CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-quorum-manager

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

56

2.32x
Quality

33%

Does it follow best practices?

Impact

100%

2.32x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-quorum-manager/SKILL.md

The canonical home for this skill is agent-quorum-manager in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

Quality

Content

38%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is an oversized implementation dump of non-executable JavaScript relying on undefined supporting classes, with no progressive disclosure into reference files. Validation/rollback logic exists inside the code but is not framed as an actionable workflow for the agent.

Suggestions

Move the strategy class implementations and MCP integration snippets into separate reference files (e.g. STRATEGIES.md, MCP_INTEGRATION.md) and keep SKILL.md as a concise overview that links to them.

Provide a short, explicit numbered workflow Claude can follow (assess network -> calculate quorum -> validate -> adjust -> verify -> rollback on failure) rather than burying it in class methods.

Either implement or stub the referenced helper classes (NetworkConditionMonitor, MembershipTracker, FaultToleranceCalculator, NetworkAnalyzer, etc.) so the code is actually runnable, or replace it with minimal executable examples.

DimensionReasoningScore

Conciseness

The body is an ~800-line dump of full JavaScript class implementations (QuorumManager plus three strategy classes) that reads like a codebase rather than concise skill guidance, matching 'noticeably verbose; several unnecessary padded sections'.

2 / 5

Actionability

Concrete-looking code is provided but it is not executable: it depends on dozens of undefined classes (NetworkAnalyzer, ConnectivityMatrix, PartitionPredictor, MembershipTracker) and undefined this.mcpTools.* methods, fitting 'some concrete guidance but incomplete; pseudocode instead of executable code'.

3 / 5

Workflow Clarity

A sequenced workflow with validation (validateQuorumConfiguration, verifyQuorumAdjustment) and rollback exists inside adjustQuorum, but it is embedded in class methods rather than presented as agent-followable steps with explicit checkpoints, fitting 'steps listed but validation gaps / checkpoints implicit'.

3 / 5

Progressive Disclosure

All content is inlined into a single monolithic SKILL.md with no references to separate files; the large strategy implementations and MCP integration clearly belong in reference files but are not split out, matching 'content that clearly belongs in separate files is inlined'.

2 / 5

Total

10

/

20

Passed

Description

28%Weight 40%Scale 1-5

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 thin auto-generated wrapper that names the quorum-manager domain but states no concrete capabilities and gives no usage triggers. It fails to answer when Claude should invoke the skill.

Suggestions

Replace the boilerplate with concrete actions, e.g. 'Calculates dynamic quorum sizes, manages cluster membership, and adjusts voting weights for distributed consensus protocols.'

Add an explicit 'Use when...' clause with natural trigger phrases such as 'quorum calculation', 'membership changes', 'consensus fault tolerance', or 'weighted voting'.

Drop the 'invoke with $agent-quorum-manager' invocation syntax from the description; it is not a user-facing trigger term.

DimensionReasoningScore

Specificity

The phrase 'Agent skill for quorum-manager' names a specific domain but provides no concrete actions at all, matching the score-2 anchor ('Names the domain but actions are minimal or generic') rather than score 1 only because a distinct domain is named.

2 / 5

Completeness

It offers only a vague 'what' ('Agent skill for quorum-manager') and no 'when'/Use-when clause at all, fitting the score-2 anchor ('Has a vague what and no when'); the missing trigger guidance also caps completeness below 4.

2 / 5

Trigger Term Quality

Only the single keyword 'quorum' appears; 'invoke with $agent-quorum-manager' is invocation syntax rather than a natural user phrase, so natural trigger terms users would actually say are missing (score-2 anchor).

2 / 5

Distinctiveness Conflict Risk

'quorum-manager' names a fairly specific distributed-consensus niche, but the generic wrapper phrasing and absence of distinct triggers leave overlap risk with related consensus/coordination skills (score-3 anchor).

3 / 5

Total

9

/

20

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/ruflo
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.