agent-quorum-manager
Agent skill for quorum-manager - invoke with $agent-quorum-manager
39
6%
Does it follow best practices?
Impact
100%
2.32xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-quorum-manager/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 description is essentially a label with an invocation command, providing no information about what the skill does, what actions it performs, or when it should be used. It fails on all dimensions because it lacks any concrete capabilities, trigger terms, or usage guidance. Claude would have no basis for selecting this skill from a list of available skills.
Suggestions
Describe what 'quorum-manager' actually does with specific concrete actions (e.g., 'Manages distributed system quorum configurations, monitors node health, and handles consensus voting').
Add an explicit 'Use when...' clause with natural trigger terms that users would say when they need this skill (e.g., 'Use when the user needs to configure quorum settings, check cluster consensus, or manage node membership').
Remove the invocation instruction ('invoke with $agent-quorum-manager') from the description and replace it with functional information that helps Claude decide when to select this skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Agent skill for quorum-manager' is entirely vague and does not describe 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 'quorum-manager', which is a technical/internal name rather than a natural term a user would say. There are no natural language trigger terms. | 1 / 3 |
Distinctiveness Conflict Risk | While 'quorum-manager' is a unique name, the description is so vague that Claude cannot determine when to select it versus any other skill. Without knowing what it does, conflict risk is high due to ambiguity. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
12%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an extremely verbose, non-executable architectural sketch of a quorum management system. It contains hundreds of lines of JavaScript that depend entirely on undefined classes and methods, making it neither actionable nor token-efficient. The content reads more like a design document or wishful API surface than a practical skill that Claude could use to perform tasks.
Suggestions
Reduce to a concise overview (under 100 lines) with the core quorum calculation formula (e.g., Byzantine: >2n/3+1, crash: >n/2+1) and a single executable example showing how to invoke quorum adjustment.
Replace the speculative class hierarchies with concrete, executable code or specific MCP tool invocations that Claude can actually run.
Extract the three strategy implementations into separate referenced files (e.g., NETWORK_STRATEGY.md, PERFORMANCE_STRATEGY.md) and keep SKILL.md as a navigation hub with a quick-start section.
Add explicit validation checkpoints with concrete commands/checks rather than calls to undefined verification methods.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~600+ lines of code. The vast majority is speculative class implementations with placeholder methods that don't contain real logic (e.g., methods that just call other undefined methods). Claude already understands distributed consensus concepts; this explains them at length without adding actionable value. | 1 / 3 |
Actionability | Despite the massive amount of code, none of it is executable. Every class depends on undefined classes (NetworkAnalyzer, PartitionPredictor, FaultAnalyzer, etc.), and methods like `getNodeCPUCapacity`, `getNodeBandwidth` are never implemented. This is architectural pseudocode dressed up as real code—it cannot be copy-pasted or run. | 1 / 3 |
Workflow Clarity | The adjustQuorum method does show a clear multi-phase sequence (prepare → execute membership changes → update weights → reconfigure → verify) with rollback on failure, which demonstrates some workflow thinking. However, there are no concrete validation checkpoints with actual commands, and the verification steps are just calls to undefined methods. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of code with no references to external files and no clear navigation structure. All strategies are inlined in full, making the document extremely long. There's no quick-start section or overview that points to detailed materials elsewhere. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (828 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- ruvnet/ruflo
- Commit
3d8f171
- 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.