CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-byzantine-coordinator

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

37

1.06x
Quality

3%

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
SKILL.md
Quality
Evals
Security

Quality

Content

7%Scale 1-3

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

This skill reads as a high-level architectural description rather than an actionable skill. It lists capabilities and responsibilities in abstract terms without providing any concrete code, commands, algorithms, or step-by-step workflows. For a coordinator skill involving complex multi-phase consensus protocols, the complete absence of executable guidance, validation steps, and concrete examples makes it essentially unusable as an instruction set.

Suggestions

Add concrete, executable code examples for at least the core PBFT three-phase protocol (pre-prepare, prepare, commit) with specific message formats and validation logic.

Define a clear step-by-step workflow for consensus rounds with explicit validation checkpoints (e.g., 'Verify 2f+1 matching prepare messages before entering commit phase').

Include specific examples of malicious behavior detection patterns with concrete detection logic rather than abstract descriptions.

Remove or replace vague bullet points like 'Implement zero-knowledge proofs for vote verification' with actual implementation guidance or remove claims about capabilities that aren't backed by actionable instructions.

DimensionReasoningScore

Conciseness

The content is verbose and abstract, listing high-level concepts (PBFT, zero-knowledge proofs, threshold signatures, DoS protection) without any concrete implementation details. It reads like a feature brochure rather than actionable instructions, and explains concepts Claude already understands without adding novel, specific guidance.

1 / 3

Actionability

There is no executable code, no concrete commands, no specific examples, and no copy-paste ready guidance. Every bullet point is a vague description ('Deploy PBFT three-phase protocol', 'Implement zero-knowledge proofs') with no actual implementation steps or code.

1 / 3

Workflow Clarity

Despite describing a multi-phase consensus protocol (which inherently requires clear sequencing and validation checkpoints), there are no sequenced steps, no validation checkpoints, no error recovery flows, and no feedback loops. The content merely lists responsibilities without defining how to execute them.

1 / 3

Progressive Disclosure

The content has some structural organization with headers and subsections, but there are no references to external files, no bundle files to support deeper content, and the collaboration section references other components without linking to them. The structure is reasonable but the content that exists is all at the same shallow level.

2 / 3

Total

5

/

12

Passed

Description

0%Scale 1-3

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 non-functional. It provides only an invocation command and an opaque name ('byzantine-coordinator') with zero information about what the skill does, what domain it operates in, or when it should be used. Claude would have no basis for selecting this skill from a list of available skills.

Suggestions

Add a clear statement of what the skill does with concrete actions (e.g., 'Coordinates distributed consensus across Byzantine fault-tolerant systems' or whatever the actual functionality is).

Add an explicit 'Use when...' clause with natural trigger terms that describe the scenarios and user requests that should activate this skill.

Replace the generic 'Agent skill for' prefix with a domain-specific description that distinguishes this skill from others.

DimensionReasoningScore

Specificity

The description contains no concrete actions whatsoever. It only names a tool ('byzantine-coordinator') without describing what it does. 'Agent skill' is completely vague.

1 / 3

Completeness

Neither 'what does this do' nor 'when should Claude use it' is answered. The description only provides invocation syntax, not purpose or trigger conditions.

1 / 3

Trigger Term Quality

There are no natural keywords a user would say. 'Byzantine-coordinator' is an opaque internal name that provides no clue about the skill's domain or functionality.

1 / 3

Distinctiveness Conflict Risk

Without any description of what the skill does, it's impossible to distinguish it from other skills. Claude would have no basis for selecting or avoiding this skill.

1 / 3

Total

4

/

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

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.