agent-raft-manager

Agent skill for raft-manager - invoke with $agent-raft-manager

0.96x

Quality

Does it follow best practices?

Impact

90%

0.96x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-raft-manager/SKILL.md

Quality

Content

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

This skill is entirely abstract and descriptive, reading like a high-level architecture overview rather than an actionable skill. It explains what Raft consensus is and lists its components—information Claude already knows—without providing any concrete commands, code, configurations, or step-by-step workflows. It fails on all dimensions: it's verbose with known concepts, provides no executable guidance, lacks sequenced workflows with validation, and has no progressive disclosure structure.

Suggestions

Replace abstract descriptions with concrete, executable code or commands for each core operation (e.g., actual election trigger commands, log replication API calls, specific configuration files).

Add step-by-step workflows with explicit validation checkpoints for critical operations like leader election and node recovery, including error handling and retry logic.

Remove explanations of Raft concepts Claude already knows and focus only on project-specific implementation details, tool usage, and configuration.

Either create supporting bundle files for detailed protocols (e.g., ELECTION.md, REPLICATION.md) with clear references, or consolidate into a lean single file with concrete guidance.

Dimension	Reasoning	Score
Conciseness	The content is verbose and describes concepts Claude already understands (Raft consensus, leader election, log replication). It reads like a high-level design document rather than actionable instructions, with padded bullet points that restate well-known Raft concepts without adding novel information.	1 / 3
Actionability	There are no concrete commands, executable code, specific configurations, or copy-paste ready examples. The entire skill is abstract descriptions like 'Execute randomized timeout-based elections' and 'Implement append entries protocol' without any actual implementation guidance, tool invocations, or specific steps.	1 / 3
Workflow Clarity	There is no clear sequenced workflow for any operation. The content lists responsibilities and features as bullet points but never defines a step-by-step process for leader election, log replication, or recovery. No validation checkpoints or feedback loops are present despite these being critical distributed systems operations.	1 / 3
Progressive Disclosure	The content is a monolithic block of abstract descriptions with no references to supporting files, no bundle files exist, and the sections don't progressively reveal detail. The 'Collaboration' section references other managers but provides no links or paths to actual resources.	1 / 3
	Total	4 / 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.

This description is critically deficient across all dimensions. It functions only as an invocation reference ('invoke with $agent-raft-manager') rather than a skill description, providing zero information about capabilities, use cases, or trigger conditions. It would be essentially unusable for skill selection among multiple available skills.

Suggestions

Add concrete actions describing what raft-manager does (e.g., 'Manages Raft consensus protocol configurations, monitors cluster health, handles leader election and log replication').

Add an explicit 'Use when...' clause with natural trigger terms users would say when needing this skill (e.g., 'Use when the user needs to configure distributed consensus, manage cluster membership, or troubleshoot Raft protocol issues').

Remove the invocation instruction ('invoke with $agent-raft-manager') from the description field, as it is operational metadata rather than a description of capabilities.

Dimension	Reasoning	Score
Specificity	The description provides no concrete actions whatsoever. 'Agent skill for raft-manager' is entirely vague and does not describe what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states it's an agent skill and how to invoke it, providing no functional or contextual information.	1 / 3
Trigger Term Quality	The only keyword is 'raft-manager', which is a technical/internal name unlikely to be naturally used by users. There are no natural language trigger terms describing tasks or problems.	1 / 3
Distinctiveness Conflict Risk	The description is so vague that it provides no distinguishing characteristics. Without knowing what 'raft-manager' does, Claude cannot differentiate this from any other agent skill.	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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/ruflo
Commit: 28c81c0

Reviewed: about 20 hours 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.