agent-raft-manager

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

0.96x

Quality

18%

Does it follow best practices?

Impact

90%

0.96x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-raft-manager/SKILL.md

Quality

Content

15%Weight 40%Scale 1-5

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 capability catalog rather than operational guidance: it describes what Raft does (much of which Claude already knows) without a single executable instruction, command, or ordered workflow. It also embeds a duplicate agent-config YAML block that reads as noise. It needs concrete procedures with validation checkpoints, or a decisive slim-down to a true overview pointing at reference files.

Suggestions

Replace descriptive bullets with executable guidance: concrete commands, code, or parameters for each operation (e.g., how to trigger an election, verify log consistency, add a node).

Sequence the operations into an ordered workflow with explicit validation checkpoints — especially for risky operations like membership changes and partition recovery, which currently have no verify step at all.

Remove the inlined agent-config YAML block or move it to a separate reference file; it duplicates frontmatter-style metadata and clutters the skill body. Also fix the typo "node addition$removal" (should be "addition/removal").

Dimension	Reasoning	Score
Conciseness	The body re-explains Raft concepts Claude already knows ("randomized timeout-based elections to prevent split votes", "Track commit index and apply entries to state machine") and carries a duplicated agent-config YAML block that adds noise. It is noticeably verbose with several padded descriptive sections, matching anchor 2 rather than anchor 3's "mostly efficient".	2 / 5
Actionability	Every bullet is an abstract description ("Coordinate randomized timeout-based leader selection", "Implement append entries protocol") with no code, commands, parameters, or concrete steps — it describes rather than instructs, exactly anchor 1. It is not anchor 2 because even high-level executable hints are absent.	1 / 5
Workflow Clarity	There is no sequence at all: content is grouped by responsibility category (election, replication, fault tolerance) rather than as an ordered process, and there are no validation checkpoints for risky cluster operations like membership changes or partition recovery. This matches anchor 1 (steps missing or incoherent; no validation), not anchor 2 which requires at least a rough sequence.	1 / 5
Progressive Disclosure	Sections are clearly headed and the skill needs no external references at this size, but the inlined second YAML frontmatter block (the raft-manager agent config with hooks) sits raw at the top of the body — structural content that belongs in a separate file or should be removed. This is anchor 3 (some structure, could be better organized), not 4 because that stray block is a significant organization gap.	3 / 5
	Total	7 / 20 Passed

Description

21%Weight 40%Scale 1-5

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 placeholder-quality meta-statement: it tells how to invoke the skill but not what the skill does or when to use it. It needs concrete capability actions (leader election, log replication, membership changes) and an explicit "Use when..." trigger clause. The Raft domain itself is distinctive, which is the only thing keeping it from scoring lower.

Suggestions

Replace the description with a third-person statement of capabilities, e.g., "Manages Raft consensus clusters: coordinates leader election, replicates logs across followers, and handles membership changes."

Add an explicit trigger clause: "Use when working with Raft consensus, leader elections, log replication, or distributed cluster consistency."

Remove the meta-invocation text ("invoke with $agent-raft-manager") — it is not a capability and wastes the description's purpose as a trigger surface.

Dimension	Reasoning	Score
Specificity	The description names the domain ("raft-manager") but lists no concrete capability actions — it only says "Agent skill for raft-manager - invoke with $agent-raft-manager", describing invocation rather than what the skill does. It sits at anchor 2 (domain named, actions minimal/generic), below anchor 3 which requires 1-2 concrete actions.	2 / 5
Completeness	The "what" is vague (an agent skill for raft-manager, with no stated capabilities) and the "when" is entirely absent — anchor 2 (vague what, no when). It is not a 3 because the what never states any actual actions, and the missing "Use when..." clause caps it at 3 regardless.	2 / 5
Trigger Term Quality	There are no natural keywords a user would say (e.g., "leader election", "log replication", "consensus"); the only terms are meta-jargon ("Agent skill", "invoke with $agent-raft-manager"). This matches anchor 1 (no natural keywords; only technical jargon), not anchor 2 which expects at least one or two generic domain keywords.	1 / 5
Distinctiveness Conflict Risk	The Raft consensus domain is a fairly distinct niche, so it would not broadly conflict with unrelated skills, but the description provides no capability or trigger information to distinguish it from other distributed-coordination skills. This is anchor 3 (somewhat specific but could overlap with similar skills), not 4 which requires mostly distinct trigger phrasing.	3 / 5
	Total	8 / 20 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/ruflo
Path: .agents/skills/agent-raft-manager/SKILL.md
Commit: b14c79e

Reviewed: 3 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.