agent-consensus-coordinator
Agent skill for consensus-coordinator - invoke with $agent-consensus-coordinator
40
7%
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 names the skill and its invocation command without describing any capabilities, use cases, or trigger conditions. It fails on every dimension of the rubric.
Suggestions
Describe what the consensus-coordinator actually does with specific concrete actions (e.g., 'Coordinates multi-agent consensus by collecting responses, identifying agreements and conflicts, and synthesizing final decisions').
Add an explicit 'Use when...' clause with natural trigger terms that describe scenarios where this skill should be selected (e.g., 'Use when multiple agents need to reach agreement, resolve conflicting outputs, or coordinate decisions').
Remove the invocation syntax ('invoke with $agent-consensus-coordinator') from the description and replace it with domain-specific keywords that help distinguish this skill from other coordination or agent-related skills.
| 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 | 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 keyword is 'consensus-coordinator', which is a technical/internal name, not 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 other skills. Without knowing what 'consensus-coordinator' does, it could overlap with anything involving coordination, collaboration, or decision-making. | 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 is excessively verbose, filled with conceptual descriptions that Claude already knows (BFT, CAP theorem, sharding, PoS), and provides mostly non-executable pseudocode with undefined helper methods. The numerous bullet-point sections describing fault tolerance mechanisms, performance optimization, and integration patterns add no actionable guidance. The blockchain neural_train example appears completely unrelated to consensus protocols.
Suggestions
Remove all descriptive bullet-point sections (Advanced Consensus Algorithms, Performance Optimization, Fault Tolerance Mechanisms, Integration Patterns) that explain concepts Claude already knows, and replace with only the specific non-obvious configuration or implementation details unique to this system.
Make code examples executable by providing complete implementations of helper methods (buildConsensusMatrix, extractAgreement, etc.) or replace with realistic, copy-paste-ready examples that actually work with the MCP tools.
Add explicit validation checkpoints and error recovery steps to workflows, e.g., 'Verify consensus was reached by checking convergenceTime < maxIterations; if not, increase epsilon or switch method.'
Split detailed usage scenarios into separate reference files and keep SKILL.md as a concise overview with clear navigation links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~300+ lines. Massive amounts of bullet-point lists that describe concepts Claude already knows (Byzantine fault tolerance, CAP theorem, sharding, etc.). Many sections are purely descriptive with no actionable content, and the blockchain neural_train example is completely irrelevant to consensus. | 1 / 3 |
Actionability | Contains some concrete code examples with MCP tool calls (solve, pageRank, analyzeMatrix), but the code is pseudocode-like with undefined helper methods (buildConsensusMatrix, extractAgreement, calculateReliability, etc.) making it non-executable. The Flow Nexus integration code references non-existent modules. | 2 / 3 |
Workflow Clarity | The 'Example Workflows' section lists high-level steps like 'Deploy consensus infrastructure' and 'Monitor consensus performance' with zero concrete commands or validation checkpoints. No feedback loops or error recovery steps are defined for any of the multi-step processes, which involve complex distributed operations. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inlined regardless of depth or relevance. Sections like 'Advanced Consensus Algorithms', 'Performance Optimization', 'Fault Tolerance Mechanisms', and 'Integration Patterns' are purely descriptive bullet lists that add no actionable value and should either be removed or split into separate reference files. | 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/ruflo
- Commit
398f7c2
- 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.