agent-consensus-coordinator
Agent skill for consensus-coordinator - invoke with $agent-consensus-coordinator
35
0%
Does it follow best practices?
Impact
96%
7.38xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-consensus-coordinator/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an extremely weak description that provides virtually no useful information for skill selection. It only states the skill's name and invocation command without describing any capabilities, use cases, or trigger conditions. It reads more like a label than a description.
Suggestions
Add concrete actions describing what the consensus-coordinator does (e.g., 'Coordinates multi-agent consensus by collecting responses, resolving conflicts, and synthesizing agreed-upon outputs').
Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when multiple agents need to reach agreement, resolve conflicting outputs, or coordinate decisions').
Replace the invocation instruction with functional description — the invocation syntax belongs in usage documentation, not in the description used for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions whatsoever. 'Agent skill for consensus-coordinator' is entirely abstract with no indication of what the skill actually does. | 1 / 3 |
Completeness | The description fails to answer both 'what does this do' and 'when should Claude use it'. It only provides an invocation command ($agent-consensus-coordinator) with no explanation of functionality or usage triggers. | 1 / 3 |
Trigger Term Quality | The only keyword is 'consensus-coordinator', which is a technical/internal name rather than a natural term a user would say. There are no natural language trigger terms like 'coordinate', 'agreement', 'voting', or any domain-specific terms. | 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 'consensus-coordinator' does, it could overlap with collaboration, decision-making, or coordination skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is a verbose, largely non-actionable document that reads more like a marketing overview of distributed consensus concepts than a practical skill file. The code examples are non-executable pseudocode with syntactically invalid tool calls and undefined helper methods. The vast majority of content consists of bullet-point lists of concepts Claude already knows, providing no concrete, executable guidance for any task.
Suggestions
Remove all conceptual explanation sections (Performance Optimization, Fault Tolerance Mechanisms, Advanced Consensus Algorithms) that are just bullet lists of topics Claude already knows — reduce to under 100 lines of actionable content.
Provide at least one fully executable, copy-paste-ready example showing an actual MCP tool call with valid syntax and realistic input data, rather than pseudocode with undefined helper methods.
Add explicit validation checkpoints to workflows — e.g., how to verify consensus was reached, how to detect and handle failures, with concrete commands or tool calls at each step.
Fix the MCP tool call syntax (hyphens in identifiers are invalid JS) and remove the nonsensical neural_train call for blockchain consensus, which undermines credibility of the entire skill.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Includes extensive bullet-point lists of concepts Claude already knows (BFT, CAP theorem, crash fault tolerance, sharding), lengthy sections that describe rather than instruct, and many sections that are purely conceptual padding with no actionable content (e.g., 'Performance Optimization', 'Fault Tolerance Mechanisms' are just bullet lists of buzzwords). | 1 / 3 |
Actionability | The code examples are pseudocode-like and not executable — they reference undefined methods (this.buildConsensusMatrix, this.extractAgreement, etc.), use MCP tool calls with invalid JavaScript syntax (mcp__sublinear-time-solver__solve as a function name with hyphens), and require non-existent modules. The 'blockchain consensus' example nonsensically uses neural_train for consensus. None of this is copy-paste ready or practically useful. | 1 / 3 |
Workflow Clarity | The 'Example Workflows' section lists high-level steps like 'Design consensus network topology' and 'Deploy consensus infrastructure' without any concrete commands, validation checkpoints, or error recovery steps. For operations involving distributed systems and Byzantine fault tolerance, the complete absence of validation/verification steps is a critical gap. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files and no bundle files. All content is inline regardless of depth or relevance. Sections like 'Advanced Consensus Algorithms', 'Performance Optimization', and 'Fault Tolerance Mechanisms' are shallow bullet lists that add no value inline and would be better as separate references or omitted entirely. | 1 / 3 |
Total | 4 / 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
e6dc21f
- 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.