CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-byzantine-coordinator

Agent skill for byzantine-coordinator - invoke with $agent-byzantine-coordinator

54

1.06x
Quality

31%

Does it follow best practices?

Impact

94%

1.06x

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-byzantine-coordinator/SKILL.md

The canonical home for this skill is agent-byzantine-coordinator in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

Quality

Content

51%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 content is well-structured and token-efficient but functions as a capability description rather than actionable guidance: it lists what the coordinator does without executable steps, a sequenced protocol workflow, or validation checkpoints for these risky consensus operations.

Suggestions

Add a concrete, sequenced PBFT workflow (e.g. pre-prepare -> prepare -> commit -> view-change) with explicit validation checkpoints for detecting and isolating malicious nodes.

Replace abstract directives ('Deploy...', 'Implement...') with concrete, executable guidance such as message formats, signature schemes, or command/protocol steps Claude can follow.

Resolve the duplication between the YAML capabilities block and the 'Core Responsibilities' list so each piece of information appears once.

DimensionReasoningScore

Conciseness

The body is mostly lean bullet points that assume Claude's competence without explaining Byzantine fault tolerance basics; the only minor trim is the capability list duplicated between the YAML block and the 'Core Responsibilities' section.

4 / 5

Actionability

Directives like 'Deploy PBFT three-phase protocol' and 'Implement threshold signature schemes' are high-level hints with no executable code, commands, or specific steps, matching the 'minimal concrete guidance; high-level hints' anchor rather than the entirely-abstract score 1.

2 / 5

Workflow Clarity

There is no sequenced workflow or validation checkpoints; only a numbered category list and an implied three-phase structure, fitting 'rough sequence present but many gaps; validation absent'.

2 / 5

Progressive Disclosure

The body is under 50 lines with no need for external references and is cleanly organized into Core Responsibilities, Implementation Approach, and Collaboration sections, qualifying for the simple-skill exception to score 5.

5 / 5

Total

13

/

20

Passed

Description

12%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.

This is a templated, metadata-style description that names the skill domain but conveys no capabilities, no natural trigger phrases, and no usage guidance. It fails to tell Claude what the skill does or when to invoke it.

Suggestions

Replace the template text with concrete actions the skill performs, e.g. 'Coordinates PBFT consensus, detects malicious nodes, and manages view changes'.

Add an explicit 'Use when...' clause naming natural trigger phrases a user would say, such as 'Use when implementing Byzantine fault-tolerant consensus or detecting malicious actors in a distributed protocol.'

Use third-person action voice ('Coordinates...', 'Detects...') instead of the generic 'Agent skill for X - invoke with $X' framing.

DimensionReasoningScore

Specificity

The phrase 'Agent skill for byzantine-coordinator' names a specific domain but states no concrete actions whatsoever, fitting the 'names the domain but actions are minimal or generic' anchor better than the entirely-vague score 1.

2 / 5

Completeness

It answers neither 'what does this do' (no actions described) nor 'when should Claude use it' (no 'Use when...' clause), matching the 'missing both what and when' anchor.

1 / 5

Trigger Term Quality

Only the technical jargon 'byzantine-coordinator' and the invocation syntax '$agent-byzantine-coordinator' appear; there are no natural keywords a user would actually say, matching the 'only technical jargon' anchor.

1 / 5

Distinctiveness Conflict Risk

The niche domain name 'byzantine-coordinator' is somewhat specific, but the generic 'Agent skill for X' framing with no distinct trigger guidance leaves overlap risk with other coordinator/consensus skills.

3 / 5

Total

7

/

20

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.