agent-mesh-coordinator
Agent skill for mesh-coordinator - invoke with $agent-mesh-coordinator
40
7%
Does it follow best practices?
Impact
99%
2.60xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-mesh-coordinator/SKILL.mdQuality
Discovery
0%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 provides virtually no useful information for skill selection. It only names the skill and its invocation command without describing any capabilities, use cases, or trigger conditions. It is essentially a placeholder rather than a functional description.
Suggestions
Add concrete actions describing what mesh-coordinator actually does (e.g., 'Orchestrates multi-agent workflows, routes tasks between agents, manages agent communication and dependencies').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when coordinating multiple agents, distributing tasks across agents, or managing parallel agent workflows').
Remove the invocation instruction ('invoke with $agent-mesh-coordinator') from the description and replace it with functional information that helps Claude decide when to select this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions whatsoever. 'Agent skill for mesh-coordinator' 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, with no functional or contextual information. | 1 / 3 |
Trigger Term Quality | The only keyword is 'mesh-coordinator', which is technical jargon unlikely to be naturally used by users. There are no natural language trigger terms that a user would say when needing this skill. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's impossible to distinguish it from any other agent skill. Without knowing what it does, there's no way to avoid conflicts with other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a distributed systems textbook chapter than an actionable skill for Claude. It extensively explains well-known concepts (pBFT, Raft, gossip protocols, DHTs, work stealing) that Claude already understands, while failing to provide a clear operational workflow for actually coordinating mesh network tasks. The MCP tool commands in the middle are the most valuable part but are buried in hundreds of lines of theoretical content.
Suggestions
Reduce content by 70%+ by removing textbook explanations of distributed systems concepts (pBFT, Raft, gossip, DHTs) that Claude already knows — focus only on project-specific configuration and tool usage.
Add a clear sequential workflow: 'When you receive a task, do step 1 (initialize network), step 2 (distribute subtasks), step 3 (monitor consensus), step 4 (collect results)' with explicit validation checkpoints between steps.
Replace pseudocode Python classes with actual MCP tool command sequences that demonstrate real coordination patterns — the current classes (WorkStealingProtocol, HeartbeatMonitor, etc.) are not executable.
Extract detailed reference material (consensus algorithm details, load balancing strategies, performance metrics) into separate bundle files and reference them from a concise overview in SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350+ lines. Includes extensive theoretical explanations of well-known distributed systems concepts (Byzantine fault tolerance, Raft consensus, gossip protocols, DHTs) that Claude already knows. The Python class examples are conceptual pseudocode that explain textbook algorithms rather than providing project-specific configuration. Most content is educational rather than instructional. | 1 / 3 |
Actionability | The MCP tool integration section provides concrete bash commands that are copy-paste ready, which is valuable. However, the bulk of the content consists of pseudocode Python classes (WorkStealingProtocol, HeartbeatMonitor, PartitionHandler, etc.) that are illustrative rather than executable — they reference undefined functions and aren't tied to any real implementation. The skill describes concepts more than it instructs specific actions. | 2 / 3 |
Workflow Clarity | There is no clear sequential workflow for how to actually coordinate a mesh network task from start to finish. The content presents isolated concepts (consensus algorithms, load balancing, failure detection) without connecting them into a coherent operational sequence. No validation checkpoints or feedback loops are defined for the coordination process itself, despite this being a complex multi-step operation involving distributed agents. | 1 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to external files and no bundle files to support it. All content — from network architecture theory to consensus algorithms to load balancing strategies — is inlined in a single massive document. There's no separation of quick-start essentials from advanced reference material. | 1 / 3 |
Total | 5 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- ruvnet/claude-flow
- Commit
d29d87f
- 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.