agent-mesh-coordinator

Agent skill for mesh-coordinator - invoke with $agent-mesh-coordinator

2.60x

Quality

—

Does it follow best practices?

Impact

99%

2.60x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

27%

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 exhaustive reference dump of mesh-networking theory and illustrative code rather than a lean, task-oriented skill; it is padded with concepts Claude already knows and provides no progressive disclosure or validation-gated workflow. Its main redeeming quality is the concrete MCP tool commands and protocol code examples, which lift actionability above the floor.

Suggestions

Trim or move general theory (gossip, pBFT, Raft, DHT explanations) into a separate reference file, keeping SKILL.md as a lean overview that assumes Claude's competence and links out for detail.

Add a concrete, sequenced task workflow with explicit validation checkpoints (e.g. init mesh -> verify peer connectivity -> run consensus -> validate quorum -> graceful shutdown) rather than parallel topical sections.

Replace illustrative protocol scaffolding with minimal runnable examples or specific commands Claude can execute directly, and add one-level-deep references (e.g. CONSENSUS.md, TOPOLOGY.md) so the overview stays short.

Dimension	Reasoning	Score
Conciseness	The ~360-line body extensively explains general distributed-systems concepts Claude already knows (pBFT phases, Raft leader election, gossip algorithms, DHT routing) and even repeats consensus material across two sections, matching the verbose/padded-with-unnecessary-context anchor rather than the mostly-efficient level 2.	1 / 3
Actionability	It provides concrete elements — executable-looking Python protocol classes and specific mcp__claude-flow__ bash commands — but the Python is illustrative scaffolding rather than copy-paste-runnable end-to-end, leaving it at 'some concrete guidance but incomplete' rather than fully executable level 3.	2 / 3
Workflow Clarity	Content is organized into topical sections with loose checklists (Best Practices), giving an implicit sequence, but there is no explicit multi-step task workflow with validation checkpoints or feedback loops for risky operations, which per the guidelines caps workflow clarity at 2.	2 / 3
Progressive Disclosure	It is a monolithic single-file wall of reference text with no bundle files and no signaled one-level-deep references (no 'See X.md' pointers), so all detail lives inline and there is no overview-to-detail split.	1 / 3
	Total	6 / 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 frontmatter description is low-quality boilerplate: it only labels the skill and tells how to invoke it, without stating concrete capabilities or when to use it. It fails every dimension because it conveys no actionable or distinctive information.

Suggestions

Replace the description with a third-person statement of concrete actions, e.g. 'Coordinates a peer-to-peer mesh network of agents, distributing tasks via work-stealing and auction protocols and reaching consensus with pBFT/Raft.'

Add an explicit 'Use when...' trigger clause naming natural terms users would say, such as 'Use when coordinating many autonomous agents, building a fault-tolerant swarm, or distributing work across a peer mesh.'

Remove the generic 'Agent skill for ... - invoke with $...' framing, which adds no signal and does not help Claude decide when to trigger this skill.

Dimension	Reasoning	Score
Specificity	The description is 'Agent skill for mesh-coordinator - invoke with $agent-mesh-coordinator' which names only the skill and its invocation syntax, with no concrete actions or domain verbs, matching the vague/abstract anchor rather than the 'names some actions' level 2.	1 / 3
Completeness	It answers neither 'what does this do' (no capability statement) nor 'when should Claude use it' (no 'Use when...' clause), and the judging guidelines note a missing trigger clause caps completeness at 2 at most — here even the 'what' is absent, so it falls to level 1.	1 / 3
Trigger Term Quality	It contains no natural keywords a user would spontaneously say; 'mesh-coordinator' is a technical label, and the phrase is jargon/generic boilerplate rather than coverage of natural trigger terms.	1 / 3
Distinctiveness Conflict Risk	The text is generic boilerplate that could prefix almost any skill and offers no niche-specific triggers, so it would not reliably distinguish this skill from others.	1 / 3
	Total	4 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.