CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-mesh-coordinator

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

56

2.60x
Quality

32%

Does it follow best practices?

Impact

99%

2.60x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-mesh-coordinator/SKILL.md

The canonical home for this skill is agent-mesh-coordinator in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

Quality

Content

36%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 thorough but verbose reference of mesh-coordination concepts and skeletons: it teaches algorithms Claude already knows, relies on non-executable Python pseudocode, lacks a sequenced workflow with validation checkpoints, and keeps all detail inline with no reference files. It reads more like a textbook chapter than an actionable skill.

Suggestions

Cut or move the explanatory background on gossip/pBFT/Raft/DHT to a reference file and keep only the mesh-specific coordination guidance Claude would not already know.

Replace Python class skeletons with executable, copy-paste-ready MCP command sequences or minimal complete scripts, or explicitly justify the pseudocode.

Add an explicit step-by-step task workflow with validation checkpoints (e.g., verify swarm status, confirm consensus quorum, validate task assignment before execution) for the destructive/batch coordination operations.

DimensionReasoningScore

Conciseness

The ~360-line body extensively explains well-known distributed-systems concepts Claude already knows (gossip algorithms, pBFT, Raft, DHT, work stealing), which is noticeably verbose and padded rather than lean.

2 / 5

Actionability

The MCP bash commands are concrete, but the Python examples (WorkStealingProtocol, TaskDistributionDHT, etc.) are skeletons calling undefined methods, i.e. pseudocode with missing key details rather than executable code.

3 / 5

Workflow Clarity

The body is a catalog of strategies rather than a sequenced workflow; the pre/post hooks give only a rough init→coordinate→shutdown sequence with no validation checkpoints for risky operations like task migration or network shutdown.

2 / 5

Progressive Disclosure

Section headers provide reasonable structure, but no bundle files exist and all detailed material (algorithm catalogs, full code skeletons, metric lists) is inlined in one monolithic file rather than split into one-level-deep references.

3 / 5

Total

10

/

20

Passed

Description

28%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 description is a boilerplate auto-generated line ('Agent skill for mesh-coordinator - invoke with $agent-mesh-coordinator') that names the domain but specifies no concrete capabilities, no natural user trigger phrases, and no 'use when' guidance. It is barely distinguishable from other coordinator skills.

Suggestions

Rewrite the description to state concrete actions (e.g., 'Coordinates a peer-to-peer mesh network of agents, distributes tasks via work-stealing or auctions, and builds consensus on decisions').

Add an explicit 'Use when...' clause with natural trigger phrases users would actually say (e.g., 'Use when distributing work across many agents, needing fault-tolerant consensus, or coordinating a decentralized swarm').

Drop the 'invoke with $...' invocation syntax from the description; it is not a capability or trigger and adds no signal for when to use the skill.

DimensionReasoningScore

Specificity

The phrase 'Agent skill for mesh-coordinator' names a specific domain but lists zero concrete actions, fitting the 'names the domain but actions are minimal or generic' anchor rather than the entirely-vague anchor below it.

2 / 5

Completeness

It offers only a vague 'what' (an agent skill for mesh-coordination, no actions) and no 'when/use when' guidance at all, matching the 'vague what and no when' anchor; a missing trigger clause also caps completeness at 3 per the guidelines.

2 / 5

Trigger Term Quality

'mesh-coordinator' is jargon and 'invoke with $agent-mesh-coordinator' is invocation syntax, not a natural phrase a user would say; only one or two generic keywords are present, missing the natural trigger terms.

2 / 5

Distinctiveness Conflict Risk

'mesh-coordinator' points at a fairly specific niche, but the description is so generic ('Agent skill for X') that it could still overlap with related coordinator/swarm skills and provides no distinct trigger context.

3 / 5

Total

9

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/ruflo
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.