Name: agent-performance-monitor
Rating: 46.400000000000006 (1 reviews)
Author: ruvnet

Blog Docs Log in Get started

agent-performance-monitor

Agent skill for performance-monitor - invoke with $agent-performance-monitor

2.43x

Quality

17%

Does it follow best practices?

Impact

100%

2.43x

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-performance-monitor/SKILL.md

The canonical home for this skill is agent-performance-monitor in ruvnet/claude-flow

Quality

Content

25%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 content presents an elaborate monitoring architecture as stubbed JavaScript classes with undefined dependencies rather than actionable, executable guidance. It is verbose, lacks a clear sequenced workflow with validation, and inlines material that should live in separate reference files.

Suggestions

Replace the stubbed class skeletons with a concise operational workflow: how to invoke metrics collection, how to interpret the report, and concrete next-step actions.

Move the long code samples into bundled reference files (e.g. references/metrics.md, references/anomaly-detection.md) and keep SKILL.md as a lean overview that links one level deep.

Add validation/feedback checkpoints for any monitoring action that triggers alerts or escalations, so Claude can confirm a violation before acting.

Dimension	Reasoning	Score
Conciseness	The body is a ~450-line wall of JavaScript class skeletons with stubbed helper methods that Claude could write itself; it heavily pads the context with illustrative code rather than lean, decision-relevant guidance.	2 / 5
Actionability	Most code references undefined helpers (e.g. mcp.agent_metrics, this.calculateEfficiency) and unimplemented classes (CPUBottleneckDetector), so it reads as a structural sketch rather than executable, copy-paste-ready guidance; the bash commands are the only genuinely runnable parts.	2 / 5
Workflow Clarity	Capabilities are presented as parallel modules with no sequenced workflow, and monitoring/anomaly operations that act on production systems lack any validation checkpoints or feedback loops; the destructive/batch cap is not needed because the baseline is already low.	2 / 5
Progressive Disclosure	No bundle files exist and all material is inlined into one monolithic SKILL.md; the large code reference blocks clearly belong in separate reference files but are instead crammed inline with minimal navigational signaling.	2 / 5
	Total	8 / 20 Passed

Description

10%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 effectively a placeholder: it identifies the skill name and invocation token but states no capabilities, no concrete actions, and no usage triggers. It fails to tell Claude what the skill does or when to invoke it.

Suggestions

Replace the placeholder with concrete actions, e.g. 'Collect real-time system and agent metrics, detect bottlenecks, monitor SLA compliance, and surface anomalies.'

Add an explicit 'Use when...' clause with natural trigger phrases such as 'when the user asks about performance, bottlenecks, SLA violations, or resource utilization'.

Use third person and avoid the raw invoke token in the description so it reads as a capability statement rather than a wiring hint.

Dimension	Reasoning	Score
Specificity	The description 'Agent skill for performance-monitor - invoke with $agent-performance-monitor' names no concrete actions whatsoever; it only states it is an 'agent skill' and gives an invocation hint.	1 / 5
Completeness	There is neither a clear 'what does this do' (no actions stated) nor any 'when should Claude use it' guidance; the guideline caps completeness at 3 for missing triggers, but here even the 'what' is entirely missing.	1 / 5
Trigger Term Quality	'performance-monitor' and the invoke token are the only terms; users might say 'monitor performance' but natural trigger phrases like 'bottleneck', 'SLA', 'metrics', or 'anomaly detection' are absent, placing it just below the midpoint.	2 / 5
Distinctiveness Conflict Risk	The label 'performance-monitor' is narrowly scoped and unlikely to collide with unrelated skills, but the total absence of distinguishing actions makes it hard to tell apart from any other monitoring agent, leaving it slightly below the midpoint.	2 / 5
	Total	6 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (677 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: ruvnet/ruflo
Path: .agents/skills/agent-performance-monitor/SKILL.md
Commit: fa13ee4

Reviewed: about 5 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.