 1-3 contain syntax errors (using '$' instead of '/' in paths like 'repos$org/$repo$contents$package.json') making them non-functional. The JavaScript, GraphQL, and YAML configuration examples are illustrative rather than executable.

1 / 3

Workflow Clarity

Some workflows like 'Synchronized Operations' and 'Dependency Management' have reasonable step sequences (clone, modify, test, create PR, report failures). However, there are no explicit validation checkpoints, no error recovery loops beyond basic test failure reporting, and the overall document lacks a clear workflow for when/how to use this skill. The relationship between the many sections is unclear - it reads more like a feature catalog than a guided workflow.

2 / 3

Progressive Disclosure

Monolithic wall of text with no content split into supporting files despite the massive length. References to 'swarm-pr.md' and 'project-board-sync.md' at the bottom, but no bundle files are provided. The document dumps everything inline - configuration examples, communication strategies, synchronization patterns, troubleshooting, use cases - all in one enormous file that would be far better organized across multiple referenced documents.

1 / 3

Total

5

/

12

Passed

Description

0%Scale 1-3

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

This is an extremely weak description that fails on all dimensions. It provides no information about what the skill does, when it should be used, or what triggers should activate it. It reads more like an internal label than a functional description.

Suggestions

Describe the concrete actions this skill performs (e.g., 'Coordinates changes across multiple repositories, synchronizes dependencies, runs cross-repo tests').

Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user needs to make coordinated changes across multiple repositories, manage cross-repo dependencies, or perform bulk operations across codebases').

Replace the invocation instruction ('invoke with $agent-multi-repo-swarm') with functional context — the description should help Claude decide *when* to use the skill, not just *how* to invoke it.

DimensionReasoningScore

Specificity

The description provides no concrete actions whatsoever. 'Agent skill for multi-repo-swarm' is entirely abstract with no indication of what the skill actually does.

1 / 3

Completeness

Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states it's an 'agent skill' and how to invoke it, providing no functional or contextual information.

1 / 3

Trigger Term Quality

The only potentially relevant term is 'multi-repo-swarm', which is a technical/internal name rather than a natural keyword a user would say. There are no natural trigger terms like 'multiple repositories', 'cross-repo', etc.

1 / 3

Distinctiveness Conflict Risk

The description is so vague that it's impossible to distinguish it from any other agent or multi-repo skill. 'Agent skill' is extremely generic and provides no clear niche.

1 / 3

Total

4

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (558 lines); consider splitting into references/ and linking

Warning

Total

10

/

11

Passed

Repository
ruvnet/claude-flow
Reviewed

Table of Contents

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.