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

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 a high-level conceptual catalog of Raft responsibilities with no executable guidance or sequenced workflow, plus a stray duplicate YAML frontmatter block embedded in the content. Its only strength is clean section organization in a short, self-contained file.

Suggestions

Replace conceptual restatements of Raft with concrete, skill-specific instructions or executable commands (e.g., actual election/replication invocation steps).

Provide a numbered workflow with explicit validation checkpoints for risky operations such as leader election, log replication, and membership changes.

Remove the duplicate YAML frontmatter block (lines 6-29) embedded in the body; consolidate metadata into the single real frontmatter and keep the body as pure instructional markdown.

Dimension	Reasoning	Score
Conciseness	The body is brief and section-organized, but it restates well-known Raft mechanics ('randomized timeout-based elections', 'append entries protocol', 'snapshotting') that Claude already knows, so it could be tightened toward skill-specific operational knowledge.	2 / 3
Actionability	There is no executable code or commands anywhere; lines like 'Implement append entries protocol' and 'Track commit index and apply entries to state machine' describe rather than instruct, and a typo 'node addition$removal' further signals unexecutable guidance.	1 / 3
Workflow Clarity	The bullets are a feature catalog, not a sequenced workflow; there is no ordered process and no validation checkpoints for risky consensus operations like elections or membership changes.	1 / 3
Progressive Disclosure	The skill is under 50 lines, has no external references, and is organized into clear sections (Core Responsibilities, Implementation Approach, Collaboration), meeting the simple-skill allowance for a top score without separate files.	3 / 3
	Total	7 / 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 generic meta-label plus invocation syntax rather than a capability-and-trigger statement; it fails to say what the skill does or when to invoke it. It is distinguishable only because 'raft-manager' names a specific niche.

Suggestions

Replace the meta label with concrete capabilities, e.g. 'Manages Raft consensus: leader election, log replication, and membership changes.'

Add an explicit 'Use when...' trigger clause covering natural user phrasing such as 'Raft consensus', 'leader election', or 'log replication'.

Drop the 'invoke with $agent-raft-manager' invocation syntax from the description; triggers belong in the description, not invocation mechanics.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for raft-manager - invoke with $agent-raft-manager' names no concrete actions; it only labels the artifact as an 'agent skill for' a named component, matching the vague/no-actions anchor.	1 / 3
Completeness	It answers neither 'what does this do' (only 'agent skill for raft-manager') nor 'when to use it' (the '- invoke with $...' clause is invocation syntax, not a 'Use when...' trigger), so both halves are weak.	1 / 3
Trigger Term Quality	The only term is the technical jargon 'raft-manager' with an invocation syntax '$agent-raft-manager'; there are no natural user phrases like 'Raft consensus', 'leader election', or 'log replication' that a user would actually say.	1 / 3
Distinctiveness Conflict Risk	'raft-manager' names a specific niche unlikely to broadly conflict, but the description carries no distinct trigger phrasing, so it could still overlap with neighboring distributed-systems skills.	2 / 3
	Total	5 / 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.