agent-gossip-coordinator

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

1.03x

Quality

—

Does it follow best practices?

Impact

85%

1.03x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

22%

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

The body is a high-level catalog of gossip-protocol responsibilities rather than executable instruction: it lists categories with no code, commands, sequenced workflow, or validation steps. A duplicated YAML config block at the top adds noise that should be removed.

Suggestions

Remove the redundant YAML agent-definition block from the body; keep configuration only in the frontmatter.

Add concrete, executable guidance — e.g. sample gossip fanout/push-pull code, the peer-selection parameters, or the Merkle-tree comparison command — instead of descriptive bullets.

Provide an ordered workflow with validation checkpoints (e.g. disseminate -> reconcile via Merkle diff -> resolve conflicts -> verify convergence), which is essential for these batch/synchronization operations.

Dimension	Reasoning	Score
Conciseness	The bullet sections are fairly lean, but the body opens with a duplicated YAML agent-definition block (lines 6-29) that is redundant with the frontmatter, and it redescribes well-known concepts (Merkle trees, vector clocks, anti-entropy); matches 'Mostly efficient but includes some unnecessary explanation'. Not score 3 because of the redundant YAML block and the 'push$pull' typo.	2 / 3
Actionability	Every item is a descriptive imperative ('Deploy push gossip protocol', 'Execute Merkle tree comparison') with no code, commands, parameters, or concrete configuration; matches 'Vague or abstract; no concrete code/commands; describes rather than instructs'. Not score 2 because nothing is executable.	1 / 3
Workflow Clarity	Content is organized by category (Dissemination, Anti-Entropy, Membership) rather than as a sequenced procedure; the numbered 'Core Responsibilities' list enumerates topics, not steps, and there are no validation checkpoints for the risky sync/conflict operations. Matches 'Steps unclear or missing; no sequence for multi-step tasks'.	1 / 3
Progressive Disclosure	Sections are organized under clear headers with no nested references, and no bundle files exist to dereference, but the duplicated agent-config YAML block is content that should not be inline in the body; matches 'Some structure but could be better organized; content that should be separate is inline'. Not score 3 because of that misplaced block.	2 / 3
	Total	6 / 12 Passed

Description

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 frontmatter description is a templated placeholder that names a topic but states no concrete capabilities and gives no 'when to use' guidance. It fails to inform the model or a user what the skill actually does or when to invoke it.

Suggestions

Replace the placeholder with a real description, e.g. 'Coordinates gossip-based consensus protocols (epidemic dissemination, peer selection, vector-clock synchronization) for eventually consistent distributed systems.'

Add an explicit trigger clause: 'Use when building or debugging gossip/epidemic protocols, peer-to-peer state synchronization, or eventual-consistency convergence.'

Drop the 'Agent skill for ... - invoke with $...' boilerplate so the description reads as a standalone capability statement in third person.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for gossip-coordinator' names only a topic label, not any concrete actions; it matches the 'Vague or no actions; abstract language' anchor ('Helps with documents'). It is not score 2 because no domain actions are enumerated.	1 / 3
Completeness	It states only that this is an 'Agent skill for gossip-coordinator' (a label, not a description of what it does) and entirely lacks a 'Use when...' clause; per guidelines a missing trigger clause caps completeness at 2, and here 'what' is also weak, so it falls to 1.	1 / 3
Trigger Term Quality	The only trigger phrase is 'invoke with $agent-gossip-coordinator', a technical invocation mechanism rather than natural keywords a user would say; matches 'No natural keywords; technical jargon or overly generic'. It is not score 2 because no common user-facing variations are present.	1 / 3
Distinctiveness Conflict Risk	The boilerplate 'Agent skill for X - invoke with $X' pattern is generic and would collide with any other similarly templated skill; matches 'Very generic; would conflict with many skills'. Not score 2 because nothing distinguishes its niche.	1 / 3
	Total	4 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: 03d4f84

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.