CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-quorum-manager

Agent skill for quorum-manager - invoke with $agent-quorum-manager

65

2.32x
Quality

Does it follow best practices?

Impact

100%

2.32x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

47%

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 massive, verbose JavaScript scaffold for a quorum manager: it shows a well-validated adjustQuorum workflow but is not executable due to pervasive undefined dependencies and is a monolithic wall of code with no progressive disclosure. Conciseness and actionability are the weakest dimensions.

Suggestions

Cut the inline concept explanations and collapse the three near-identical strategy classes into a concise overview plus one representative example, dropping tokens that restate distributed-systems fundamentals Claude already knows.

Either define the referenced helpers (NetworkAnalyzer, mcpTools, MembershipTracker, etc.) or clearly mark the code as an illustrative scaffold with stubs, so it is honest about what is and is not executable.

Move the strategy implementations and MCP integration into separate reference files (e.g. strategies.md, mcp-integration.md) linked from a lean overview, turning the monolithic file into one-level-deep progressive disclosure.

DimensionReasoningScore

Conciseness

The body is an ~800-line code dump padded with inline explanations of concepts Claude already knows (e.g. '// For Byzantine fault tolerance: need > 2/3 of total nodes'), matching the 'verbose; explains concepts Claude knows' anchor; it is far from the lean level-3 ideal.

1 / 3

Actionability

Real JavaScript syntax and method signatures are provided, but the code depends throughout on undefined infrastructure (NetworkAnalyzer, ConnectivityMatrix, MembershipTracker, this.mcpTools, etc.), so it is incomplete and not copy-paste executable — 'some concrete guidance but incomplete; missing key details' rather than fully executable.

2 / 3

Workflow Clarity

adjustQuorum sequences validate -> create plan -> execute (five commented phases) -> verify -> record, with an explicit catch -> rollbackQuorumAdjustment feedback loop for a destructive/distributed operation, matching the 'clear sequence with explicit validation steps and feedback loops for error recovery' anchor.

3 / 3

Progressive Disclosure

Section headers exist (Core Responsibilities, Technical Implementation, MCP Integration Hooks), but no bundle files (references/scripts/assets) are present and all content is inlined in one ~800-line monolithic file; content that should be split (the three strategy classes, MCP integration) is inline, matching 'some structure but content that should be separate is inline'.

2 / 3

Total

8

/

12

Passed

Description

47%

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 sparse label-plus-invocation string: it identifies a distinct niche but names no concrete capabilities and provides no explicit use-when trigger. It is distinguishable from other skills yet weak on specificity and completeness.

Suggestions

Rewrite the description to list concrete actions, e.g. 'Calculates optimal quorum sizes, adjusts membership, and assigns weighted voting for distributed consensus protocols', instead of 'Agent skill for quorum-manager'.

Add an explicit trigger clause such as 'Use when managing quorum, membership, or weighted voting in distributed consensus / Raft / Byzantine systems'.

Replace the technical '$agent-quorum-manager' invocation jargon with natural terms a user would actually say (quorum, consensus, voting weight, node membership).

DimensionReasoningScore

Specificity

The description is "Agent skill for quorum-manager - invoke with $agent-quorum-manager", which names only the domain and an invocation hint with no concrete actions described, matching the 'vague or no actions' anchor; it does not reach level 2 because no specific actions are ever named.

1 / 3

Completeness

It gestures at a 'what' via the domain label and gives an invocation cue, but there is no explicit "Use when..." trigger guidance, so per the rubric completeness is capped at 2; it is not 1 because a domain/what signal is present.

2 / 3

Trigger Term Quality

"quorum-manager" is a relevant domain term, but the remainder ("invoke with $agent-quorum-manager") is technical invocation jargon rather than natural language a user would say, and common natural variations are missing — closer to 'some relevant keywords but missing common variations' than to full coverage.

2 / 3

Distinctiveness Conflict Risk

"quorum-manager" denotes a clear niche (distributed consensus quorum adjustment) with a distinct invocation token, making it unlikely to trigger for the wrong skill, matching the 'clear niche with distinct triggers' anchor.

3 / 3

Total

8

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (828 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
ruvnet/claude-flow
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.