CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-byzantine-coordinator

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

46

1.06x
Quality

18%

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

30%

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

The body is well-organized and reasonably lean, but it is a descriptive capability catalog rather than actionable guidance: it lacks executable code, a sequenced consensus workflow, and validation checkpoints. Progressive disclosure is fine given the small, single-file scope.

Suggestions

Add executable examples or concrete commands for the core tasks (e.g., how to run a PBFT round, how to authenticate a message) instead of only describing them.

Sequence the consensus process as numbered steps with explicit validation checkpoints (e.g., validate signatures -> confirm quorum -> commit), especially around view changes.

Remove the redundant embedded YAML config block or move it to a reference file, since its description and capabilities duplicate the markdown sections.

DimensionReasoningScore

Conciseness

The body is mostly lean bullet lists rather than padded prose, but the second embedded YAML block duplicates the description/capabilities already covered in the markdown and could be tightened, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the fully lean score-3 anchor.

2 / 3

Actionability

The body describes capabilities abstractly ('Deploy PBFT three-phase protocol', 'Implement zero-knowledge proofs') with no executable code or concrete commands for the core consensus task, matching 'describes rather than instructs'; the only concrete bash is trivial hook echo statements, not actionable skill guidance.

1 / 3

Workflow Clarity

Although PBFT is described as 'three-phase', the phases are not sequenced as steps and there are no validation checkpoints or feedback loops for the risky view-change/consensus operations, matching 'steps unclear or missing; no sequence; no validation'.

1 / 3

Progressive Disclosure

The skill is under 50 lines, self-contained with no bundle files, and organized into clearly labeled sections (Core Responsibilities, Implementation Approach, Collaboration), so per the simple-skills note it earns full marks on organization alone.

3 / 3

Total

7

/

12

Passed

Description

7%

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 auto-generated boilerplate that names the skill but conveys no concrete capabilities or natural trigger guidance, leaving both 'what' and 'when' essentially unstated. It is narrowly niche-named yet indistinguishable in form from other agent-skill descriptions.

Suggestions

Replace the boilerplate with the actual capability, e.g. 'Coordinates Byzantine fault-tolerant consensus protocols, detects malicious actors, and manages view changes and message authentication.'

Add a 'Use when...' clause with natural trigger terms users would say, e.g. 'Use when the user needs Byzantine consensus, fault-tolerant voting, or malicious-node detection.'

Use third-person action verbs ('Coordinates', 'Detects') instead of the meta 'invoke with $agent-byzantine-coordinator' phrasing.

DimensionReasoningScore

Specificity

The description ('Agent skill for byzantine-coordinator - invoke with $agent-byzantine-coordinator') names a domain but lists no concrete actions whatsoever, matching the 'vague or no actions; abstract language' anchor rather than the score-2 anchor which requires naming 'some actions'.

1 / 3

Completeness

It neither states what the skill concretely does (the actual consensus capability is absent) nor gives any 'Use when...' trigger guidance, so both 'what' and 'when' are very weak, matching the score-1 anchor.

1 / 3

Trigger Term Quality

'byzantine-coordinator' and '$agent-byzantine-coordinator' are technical jargon / an invocation directive rather than natural phrases a user would say, fitting the 'no natural keywords; technical jargon' anchor.

1 / 3

Distinctiveness Conflict Risk

The unique niche name makes it somewhat distinguishable from unrelated skills, but the boilerplate 'Agent skill for X - invoke with $X' pattern offers no distinct capability triggers, so it sits at 'somewhat specific but could overlap' rather than a clear niche.

2 / 3

Total

5

/

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.

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.