CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-gossip-coordinator

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

46

1.03x
Quality

21%

Does it follow best practices?

Impact

85%

1.03x

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-gossip-coordinator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%

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

The body reads like a high-level concept map of gossip protocols rather than actionable skill instructions: it lists abstract responsibilities without any concrete commands, code, or verification steps. Organization is clean, but it lacks the executable guidance that makes a skill useful.

Suggestions

Replace abstract directives with concrete, executable guidance, e.g. specific fanout parameters, a reference gossip-round pseudocode block, or commands/libraries for convergence testing.

Add validation checkpoints for risky operations such as conflict resolution and convergence monitoring (e.g., 'verify vector-clock invariants before committing merged state').

Cut the conceptual restatement of known ideas (what push/pull gossip or Merkle trees are) and keep only the non-obvious protocol-specific decisions Claude would not infer.

DimensionReasoningScore

Conciseness

The body is reasonably lean with short bulleted lists, but it largely re-describes well-known distributed systems concepts (push/pull gossip, Merkle trees, vector clocks) that Claude already understands without adding novel instruction.

2 / 3

Actionability

Every item is an abstract directive ('Implement', 'Execute', 'Manage') with no concrete code, commands, parameters, or worked examples; it describes what to do rather than how to do it.

1 / 3

Workflow Clarity

Responsibilities and implementation areas are grouped into a recognizable sequence, but there are no concrete steps, no executable commands, and no validation checkpoints for operations (e.g., convergence monitoring, conflict resolution) that warrant verification.

2 / 3

Progressive Disclosure

The skill is a compact single-file overview with no bundle files and clearly organized sections; for a short skill with no external references needed, this structure is appropriately navigable.

3 / 3

Total

8

/

12

Passed

Description

0%

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 boilerplate auto-generated label that fails to communicate the skill's purpose, concrete actions, or usage triggers. It reads as metadata rather than a genuine capability description.

Suggestions

Replace the boilerplate with a real description of capabilities, e.g. 'Coordinates gossip-based consensus protocols: epidemic dissemination, peer selection, and state synchronization for eventually consistent distributed systems.'

Add an explicit trigger clause such as 'Use when designing or debugging gossip protocols, anti-entropy synchronization, or scalable eventual-consistency systems.'

Avoid presenting the raw '$agent-gossip-coordinator' invocation token as the description; surface natural user-facing keywords like 'gossip protocol', 'epidemic dissemination', and 'eventual consistency' instead.

DimensionReasoningScore

Specificity

The description 'Agent skill for gossip-coordinator - invoke with $agent-gossip-coordinator' names only the skill's identity, not any concrete actions it performs.

1 / 3

Completeness

It conveys neither what the skill does (no actions stated) nor when to use it (no 'Use when...' clause or equivalent trigger guidance).

1 / 3

Trigger Term Quality

The only trigger term is the literal invocation token '$agent-gossip-coordinator'; there are no natural keywords a user would actually say when they need gossip consensus protocols.

1 / 3

Distinctiveness Conflict Risk

The text is purely a generic invocation label with no domain-specific triggers, making it indistinguishable from any other agent skill and likely to conflict.

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.

Validation16 / 16 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.